{ "themes": [ { "id": "predictions", "name": "Learning with predictions", "short": "Predictions", "icon": "chart-line", "question": "When should a decision maker trust a prediction?", "description": "Algorithms that benefit from accurate advice while limiting the cost of errors. This thread studies consistency, robustness, competitive analysis, and the value of different forms of predictive information.", "keywords": [ "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization" ] }, { "id": "control", "name": "Safe and distributed control", "short": "Control", "icon": "sliders-h", "question": "How can a controller learn while preserving reliable operation?", "description": "Predictive control with performance and feasibility guarantees. The work spans perturbation analysis, nonlinear policy certification, aggregate flexibility, and distributed system level synthesis.", "keywords": [ "model predictive control", "MPC", "stability", "recursive feasibility", "distributed control", "system level synthesis" ] }, { "id": "agents", "name": "Language and decision agents", "short": "Agents", "icon": "comment-dots", "question": "How can language and world models support dependable decisions?", "description": "Language models provide context, preferences, and predictions for sequential decisions. Algorithmic guidance and structural certification connect these capabilities to explicit performance guarantees.", "keywords": [ "large language models", "LLM agents", "contextual control", "world models", "reinforcement learning", "dueling bandits" ] }, { "id": "energy", "name": "Energy and infrastructure", "short": "Energy", "icon": "bolt", "question": "How can intelligent infrastructure use energy more effectively?", "description": "Control and learning for electric vehicle charging, renewable integration, demand forecasting, water systems, and grid coordination. Physical constraints and changing operating conditions shape the algorithms.", "keywords": [ "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization" ] }, { "id": "games", "name": "Strategic and equitable learning", "short": "Games and equity", "icon": "balance-scale", "question": "What changes when decisions affect other decision makers?", "description": "Learning and optimization with interacting agents. This work examines uncertain beliefs, strategic advice, equilibrium, and the distribution of benefits from shared predictive models.", "keywords": [ "game theory", "learning in games", "Bayesian games", "Stackelberg strategies", "equity", "public models" ] }, { "id": "structure", "name": "Information and network learning", "short": "Information", "icon": "project-diagram", "question": "What information and structure are needed to learn reliably?", "description": "Information limits and structured learning, from group testing and communication channels to graph recovery and adaptive graph geometry. These results connect limited measurements to useful representations.", "keywords": [ "information theory", "graph learning", "sample complexity", "compressed sensing", "graph neural networks", "Riemannian geometry" ] } ], "papers": [ { "id": "argnn", "title": "Adaptive Riemannian Graph Neural Networks", "authors": [ "Xudong Wang", "Chris Ding", "Tongxin Li", "Jicong Fan" ], "year": 2026, "venue": "AAAI", "publication": "Proceedings of the AAAI Conference on Artificial Intelligence", "doi": "10.1609/aaai.v40i31.39869", "themes": [ "structure" ], "question": "How can a graph model adapt to different local geometries?", "summary": "ARGNN learns a node specific Riemannian metric instead of imposing one fixed curvature on an entire graph. A diagonal metric parameterization and geometric regularization support efficient training, with convergence analysis and experiments on homophilic and heterophilic graphs.", "path": "/research/papers/argnn/", "entry_type": "inproceedings", "primary_url": "https://doi.org/10.1609/aaai.v40i31.39869", "theme_names": [ "Information and network learning" ], "keywords": [ "information theory", "graph learning", "sample complexity", "compressed sensing", "graph neural networks", "Riemannian geometry" ], "citation": "Xudong Wang, Chris Ding, Tongxin Li, Jicong Fan. Adaptive Riemannian Graph Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 2026. https://doi.org/10.1609/aaai.v40i31.39869", "canonical_url": "https://tongxin.me/research/papers/argnn/" }, { "id": "counterfactual-load", "title": "Counterfactual load forecasting with LLM-structured events and representation learning", "authors": [ "Yujie Chen", "Yifei Gao", "Runyao Yu", "Yuhe Wu", "Guangyu Wang", "Yue Chen", "Tongxin Li" ], "year": 2026, "venue": "Applied Energy", "publication": "Applied Energy", "doi": "10.1016/j.apenergy.2026.128554", "project": "https://yujiechen8888.github.io/counterfactual-load-forecasting-web/", "themes": [ "energy", "agents" ], "question": "How might electricity demand change under a different news event?", "summary": "NACF turns news into structured treatments and estimates load trajectories under alternative event conditions. Reweighting and representation balancing address observed confounding. Experiments examine factual accuracy and interpretable demand perturbations without claiming that unobserved counterfactual outcomes can be directly validated.", "path": "/research/papers/counterfactual-load/", "entry_type": "article", "primary_url": "https://doi.org/10.1016/j.apenergy.2026.128554", "theme_names": [ "Energy and infrastructure", "Language and decision agents" ], "keywords": [ "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization", "large language models", "LLM agents", "contextual control", "world models", "reinforcement learning", "dueling bandits" ], "citation": "Yujie Chen, Yifei Gao, Runyao Yu, Yuhe Wu, Guangyu Wang, Yue Chen, Tongxin Li. Counterfactual load forecasting with LLM-structured events and representation learning. Applied Energy, 2026. https://doi.org/10.1016/j.apenergy.2026.128554", "canonical_url": "https://tongxin.me/research/papers/counterfactual-load/" }, { "id": "dualnilm", "title": "Energy Injection Identification enabled Disaggregation with Deep Multi-Task Learning", "authors": [ "Xudong Wang", "Guoming Tang", "Junyu Xue", "Srinivasan Keshav", "Tongxin Li", "Chris Ding" ], "year": 2026, "venue": "ACM e-Energy", "publication": "ACM International Conference on Future and Sustainable Energy Systems", "doi": "10.1145/3744255.3798113", "code": "https://github.com/MathAdventurer/PV-Augmented-NILM-Datasets", "themes": [ "energy", "structure" ], "question": "Can appliances be identified when solar and storage obscure meter readings?", "summary": "DualNILM jointly recognizes appliance states and identifies energy injected behind the meter. Its transformer architecture combines temporal learning tasks to separate consumption from injections, with evaluation on measured and synthesized datasets.", "path": "/research/papers/dualnilm/", "entry_type": "inproceedings", "primary_url": "https://doi.org/10.1145/3744255.3798113", "theme_names": [ "Energy and infrastructure", "Information and network learning" ], "keywords": [ "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization", "information theory", "graph learning", "sample complexity", "compressed sensing", "graph neural networks", "Riemannian geometry" ], "citation": "Xudong Wang, Guoming Tang, Junyu Xue, Srinivasan Keshav, Tongxin Li, Chris Ding. Energy Injection Identification enabled Disaggregation with Deep Multi-Task Learning. ACM International Conference on Future and Sustainable Energy Systems, 2026. https://doi.org/10.1145/3744255.3798113", "canonical_url": "https://tongxin.me/research/papers/dualnilm/" }, { "id": "strategic-advice", "title": "Leveraging Machine-Learned Advice in Strategic Interactions with No-Regret Learners", "authors": [ "Tinashe Handina", "Tongxin Li", "Kishan Panaganti", "Eric Mazumdar", "Adam Wierman" ], "year": 2026, "venue": "AISTATS", "publication": "Proceedings of the International Conference on Artificial Intelligence and Statistics", "url": "https://arxiv.org/abs/2606.10261", "pdf": "https://arxiv.org/pdf/2606.10261", "themes": [ "games", "predictions" ], "question": "How useful is imperfect advice against an adaptive opponent?", "summary": "A measure of advice quality connects simulators and payoff predictions to strategic performance. The paper establishes benefits of reliable advice for approximate Stackelberg play and limitations on simultaneously exploiting accurate advice and protecting against inaccurate advice.", "path": "/research/papers/strategic-advice/", "entry_type": "inproceedings", "primary_url": "https://arxiv.org/abs/2606.10261", "theme_names": [ "Strategic and equitable learning", "Learning with predictions" ], "keywords": [ "game theory", "learning in games", "Bayesian games", "Stackelberg strategies", "equity", "public models", "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization" ], "citation": "Tinashe Handina, Tongxin Li, Kishan Panaganti, Eric Mazumdar, Adam Wierman. Leveraging Machine-Learned Advice in Strategic Interactions with No-Regret Learners. Proceedings of the International Conference on Artificial Intelligence and Statistics, 2026. https://arxiv.org/abs/2606.10261", "canonical_url": "https://tongxin.me/research/papers/strategic-advice/" }, { "id": "pearl", "title": "PEARL: A Physics-Enhanced Adaptive Residual Learning Framework for PV Modeling", "authors": [ "Yikai Lu", "Yujie Chen", "Tongxin Li" ], "year": 2026, "venue": "IEEE PES International Meeting", "publication": "IEEE PES International Meeting", "doi": "10.1109/PESIM67009.2026.11438881", "themes": [ "energy", "predictions" ], "question": "Can learned residuals improve physical models of solar generation?", "summary": "PEARL separates a physical photovoltaic simulator from a learned residual correction. A controlled benchmark compares several machine learning architectures and a coupled modeling baseline, examining accuracy while retaining the physical model as an interpretable reference.", "path": "/research/papers/pearl/", "entry_type": "inproceedings", "primary_url": "https://doi.org/10.1109/PESIM67009.2026.11438881", "theme_names": [ "Energy and infrastructure", "Learning with predictions" ], "keywords": [ "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization", "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization" ], "citation": "Yikai Lu, Yujie Chen, Tongxin Li. PEARL: A Physics-Enhanced Adaptive Residual Learning Framework for PV Modeling. IEEE PES International Meeting, 2026. https://doi.org/10.1109/PESIM67009.2026.11438881", "canonical_url": "https://tongxin.me/research/papers/pearl/" }, { "id": "prediction-specific", "title": "Prediction-Specific Design of Learning-Augmented Algorithms", "authors": [ "Sizhe Li", "Nicolas Christianson", "Tongxin Li" ], "year": 2026, "venue": "POMACS", "publication": "Proceedings of the ACM on Measurement and Analysis of Computing Systems", "doi": "10.1145/3788100", "themes": [ "predictions" ], "versions": [ { "label": "SIGMETRICS 2026 abstract", "url": "https://doi.org/10.1145/3801489.3806913" } ], "question": "Can an algorithm be optimal for the particular prediction it receives?", "summary": "Strong optimality refines the usual consistency and robustness tradeoff to account for each prediction. A bilevel optimization framework constructs algorithms for ski rental and one max search, with case studies in power management and trading.", "path": "/research/papers/prediction-specific/", "entry_type": "article", "primary_url": "https://doi.org/10.1145/3788100", "theme_names": [ "Learning with predictions" ], "keywords": [ "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization" ], "citation": "Sizhe Li, Nicolas Christianson, Tongxin Li. Prediction-Specific Design of Learning-Augmented Algorithms. Proceedings of the ACM on Measurement and Analysis of Computing Systems, 2026. https://doi.org/10.1145/3788100", "canonical_url": "https://tongxin.me/research/papers/prediction-specific/" }, { "id": "quantum-coordination", "title": "Quantum Learning and Estimation for Coordinated Operation between Distribution Networks and Energy Communities", "authors": [ "Yingrui Zhuang", "Lin Cheng", "Yuji Cao", "Tongxin Li", "Ning Qi", "Yan Xu", "Yue Chen" ], "year": 2026, "venue": "CSEE JPES", "publication": "CSEE Journal of Power and Energy Systems", "doi": "10.17775/CSEEJPES.2025.05720", "url": "https://arxiv.org/abs/2506.11730", "pdf": "https://arxiv.org/pdf/2506.11730", "note": "Journal accepted version dated 2026. The first preprint appeared in 2025.", "themes": [ "energy", "structure" ], "question": "Can quantum methods assist coordination with limited local information?", "summary": "A hybrid quantum learning model estimates energy community responses to prices, while quantum amplitude estimation supports uncertainty calculations. Numerical studies assess accuracy and resource requirements. Reported timing advantages assume ideal quantum devices rather than deployed hardware.", "path": "/research/papers/quantum-coordination/", "entry_type": "article", "primary_url": "https://doi.org/10.17775/CSEEJPES.2025.05720", "theme_names": [ "Energy and infrastructure", "Information and network learning" ], "keywords": [ "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization", "information theory", "graph learning", "sample complexity", "compressed sensing", "graph neural networks", "Riemannian geometry" ], "citation": "Yingrui Zhuang, Lin Cheng, Yuji Cao, Tongxin Li, Ning Qi, Yan Xu, Yue Chen. Quantum Learning and Estimation for Coordinated Operation between Distribution Networks and Energy Communities. CSEE Journal of Power and Energy Systems, 2026. https://doi.org/10.17775/CSEEJPES.2025.05720", "canonical_url": "https://tongxin.me/research/papers/quantum-coordination/" }, { "id": "vigilmpc", "title": "VigilMPC: Certified Online Tube Model Predictive Control for Safe Real-Time Neuromodulation", "authors": [ "Yu Mao", "Zhichao Liang", "Junxiang Zhang", "Quanying Liu", "Tongxin Li" ], "year": 2026, "venue": "IEEE Control Systems Letters", "publication": "IEEE Control Systems Letters", "doi": "10.1109/LCSYS.2026.3711599", "themes": [ "control", "predictions" ], "question": "Can a predictive controller safely update its learned dynamics online?", "summary": "VigilMPC accepts a predictor update only when a backup plan remains feasible under tightened constraints. Recursive feasibility and constraint satisfaction follow under the tube MPC assumptions. Evaluation uses simulated neural dynamics and a switching benchmark, rather than clinical deployment.", "path": "/research/papers/vigilmpc/", "entry_type": "article", "primary_url": "https://doi.org/10.1109/LCSYS.2026.3711599", "theme_names": [ "Safe and distributed control", "Learning with predictions" ], "keywords": [ "model predictive control", "MPC", "stability", "recursive feasibility", "distributed control", "system level synthesis", "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization" ], "citation": "Yu Mao, Zhichao Liang, Junxiang Zhang, Quanying Liu, Tongxin Li. VigilMPC: Certified Online Tube Model Predictive Control for Safe Real-Time Neuromodulation. IEEE Control Systems Letters, 2026. https://doi.org/10.1109/LCSYS.2026.3711599", "canonical_url": "https://tongxin.me/research/papers/vigilmpc/" }, { "id": "world-models", "title": "World Models in Pieces: Structural Certification for General Agents", "authors": [ "Yikai Lu", "Yifei Wu", "Xinyu Lu", "Tongxin Li" ], "year": 2026, "venue": "ICML", "publication": "Proceedings of the International Conference on Machine Learning", "url": "https://arxiv.org/abs/2606.24842", "pdf": "https://arxiv.org/pdf/2606.24842", "themes": [ "agents", "structure" ], "question": "Which parts of an agent's world model can support reliable planning?", "summary": "Structural certification links performance on compositional goals to local guarantees on world model transitions. The results identify reliable pieces of a model without requiring universal competence, and establish limits on the precision of such guarantees.", "path": "/research/papers/world-models/", "entry_type": "inproceedings", "primary_url": "https://arxiv.org/abs/2606.24842", "theme_names": [ "Language and decision agents", "Information and network learning" ], "keywords": [ "large language models", "LLM agents", "contextual control", "world models", "reinforcement learning", "dueling bandits", "information theory", "graph learning", "sample complexity", "compressed sensing", "graph neural networks", "Riemannian geometry" ], "citation": "Yikai Lu, Yifei Wu, Xinyu Lu, Tongxin Li. World Models in Pieces: Structural Certification for General Agents. Proceedings of the International Conference on Machine Learning, 2026. https://arxiv.org/abs/2606.24842", "canonical_url": "https://tongxin.me/research/papers/world-models/" }, { "id": "lead", "title": "Beyond Numeric Rewards: In-Context Dueling Bandits with LLM Agents", "authors": [ "Fanzeng Xia", "Hao Liu", "Yisong Yue", "Tongxin Li" ], "year": 2025, "venue": "ACL Findings", "publication": "Findings of the Association for Computational Linguistics", "doi": "10.18653/v1/2025.findings-acl.519", "pdf": "https://aclanthology.org/2025.findings-acl.519.pdf", "themes": [ "agents", "predictions" ], "question": "Can language agents learn reliably from pairwise preferences?", "summary": "The study identifies a gap between quick preference discovery and sustained exploitation by language agents. LEAD combines LLM reasoning with dueling bandit algorithms to obtain weak and strong regret guarantees, with evaluations under noisy and adversarial prompts.", "path": "/research/papers/lead/", "entry_type": "inproceedings", "primary_url": "https://doi.org/10.18653/v1/2025.findings-acl.519", "theme_names": [ "Language and decision agents", "Learning with predictions" ], "keywords": [ "large language models", "LLM agents", "contextual control", "world models", "reinforcement learning", "dueling bandits", "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization" ], "citation": "Fanzeng Xia, Hao Liu, Yisong Yue, Tongxin Li. Beyond Numeric Rewards: In-Context Dueling Bandits with LLM Agents. Findings of the Association for Computational Linguistics, 2025. https://doi.org/10.18653/v1/2025.findings-acl.519", "canonical_url": "https://tongxin.me/research/papers/lead/" }, { "id": "coupled-networks", "title": "Hierarchical Game for Coupled Power System With Energy Sharing and Transportation System", "authors": [ "Dongxiang Yan", "Tongxin Li", "Changhong Zhao", "Han Wang", "Yue Chen" ], "year": 2025, "venue": "IEEE Transactions on Transportation Electrification", "publication": "IEEE Transactions on Transportation Electrification", "doi": "10.1109/TTE.2024.3398988", "themes": [ "energy", "games" ], "note": "Published online in 2024 and assigned to the February 2025 journal issue.", "question": "How do charging, traffic, and local energy trading influence one another?", "summary": "A hierarchical game couples an energy sharing mechanism with transportation decisions and power network constraints. The paper establishes properties of the energy sharing equilibrium and reformulates the coupled problem for numerical solution.", "path": "/research/papers/coupled-networks/", "entry_type": "article", "primary_url": "https://doi.org/10.1109/TTE.2024.3398988", "theme_names": [ "Energy and infrastructure", "Strategic and equitable learning" ], "keywords": [ "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization", "game theory", "learning in games", "Bayesian games", "Stackelberg strategies", "equity", "public models" ], "citation": "Dongxiang Yan, Tongxin Li, Changhong Zhao, Han Wang, Yue Chen. Hierarchical Game for Coupled Power System With Energy Sharing and Transportation System. IEEE Transactions on Transportation Electrification, 2025. https://doi.org/10.1109/TTE.2024.3398988", "canonical_url": "https://tongxin.me/research/papers/coupled-networks/" }, { "id": "instruct-mpc", "title": "INSTRUCT MPC: A Human-LLM-in-the-Loop Framework for Context-Aware Control", "authors": [ "Ruixiang Wu", "Jiahao Ai", "Tongxin Li" ], "year": 2025, "venue": "CDC", "publication": "IEEE Conference on Decision and Control", "doi": "10.1109/CDC57313.2025.11312156", "themes": [ "agents", "control", "energy" ], "question": "How can human instructions improve predictive control?", "summary": "A language to distribution module converts contextual instructions into disturbance predictions for MPC. The framework closes the loop between instructions, predictions, and control, with a regret analysis for linear dynamics under the stated training assumptions.", "path": "/research/papers/instruct-mpc/", "entry_type": "inproceedings", "primary_url": "https://doi.org/10.1109/CDC57313.2025.11312156", "theme_names": [ "Language and decision agents", "Safe and distributed control", "Energy and infrastructure" ], "keywords": [ "large language models", "LLM agents", "contextual control", "world models", "reinforcement learning", "dueling bandits", "model predictive control", "MPC", "stability", "recursive feasibility", "distributed control", "system level synthesis", "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization" ], "citation": "Ruixiang Wu, Jiahao Ai, Tongxin Li. INSTRUCT MPC: A Human-LLM-in-the-Loop Framework for Context-Aware Control. IEEE Conference on Decision and Control, 2025. https://doi.org/10.1109/CDC57313.2025.11312156", "canonical_url": "https://tongxin.me/research/papers/instruct-mpc/" }, { "id": "water-control", "title": "Learning-Augmented Online Control for Decarbonizing Water Infrastructures", "authors": [ "Jianyi Yang", "Pengfei Li", "Tongxin Li", "Adam Wierman", "Shaolei Ren" ], "year": 2025, "venue": "ACM e-Energy", "publication": "ACM International Conference on Future and Sustainable Energy Systems", "doi": "10.1145/3679240.3734595", "themes": [ "energy", "control", "predictions" ], "question": "Can learned pump control reduce carbon costs while meeting safety constraints?", "summary": "LAOC restricts online decisions to safe action sets while exploiting learned predictions for pump scheduling. Analysis characterizes the relationship between safety requirements and operating costs, with a building water supply case study.", "path": "/research/papers/water-control/", "entry_type": "inproceedings", "primary_url": "https://doi.org/10.1145/3679240.3734595", "theme_names": [ "Energy and infrastructure", "Safe and distributed control", "Learning with predictions" ], "keywords": [ "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization", "model predictive control", "MPC", "stability", "recursive feasibility", "distributed control", "system level synthesis", "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization" ], "citation": "Jianyi Yang, Pengfei Li, Tongxin Li, Adam Wierman, Shaolei Ren. Learning-Augmented Online Control for Decarbonizing Water Infrastructures. ACM International Conference on Future and Sustainable Energy Systems, 2025. https://doi.org/10.1145/3679240.3734595", "canonical_url": "https://tongxin.me/research/papers/water-control/" }, { "id": "opencem", "title": "Open In-Context Energy Management Platform", "authors": [ "Yikai Lu", "Tinko Sebastian Bartels", "Ruixiang Wu", "Fanzeng Xia", "Xudong Wang", "Yifei Wu", "Haoxiang Yang", "Tongxin Li" ], "year": 2025, "venue": "ACM e-Energy demo", "publication": "ACM International Conference on Future and Sustainable Energy Systems", "doi": "10.1145/3679240.3734678", "themes": [ "agents", "energy", "control" ], "question": "What would a shared benchmark for contextual energy management provide?", "summary": "OpenCEM presents a platform design connecting energy time series, events, human context, and simulation. An on campus solar and battery installation motivates evaluation of context sensitive control. The paper describes planned data and API capabilities.", "path": "/research/papers/opencem/", "entry_type": "inproceedings", "primary_url": "https://doi.org/10.1145/3679240.3734678", "theme_names": [ "Language and decision agents", "Energy and infrastructure", "Safe and distributed control" ], "keywords": [ "large language models", "LLM agents", "contextual control", "world models", "reinforcement learning", "dueling bandits", "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization", "model predictive control", "MPC", "stability", "recursive feasibility", "distributed control", "system level synthesis" ], "citation": "Yikai Lu, Tinko Sebastian Bartels, Ruixiang Wu, Fanzeng Xia, Xudong Wang, Yifei Wu, Haoxiang Yang, Tongxin Li. Open In-Context Energy Management Platform. ACM International Conference on Future and Sustainable Energy Systems, 2025. https://doi.org/10.1145/3679240.3734678", "canonical_url": "https://tongxin.me/research/papers/opencem/" }, { "id": "ood-charging", "title": "Out-of-Distribution-Aware Electric Vehicle Charging", "authors": [ "Tongxin Li", "Chenxi Sun" ], "year": 2025, "venue": "IEEE Transactions on Transportation Electrification", "publication": "IEEE Transactions on Transportation Electrification", "doi": "10.1109/TTE.2024.3434750", "themes": [ "energy", "predictions", "control" ], "note": "Published online in 2024 and assigned to the February 2025 journal issue.", "question": "How should charging schedules respond when user behavior changes?", "summary": "OOD Charging adapts an awareness radius using temporal difference errors to balance learned scheduling with a robust baseline. Evaluation on ACN data examines behavioral changes during COVID 19 and the resulting distribution shift.", "path": "/research/papers/ood-charging/", "entry_type": "article", "primary_url": "https://doi.org/10.1109/TTE.2024.3434750", "theme_names": [ "Energy and infrastructure", "Learning with predictions", "Safe and distributed control" ], "keywords": [ "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization", "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization", "model predictive control", "MPC", "stability", "recursive feasibility", "distributed control", "system level synthesis" ], "citation": "Tongxin Li, Chenxi Sun. Out-of-Distribution-Aware Electric Vehicle Charging. IEEE Transactions on Transportation Electrification, 2025. https://doi.org/10.1109/TTE.2024.3434750", "canonical_url": "https://tongxin.me/research/papers/ood-charging/" }, { "id": "predsls", "title": "PredSLS: A System-Level Framework for Distributed Predictive Control", "authors": [ "Yifei Wu", "Jing Yu", "Tongxin Li" ], "year": 2025, "venue": "CDC", "publication": "IEEE Conference on Decision and Control", "doi": "10.1109/CDC57313.2025.11312851", "themes": [ "control", "predictions" ], "question": "How can distributed controllers use predictions with limited communication?", "summary": "PredSLS integrates forecasts directly into system level synthesis with locality constraints. Temporal decay of prediction effects supports finite horizon approximations, while spatial and temporal decomposition enable scalable computation across a network.", "path": "/research/papers/predsls/", "entry_type": "inproceedings", "primary_url": "https://doi.org/10.1109/CDC57313.2025.11312851", "theme_names": [ "Safe and distributed control", "Learning with predictions" ], "keywords": [ "model predictive control", "MPC", "stability", "recursive feasibility", "distributed control", "system level synthesis", "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization" ], "citation": "Yifei Wu, Jing Yu, Tongxin Li. PredSLS: A System-Level Framework for Distributed Predictive Control. IEEE Conference on Decision and Control, 2025. https://doi.org/10.1109/CDC57313.2025.11312851", "canonical_url": "https://tongxin.me/research/papers/predsls/" }, { "id": "bellman-jensen", "title": "Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach", "authors": [ "Chenbei Lu", "Zaiwei Chen", "Tongxin Li", "Chenye Wu", "Adam Wierman" ], "year": 2025, "venue": "NeurIPS", "publication": "Advances in Neural Information Processing Systems", "url": "https://papers.nips.cc/paper_files/paper/2025/hash/940a7634dab556b67af15bacd337f7db-Abstract-Conference.html", "themes": [ "predictions", "agents", "energy" ], "question": "How can reinforcement learning use imperfect forecasts beyond one step?", "summary": "A Bayesian value function and Bellman Jensen gap quantify the value of imperfect transition forecasts. BOLA separates offline value learning from online adaptation, with sample efficiency analysis and experiments in synthetic environments and wind energy storage control.", "path": "/research/papers/bellman-jensen/", "entry_type": "inproceedings", "primary_url": "https://papers.nips.cc/paper_files/paper/2025/hash/940a7634dab556b67af15bacd337f7db-Abstract-Conference.html", "theme_names": [ "Learning with predictions", "Language and decision agents", "Energy and infrastructure" ], "keywords": [ "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization", "large language models", "LLM agents", "contextual control", "world models", "reinforcement learning", "dueling bandits", "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization" ], "citation": "Chenbei Lu, Zaiwei Chen, Tongxin Li, Chenye Wu, Adam Wierman. Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach. Advances in Neural Information Processing Systems, 2025. https://papers.nips.cc/paper_files/paper/2025/hash/940a7634dab556b67af15bacd337f7db-Abstract-Conference.html", "canonical_url": "https://tongxin.me/research/papers/bellman-jensen/" }, { "id": "robust-grid", "title": "Robust machine-learned algorithms for efficient grid operation", "authors": [ "Nicolas Christianson", "Christopher Yeh", "Tongxin Li", "Mehdi Hosseini", "Mahdi Torabi Rad", "Azarang Golmohammadi", "Adam Wierman" ], "year": 2025, "venue": "Environmental Data Science", "publication": "Environmental Data Science", "doi": "10.1017/eds.2024.28", "themes": [ "energy", "predictions", "control" ], "question": "Can learned dispatch policies remain reliable under distribution shift?", "summary": "RobustML combines a learned dispatch algorithm with a bound on worst case cost. A combined cycle cogeneration case study examines dispatch and ramping costs as renewable penetration increases, including performance under distribution shift.", "path": "/research/papers/robust-grid/", "entry_type": "article", "primary_url": "https://doi.org/10.1017/eds.2024.28", "theme_names": [ "Energy and infrastructure", "Learning with predictions", "Safe and distributed control" ], "keywords": [ "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization", "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization", "model predictive control", "MPC", "stability", "recursive feasibility", "distributed control", "system level synthesis" ], "citation": "Nicolas Christianson, Christopher Yeh, Tongxin Li, Mehdi Hosseini, Mahdi Torabi Rad, Azarang Golmohammadi, Adam Wierman. Robust machine-learned algorithms for efficient grid operation. Environmental Data Science, 2025. https://doi.org/10.1017/eds.2024.28", "canonical_url": "https://tongxin.me/research/papers/robust-grid/" }, { "id": "solar-hosting", "title": "Robust Solar Hosting Capacity for Pasadena's Decarbonization: A Mathematical Program for Robustness Against Uncertainty", "authors": [ "Han Xu", "Yiheng Xie", "Wenqi Cui", "Tongxin Li", "Steven Low" ], "year": 2025, "venue": "IEEE Energy Sustainability Magazine", "publication": "IEEE Energy Sustainability Magazine", "doi": "10.1109/ESM.2025.3606174", "pdf": "https://ieee-pes.org/wp-content/uploads/2025/12/Robust-Solar-Hosting-Capacity-for-Pasadenas-Decarbonization.pdf", "themes": [ "energy" ], "question": "How much distributed solar can a grid accommodate under uncertainty?", "summary": "The Pasadena case study formulates solar hosting capacity planning as a robust optimization problem. It connects uncertainty in renewable generation and demand to distribution network constraints and practical choices along a municipal decarbonization pathway.", "path": "/research/papers/solar-hosting/", "entry_type": "article", "primary_url": "https://doi.org/10.1109/ESM.2025.3606174", "theme_names": [ "Energy and infrastructure" ], "keywords": [ "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization" ], "citation": "Han Xu, Yiheng Xie, Wenqi Cui, Tongxin Li, Steven Low. Robust Solar Hosting Capacity for Pasadena's Decarbonization: A Mathematical Program for Robustness Against Uncertainty. IEEE Energy Sustainability Magazine, 2025. https://doi.org/10.1109/ESM.2025.3606174", "canonical_url": "https://tongxin.me/research/papers/solar-hosting/" }, { "id": "early-stations", "title": "A Data-Driven Approach for Optimizing Early-Stage Electric Vehicle Charging Station Placement", "authors": [ "Chenxi Sun", "Tongxin Li", "Xiaoying Tang" ], "year": 2024, "venue": "IEEE Transactions on Industrial Informatics", "publication": "IEEE Transactions on Industrial Informatics", "doi": "10.1109/TII.2023.3245633", "themes": [ "energy" ], "note": "Published online in 2023 and assigned to the October 2024 journal issue.", "question": "How can early charging infrastructure encourage electric vehicle adoption?", "summary": "Two proximity models represent user satisfaction with station locations. Population, travel, road network, and point of interest data inform a submodular optimization problem, solved approximately with a greedy method and evaluated in Haikou.", "related": [ "station-placement" ], "path": "/research/papers/early-stations/", "entry_type": "article", "primary_url": "https://doi.org/10.1109/TII.2023.3245633", "theme_names": [ "Energy and infrastructure" ], "keywords": [ "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization" ], "citation": "Chenxi Sun, Tongxin Li, Xiaoying Tang. A Data-Driven Approach for Optimizing Early-Stage Electric Vehicle Charging Station Placement. IEEE Transactions on Industrial Informatics, 2024. https://doi.org/10.1109/TII.2023.3245633", "canonical_url": "https://tongxin.me/research/papers/early-stations/" }, { "id": "equitable-models", "title": "Building Socially-Equitable Public Models", "authors": [ "Yejia Liu", "Jianyi Yang", "Pengfei Li", "Tongxin Li", "Shaolei Ren" ], "year": 2024, "venue": "ICML", "publication": "Proceedings of the International Conference on Machine Learning", "url": "https://proceedings.mlr.press/v235/liu24bw.html", "code": "https://github.com/Ren-Research/Socially-Equitable-Public-Models", "themes": [ "games", "predictions" ], "question": "Who benefits when many decision makers share one predictive model?", "summary": "The Equitable Objective trains a public predictive model around the outcomes of heterogeneous downstream agents. A policy gradient method and theoretical analysis study a more equitable distribution of performance, beyond optimizing prediction accuracy alone.", "path": "/research/papers/equitable-models/", "entry_type": "inproceedings", "primary_url": "https://proceedings.mlr.press/v235/liu24bw.html", "theme_names": [ "Strategic and equitable learning", "Learning with predictions" ], "keywords": [ "game theory", "learning in games", "Bayesian games", "Stackelberg strategies", "equity", "public models", "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization" ], "citation": "Yejia Liu, Jianyi Yang, Pengfei Li, Tongxin Li, Shaolei Ren. Building Socially-Equitable Public Models. Proceedings of the International Conference on Machine Learning, 2024. https://proceedings.mlr.press/v235/liu24bw.html", "canonical_url": "https://tongxin.me/research/papers/equitable-models/" }, { "id": "disc", "title": "Disentangling Linear Quadratic Control with Untrusted ML Predictions", "authors": [ "Tongxin Li", "Hao Liu", "Yisong Yue" ], "year": 2024, "venue": "NeurIPS", "publication": "Advances in Neural Information Processing Systems", "url": "https://papers.nips.cc/paper_files/paper/2024/hash/9dff3b83d463fab213941bfee23341ba-Abstract-Conference.html", "themes": [ "predictions", "control" ], "question": "Can a controller learn which components of a forecast to trust?", "summary": "DISC learns confidence in predictions of latent disturbance components. Competitive analysis covers linear and more general mixing functions, showing how online confidence adaptation can exploit accurate forecasts while maintaining protection against large errors.", "path": "/research/papers/disc/", "entry_type": "inproceedings", "primary_url": "https://papers.nips.cc/paper_files/paper/2024/hash/9dff3b83d463fab213941bfee23341ba-Abstract-Conference.html", "theme_names": [ "Learning with predictions", "Safe and distributed control" ], "keywords": [ "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization", "model predictive control", "MPC", "stability", "recursive feasibility", "distributed control", "system level synthesis" ], "citation": "Tongxin Li, Hao Liu, Yisong Yue. Disentangling Linear Quadratic Control with Untrusted ML Predictions. Advances in Neural Information Processing Systems, 2024. https://papers.nips.cc/paper_files/paper/2024/hash/9dff3b83d463fab213941bfee23341ba-Abstract-Conference.html", "canonical_url": "https://tongxin.me/research/papers/disc/" }, { "id": "safe-play", "title": "Safe Exploitative Play with Untrusted Type Beliefs", "authors": [ "Tongxin Li", "Tinashe Handina", "Shaolei Ren", "Adam Wierman" ], "year": 2024, "venue": "NeurIPS", "publication": "Advances in Neural Information Processing Systems", "url": "https://papers.nips.cc/paper_files/paper/2024/hash/858e773f5c99a4186b548f3f531fb07e-Abstract-Conference.html", "themes": [ "games", "predictions" ], "question": "How much risk comes from exploiting a predicted opponent type?", "summary": "The paper formalizes a risk and opportunity tradeoff for agents with uncertain beliefs about other players. Upper and lower bounds characterize the Pareto frontier in normal form and stochastic Bayesian games, with numerical illustrations of the tradeoff.", "path": "/research/papers/safe-play/", "entry_type": "inproceedings", "primary_url": "https://papers.nips.cc/paper_files/paper/2024/hash/858e773f5c99a4186b548f3f531fb07e-Abstract-Conference.html", "theme_names": [ "Strategic and equitable learning", "Learning with predictions" ], "keywords": [ "game theory", "learning in games", "Bayesian games", "Stackelberg strategies", "equity", "public models", "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization" ], "citation": "Tongxin Li, Tinashe Handina, Shaolei Ren, Adam Wierman. Safe Exploitative Play with Untrusted Type Beliefs. Advances in Neural Information Processing Systems, 2024. https://papers.nips.cc/paper_files/paper/2024/hash/858e773f5c99a4186b548f3f531fb07e-Abstract-Conference.html", "canonical_url": "https://tongxin.me/research/papers/safe-play/" }, { "id": "anytime-rl", "title": "Anytime-Competitive Reinforcement Learning with Policy Prior", "authors": [ "Jianyi Yang", "Pengfei Li", "Tongxin Li", "Adam Wierman", "Shaolei Ren" ], "year": 2023, "venue": "NeurIPS", "publication": "Advances in Neural Information Processing Systems", "url": "https://papers.nips.cc/paper_files/paper/2023/hash/f53437debdd397c42929d929614bc705-Abstract-Conference.html", "themes": [ "agents", "predictions", "control" ], "question": "Can reinforcement learning enforce cost protection throughout an episode?", "summary": "ACRL constrains cumulative costs relative to a policy prior at each round, rather than only in expectation over episodes. The analysis establishes cost guarantees and regret relative to the constrained optimum, with experiments in carbon aware computing.", "path": "/research/papers/anytime-rl/", "entry_type": "inproceedings", "primary_url": "https://papers.nips.cc/paper_files/paper/2023/hash/f53437debdd397c42929d929614bc705-Abstract-Conference.html", "theme_names": [ "Language and decision agents", "Learning with predictions", "Safe and distributed control" ], "keywords": [ "large language models", "LLM agents", "contextual control", "world models", "reinforcement learning", "dueling bandits", "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization", "model predictive control", "MPC", "stability", "recursive feasibility", "distributed control", "system level synthesis" ], "citation": "Jianyi Yang, Pengfei Li, Tongxin Li, Adam Wierman, Shaolei Ren. Anytime-Competitive Reinforcement Learning with Policy Prior. Advances in Neural Information Processing Systems, 2023. https://papers.nips.cc/paper_files/paper/2023/hash/f53437debdd397c42929d929614bc705-Abstract-Conference.html", "canonical_url": "https://tongxin.me/research/papers/anytime-rl/" }, { "id": "q-value-advice", "title": "Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions", "authors": [ "Tongxin Li", "Yiheng Lin", "Shaolei Ren", "Adam Wierman" ], "year": 2023, "venue": "NeurIPS", "publication": "Advances in Neural Information Processing Systems", "url": "https://papers.nips.cc/paper_files/paper/2023/hash/8e806d3c56ed5f1dab85d601e13cbe38-Abstract-Conference.html", "themes": [ "predictions", "agents" ], "question": "Does the structure of advice improve robust decision making?", "summary": "Q value predictions expose more information than an opaque policy recommendation. For a single trajectory MDP, the analysis characterizes consistency and robustness tradeoffs and shows how structured advice improves the guarantees available from a robust baseline.", "path": "/research/papers/q-value-advice/", "entry_type": "inproceedings", "primary_url": "https://papers.nips.cc/paper_files/paper/2023/hash/8e806d3c56ed5f1dab85d601e13cbe38-Abstract-Conference.html", "theme_names": [ "Learning with predictions", "Language and decision agents" ], "keywords": [ "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization", "large language models", "LLM agents", "contextual control", "world models", "reinforcement learning", "dueling bandits" ], "citation": "Tongxin Li, Yiheng Lin, Shaolei Ren, Adam Wierman. Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions. Advances in Neural Information Processing Systems, 2023. https://papers.nips.cc/paper_files/paper/2023/hash/8e806d3c56ed5f1dab85d601e13cbe38-Abstract-Conference.html", "canonical_url": "https://tongxin.me/research/papers/q-value-advice/" }, { "id": "certified-policies", "title": "Certifying Black-Box Policies With Stability for Nonlinear Control", "authors": [ "Tongxin Li", "Ruixiao Yang", "Guannan Qu", "Yiheng Lin", "Adam Wierman", "Steven H. Low" ], "year": 2023, "venue": "IEEE Open Journal of Control Systems", "publication": "IEEE Open Journal of Control Systems", "doi": "10.1109/OJCSYS.2023.3241486", "themes": [ "control", "predictions", "energy" ], "question": "How can model based advice stabilize a learned nonlinear policy?", "summary": "Simply blending two stabilizing policies can cause instability. An adaptive confidence policy instead uses approximate model information to certify stability, with competitive guarantees under bounded nonlinearity and evaluations on Cart Pole and charging under distribution shift.", "path": "/research/papers/certified-policies/", "entry_type": "article", "primary_url": "https://doi.org/10.1109/OJCSYS.2023.3241486", "theme_names": [ "Safe and distributed control", "Learning with predictions", "Energy and infrastructure" ], "keywords": [ "model predictive control", "MPC", "stability", "recursive feasibility", "distributed control", "system level synthesis", "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization", "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization" ], "citation": "Tongxin Li, Ruixiao Yang, Guannan Qu, Yiheng Lin, Adam Wierman, Steven H. Low. Certifying Black-Box Policies With Stability for Nonlinear Control. IEEE Open Journal of Control Systems, 2023. https://doi.org/10.1109/OJCSYS.2023.3241486", "canonical_url": "https://tongxin.me/research/papers/certified-policies/" }, { "id": "bounded-regret-mpc", "title": "Bounded-Regret MPC via Perturbation Analysis: Prediction Error, Constraints, and Nonlinearity", "authors": [ "Yiheng Lin", "Yang Hu", "Guannan Qu", "Tongxin Li", "Adam Wierman" ], "year": 2022, "venue": "NeurIPS", "publication": "Advances in Neural Information Processing Systems", "url": "https://papers.nips.cc/paper_files/paper/2022/hash/eadeef7c51ad86989cc3b311cb49ec89-Abstract-Conference.html", "themes": [ "control", "predictions" ], "question": "How do forecast errors translate into regret for MPC?", "summary": "A general analysis pipeline converts perturbation bounds for finite horizon control into dynamic regret bounds for MPC. It handles prediction errors in costs, dynamics, and disturbances, and extends the analysis to constrained and nonlinear settings under suitable regularity conditions.", "path": "/research/papers/bounded-regret-mpc/", "entry_type": "inproceedings", "primary_url": "https://papers.nips.cc/paper_files/paper/2022/hash/eadeef7c51ad86989cc3b311cb49ec89-Abstract-Conference.html", "theme_names": [ "Safe and distributed control", "Learning with predictions" ], "keywords": [ "model predictive control", "MPC", "stability", "recursive feasibility", "distributed control", "system level synthesis", "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization" ], "citation": "Yiheng Lin, Yang Hu, Guannan Qu, Tongxin Li, Adam Wierman. Bounded-Regret MPC via Perturbation Analysis: Prediction Error, Constraints, and Nonlinearity. Advances in Neural Information Processing Systems, 2022. https://papers.nips.cc/paper_files/paper/2022/hash/eadeef7c51ad86989cc3b311cb49ec89-Abstract-Conference.html", "canonical_url": "https://tongxin.me/research/papers/bounded-regret-mpc/" }, { "id": "robust-lqc", "title": "Robustness and Consistency in Linear Quadratic Control with Untrusted Predictions", "authors": [ "Tongxin Li", "Ruixiao Yang", "Guannan Qu", "Guanya Shi", "Chenkai Yu", "Adam Wierman", "Steven Low" ], "year": 2022, "venue": "POMACS", "publication": "Proceedings of the ACM on Measurement and Analysis of Computing Systems", "doi": "10.1145/3508038", "url": "https://arxiv.org/abs/2106.09659", "themes": [ "predictions", "control" ], "versions": [ { "label": "SIGMETRICS 2022 abstract", "url": "https://doi.org/10.1145/3489048.3522658" } ], "question": "Can predictive control balance consistency and robustness automatically?", "summary": "A confidence parameter governs how much a linear quadratic controller trusts disturbance predictions. Competitive bounds describe the tradeoff between accurate and inaccurate advice, and a self tuning policy adapts confidence online using observed prediction quality.", "path": "/research/papers/robust-lqc/", "entry_type": "article", "primary_url": "https://doi.org/10.1145/3508038", "theme_names": [ "Learning with predictions", "Safe and distributed control" ], "keywords": [ "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization", "model predictive control", "MPC", "stability", "recursive feasibility", "distributed control", "system level synthesis" ], "citation": "Tongxin Li, Ruixiao Yang, Guannan Qu, Guanya Shi, Chenkai Yu, Adam Wierman, Steven Low. Robustness and Consistency in Linear Quadratic Control with Untrusted Predictions. Proceedings of the ACM on Measurement and Analysis of Computing Systems, 2022. https://doi.org/10.1145/3508038", "canonical_url": "https://tongxin.me/research/papers/robust-lqc/" }, { "id": "phase-optimization", "title": "Towards balanced three-phase charging: Phase optimization in adaptive charging networks", "authors": [ "Zixin Ye", "Tongxin Li", "Steven Low" ], "year": 2022, "venue": "Electric Power Systems Research", "publication": "Electric Power Systems Research", "doi": "10.1016/j.epsr.2022.108322", "themes": [ "energy", "control" ], "question": "How should electric vehicle demand be assigned across electrical phases?", "summary": "PXA solves a relaxation of the phase optimization problem, with convergence guarantees under specified conditions. Its MPC implementation updates decisions online. Experiments use adaptive charging network data to examine energy delivery, charging costs, and phase balance.", "path": "/research/papers/phase-optimization/", "entry_type": "article", "primary_url": "https://doi.org/10.1016/j.epsr.2022.108322", "theme_names": [ "Energy and infrastructure", "Safe and distributed control" ], "keywords": [ "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization", "model predictive control", "MPC", "stability", "recursive feasibility", "distributed control", "system level synthesis" ], "citation": "Zixin Ye, Tongxin Li, Steven Low. Towards balanced three-phase charging: Phase optimization in adaptive charging networks. Electric Power Systems Research, 2022. https://doi.org/10.1016/j.epsr.2022.108322", "canonical_url": "https://tongxin.me/research/papers/phase-optimization/" }, { "id": "station-placement", "title": "Data-driven Electric Vehicle Charging Station Placement for Incentivizing Potential Demand", "authors": [ "Chenxi Sun", "Tongxin Li", "Xiaoying Tang" ], "year": 2021, "venue": "SmartGridComm", "publication": "IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids", "doi": "10.1109/SmartGridComm51999.2021.9632309", "themes": [ "energy" ], "question": "Where should a city place charging stations with a limited budget?", "summary": "A proximity based satisfaction model turns station placement into monotone submodular maximization. A greedy algorithm has a provable approximation ratio, with a Haikou case study using population, travel, and point of interest data.", "related": [ "early-stations" ], "path": "/research/papers/station-placement/", "entry_type": "inproceedings", "primary_url": "https://doi.org/10.1109/SmartGridComm51999.2021.9632309", "theme_names": [ "Energy and infrastructure" ], "keywords": [ "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization" ], "citation": "Chenxi Sun, Tongxin Li, Xiaoying Tang. Data-driven Electric Vehicle Charging Station Placement for Incentivizing Potential Demand. IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, 2021. https://doi.org/10.1109/SmartGridComm51999.2021.9632309", "canonical_url": "https://tongxin.me/research/papers/station-placement/" }, { "id": "vpp-predictions", "title": "Decentralized Provision of Renewable Predictions Within a Virtual Power Plant", "authors": [ "Yue Chen", "Tongxin Li", "Changhong Zhao", "Wei Wei" ], "year": 2021, "venue": "IEEE Transactions on Power Systems", "publication": "IEEE Transactions on Power Systems", "doi": "10.1109/TPWRS.2020.3035174", "themes": [ "energy", "games", "predictions" ], "note": "Published online in 2020 and assigned to the May 2021 journal issue.", "question": "Can local renewable forecasts support decentralized market coordination?", "summary": "A decentralized prediction provision scheme lets consumers obtain local forecasts and exchange summaries with a virtual power plant. The analysis studies social surplus, convergence, and the demand gap relative to centralized information sharing.", "path": "/research/papers/vpp-predictions/", "entry_type": "article", "primary_url": "https://doi.org/10.1109/TPWRS.2020.3035174", "theme_names": [ "Energy and infrastructure", "Strategic and equitable learning", "Learning with predictions" ], "keywords": [ "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization", "game theory", "learning in games", "Bayesian games", "Stackelberg strategies", "equity", "public models", "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization" ], "citation": "Yue Chen, Tongxin Li, Changhong Zhao, Wei Wei. Decentralized Provision of Renewable Predictions Within a Virtual Power Plant. IEEE Transactions on Power Systems, 2021. https://doi.org/10.1109/TPWRS.2020.3035174", "canonical_url": "https://tongxin.me/research/papers/vpp-predictions/" }, { "id": "information-aggregation", "title": "Information Aggregation for Constrained Online Control", "authors": [ "Tongxin Li", "Yue Chen", "Bo Sun", "Adam Wierman", "Steven Low" ], "year": 2021, "venue": "POMACS", "publication": "Proceedings of the ACM on Measurement and Analysis of Computing Systems", "doi": "10.1145/3460085", "themes": [ "control", "structure", "energy" ], "versions": [ { "label": "SIGMETRICS 2021 abstract", "url": "https://doi.org/10.1145/3410220.3461737" } ], "question": "How much feasibility information must a local controller share?", "summary": "Entropic aggregation summarizes a local controller's feasible actions for a remote decision maker. Penalized Predictive Control can approach the regret of full information control under causal invariance and a sufficiently long prediction window.", "path": "/research/papers/information-aggregation/", "entry_type": "article", "primary_url": "https://doi.org/10.1145/3460085", "theme_names": [ "Safe and distributed control", "Information and network learning", "Energy and infrastructure" ], "keywords": [ "model predictive control", "MPC", "stability", "recursive feasibility", "distributed control", "system level synthesis", "information theory", "graph learning", "sample complexity", "compressed sensing", "graph neural networks", "Riemannian geometry", "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization" ], "citation": "Tongxin Li, Yue Chen, Bo Sun, Adam Wierman, Steven Low. Information Aggregation for Constrained Online Control. Proceedings of the ACM on Measurement and Analysis of Computing Systems, 2021. https://doi.org/10.1145/3460085", "canonical_url": "https://tongxin.me/research/papers/information-aggregation/" }, { "id": "aggregate-flexibility", "title": "Learning-Based Predictive Control via Real-Time Aggregate Flexibility", "authors": [ "Tongxin Li", "Bo Sun", "Yue Chen", "Zixin Ye", "Steven H. Low", "Adam Wierman" ], "year": 2021, "venue": "IEEE Transactions on Smart Grid", "publication": "IEEE Transactions on Smart Grid", "doi": "10.1109/TSG.2021.3094719", "url": "https://arxiv.org/abs/2012.11261", "themes": [ "control", "energy", "agents" ], "question": "How can an aggregator communicate flexibility in real time?", "summary": "Maximum entropy feedback summarizes the feasible actions of controllable loads. Reinforcement learning approximates this feedback for Penalized Predictive Control, reducing information and computation requirements. Charging data demonstrates the coordination approach.", "path": "/research/papers/aggregate-flexibility/", "entry_type": "article", "primary_url": "https://doi.org/10.1109/TSG.2021.3094719", "theme_names": [ "Safe and distributed control", "Energy and infrastructure", "Language and decision agents" ], "keywords": [ "model predictive control", "MPC", "stability", "recursive feasibility", "distributed control", "system level synthesis", "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization", "large language models", "LLM agents", "contextual control", "world models", "reinforcement learning", "dueling bandits" ], "citation": "Tongxin Li, Bo Sun, Yue Chen, Zixin Ye, Steven H. Low, Adam Wierman. Learning-Based Predictive Control via Real-Time Aggregate Flexibility. IEEE Transactions on Smart Grid, 2021. https://doi.org/10.1109/TSG.2021.3094719", "canonical_url": "https://tongxin.me/research/papers/aggregate-flexibility/" }, { "id": "charging-clusters", "title": "Classification of electric vehicle charging time series with selective clustering", "authors": [ "Chenxi Sun", "Tongxin Li", "Steven H. Low", "Victor O. K. Li" ], "year": 2020, "venue": "Electric Power Systems Research", "publication": "Electric Power Systems Research", "doi": "10.1016/j.epsr.2020.106695", "themes": [ "energy", "structure" ], "question": "What battery behavior can be learned from imperfect charging records?", "summary": "An iterative procedure extracts and clusters the tail portions of charging curves despite missing observations, variable lengths, scheduling effects, and measurement noise. Experiments on ACN data illustrate how these patterns can support useful charging models.", "path": "/research/papers/charging-clusters/", "entry_type": "article", "primary_url": "https://doi.org/10.1016/j.epsr.2020.106695", "theme_names": [ "Energy and infrastructure", "Information and network learning" ], "keywords": [ "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization", "information theory", "graph learning", "sample complexity", "compressed sensing", "graph neural networks", "Riemannian geometry" ], "citation": "Chenxi Sun, Tongxin Li, Steven H. Low, Victor O. K. Li. Classification of electric vehicle charging time series with selective clustering. Electric Power Systems Research, 2020. https://doi.org/10.1016/j.epsr.2020.106695", "canonical_url": "https://tongxin.me/research/papers/charging-clusters/" }, { "id": "online-knapsack", "title": "Competitive Algorithms for the Online Multiple Knapsack Problem with Application to Electric Vehicle Charging", "authors": [ "Bo Sun", "Ali Zeynali", "Tongxin Li", "Mohammad Hajiesmaili", "Adam Wierman", "Danny H. K. Tsang" ], "year": 2020, "venue": "POMACS", "publication": "Proceedings of the ACM on Measurement and Analysis of Computing Systems", "doi": "10.1145/3428336", "themes": [ "predictions", "energy" ], "versions": [ { "label": "SIGMETRICS 2021 abstract", "url": "https://doi.org/10.1145/3410220.3456271" } ], "question": "How should limited resources be allocated to requests arriving online?", "summary": "A general fractional multiple knapsack model captures assignment and rate constraints. An online primal dual algorithm obtains near optimal competitive guarantees and is evaluated using charging traces. This work provides an online allocation foundation without requiring learned predictions.", "path": "/research/papers/online-knapsack/", "entry_type": "article", "primary_url": "https://doi.org/10.1145/3428336", "theme_names": [ "Learning with predictions", "Energy and infrastructure" ], "keywords": [ "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization", "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization" ], "citation": "Bo Sun, Ali Zeynali, Tongxin Li, Mohammad Hajiesmaili, Adam Wierman, Danny H. K. Tsang. Competitive Algorithms for the Online Multiple Knapsack Problem with Application to Electric Vehicle Charging. Proceedings of the ACM on Measurement and Analysis of Computing Systems, 2020. https://doi.org/10.1145/3428336", "canonical_url": "https://tongxin.me/research/papers/online-knapsack/" }, { "id": "graph-recovery", "title": "Learning Graphs From Linear Measurements: Fundamental Trade-Offs and Applications", "authors": [ "Tongxin Li", "Lucien Werner", "Steven H. Low" ], "year": 2020, "venue": "IEEE TSIPN", "publication": "IEEE Transactions on Signal and Information Processing over Networks", "doi": "10.1109/TSIPN.2020.2975368", "themes": [ "structure", "energy" ], "question": "What determines the sample complexity of network reconstruction?", "summary": "Bounds for noisy and noiseless graph recovery connect sparsity, graph distributions, and linear measurements. A three stage recovery scheme and practical algorithm are studied on canonical graphs and electrical grid admittance matrices.", "related": [ "graph-parameters", "graph-recovery", "charging-clusters", "dualnilm" ], "path": "/research/papers/graph-recovery/", "entry_type": "article", "primary_url": "https://doi.org/10.1109/TSIPN.2020.2975368", "theme_names": [ "Information and network learning", "Energy and infrastructure" ], "keywords": [ "information theory", "graph learning", "sample complexity", "compressed sensing", "graph neural networks", "Riemannian geometry", "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization" ], "citation": "Tongxin Li, Lucien Werner, Steven H. Low. Learning Graphs From Linear Measurements: Fundamental Trade-Offs and Applications. IEEE Transactions on Signal and Information Processing over Networks, 2020. https://doi.org/10.1109/TSIPN.2020.2975368", "canonical_url": "https://tongxin.me/research/papers/graph-recovery/" }, { "id": "orc", "title": "ORC: An Online Competitive Algorithm for Recommendation and Charging Schedule in Electric Vehicle Charging Network", "authors": [ "Bo Sun", "Tongxin Li", "Steven H. Low", "Danny H. K. Tsang" ], "year": 2020, "venue": "ACM e-Energy", "publication": "ACM International Conference on Future Energy Systems", "doi": "10.1145/3396851.3397727", "themes": [ "energy", "predictions" ], "question": "How can charging recommendations and schedules be coordinated online?", "summary": "ORC jointly recommends stations and prices while scheduling charging for sequential arrivals. A customizable value function supports competitive guarantees despite uncertainty in arrivals and user choices. Experiments compare operator revenue with benchmark scheduling methods.", "path": "/research/papers/orc/", "entry_type": "inproceedings", "primary_url": "https://doi.org/10.1145/3396851.3397727", "theme_names": [ "Energy and infrastructure", "Learning with predictions" ], "keywords": [ "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization", "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization" ], "citation": "Bo Sun, Tongxin Li, Steven H. Low, Danny H. K. Tsang. ORC: An Online Competitive Algorithm for Recommendation and Charging Schedule in Electric Vehicle Charging Network. ACM International Conference on Future Energy Systems, 2020. https://doi.org/10.1145/3396851.3397727", "canonical_url": "https://tongxin.me/research/papers/orc/" }, { "id": "graph-parameters", "title": "Learning Graph Parameters from Linear Measurements: Fundamental Trade-offs and Application to Electric Grids", "authors": [ "Tongxin Li", "Lucien Werner", "Steven H. Low" ], "year": 2019, "venue": "CDC", "publication": "IEEE Conference on Decision and Control", "doi": "10.1109/CDC40024.2019.9029949", "themes": [ "structure", "energy" ], "question": "How many measurements are needed to recover a network?", "summary": "Information theoretic bounds relate measurement requirements to graph complexity and recovery error. A recovery algorithm estimates topology and parameters from linear measurements, with demonstrations on graph families and electrical grid test cases.", "related": [ "graph-recovery" ], "path": "/research/papers/graph-parameters/", "entry_type": "inproceedings", "primary_url": "https://doi.org/10.1109/CDC40024.2019.9029949", "theme_names": [ "Information and network learning", "Energy and infrastructure" ], "keywords": [ "information theory", "graph learning", "sample complexity", "compressed sensing", "graph neural networks", "Riemannian geometry", "AI for energy", "electric vehicle charging", "demand response", "renewable energy", "load forecasting", "decarbonization" ], "citation": "Tongxin Li, Lucien Werner, Steven H. Low. Learning Graph Parameters from Linear Measurements: Fundamental Trade-offs and Application to Electric Grids. IEEE Conference on Decision and Control, 2019. https://doi.org/10.1109/CDC40024.2019.9029949", "canonical_url": "https://tongxin.me/research/papers/graph-parameters/" }, { "id": "channel-capacity", "title": "Maximum Likelihood Upper Bounds on the Capacities of Discrete Information Stable Channels", "authors": [ "Tongxin Li" ], "year": 2018, "venue": "ITW", "publication": "IEEE Information Theory Workshop", "doi": "10.1109/ITW.2018.8613485", "themes": [ "structure" ], "question": "How can channel capacity be bounded through maximum likelihood?", "summary": "The paper derives a maximum likelihood upper bound using optimality conditions for discrete information stable channels. It recovers capacity for selected memoryless channels and develops a counting based bound for the binary deletion channel.", "path": "/research/papers/channel-capacity/", "entry_type": "inproceedings", "primary_url": "https://doi.org/10.1109/ITW.2018.8613485", "theme_names": [ "Information and network learning" ], "keywords": [ "information theory", "graph learning", "sample complexity", "compressed sensing", "graph neural networks", "Riemannian geometry" ], "citation": "Tongxin Li. Maximum Likelihood Upper Bounds on the Capacities of Discrete Information Stable Channels. IEEE Information Theory Workshop, 2018. https://doi.org/10.1109/ITW.2018.8613485", "canonical_url": "https://tongxin.me/research/papers/channel-capacity/" }, { "id": "causal-channels", "title": "Quadratically Constrained Channels with Causal Adversaries", "authors": [ "Tongxin Li", "Bikash Kumar Dey", "Sidharth Jaggi", "Michael Langberg", "Anand D. Sarwate" ], "year": 2018, "venue": "ISIT", "publication": "IEEE International Symposium on Information Theory", "doi": "10.1109/ISIT.2018.8437839", "themes": [ "structure" ], "question": "What rates are possible when a jammer observes transmissions causally?", "summary": "Capacity is characterized through a sequence of optimization problems under quadratic power constraints. Analytical and numerical bounds show that nonuniform power allocation can outperform uniform allocation in certain signal to noise regimes.", "path": "/research/papers/causal-channels/", "entry_type": "inproceedings", "primary_url": "https://doi.org/10.1109/ISIT.2018.8437839", "theme_names": [ "Information and network learning" ], "keywords": [ "information theory", "graph learning", "sample complexity", "compressed sensing", "graph neural networks", "Riemannian geometry" ], "citation": "Tongxin Li, Bikash Kumar Dey, Sidharth Jaggi, Michael Langberg, Anand D. Sarwate. Quadratically Constrained Channels with Causal Adversaries. IEEE International Symposium on Information Theory, 2018. https://doi.org/10.1109/ISIT.2018.8437839", "canonical_url": "https://tongxin.me/research/papers/causal-channels/" }, { "id": "clustering-sdp", "title": "Robust and Consistent Clustering Recovery via SDP Approaches", "authors": [ "Chenxi Sun", "Tongxin Li", "Victor O. K. Li" ], "year": 2018, "venue": "IEEE DSW", "publication": "IEEE Data Science Workshop", "doi": "10.1109/DSW.2018.8439918", "themes": [ "structure" ], "question": "Can clusters be recovered from noisy similarities without knowing their number?", "summary": "A semidefinite programming approach recovers clustering structure in the presence of noise and outliers. The analysis gives conditions for exact recovery and consistency in a Gaussian similarity model, supported by synthetic experiments.", "path": "/research/papers/clustering-sdp/", "entry_type": "inproceedings", "primary_url": "https://doi.org/10.1109/DSW.2018.8439918", "theme_names": [ "Information and network learning" ], "keywords": [ "information theory", "graph learning", "sample complexity", "compressed sensing", "graph neural networks", "Riemannian geometry" ], "citation": "Chenxi Sun, Tongxin Li, Victor O. K. Li. Robust and Consistent Clustering Recovery via SDP Approaches. IEEE Data Science Workshop, 2018. https://doi.org/10.1109/DSW.2018.8439918", "canonical_url": "https://tongxin.me/research/papers/clustering-sdp/" }, { "id": "energy-sensing", "title": "Fundamental limits and achievable strategies for low energy compressed sensing with applications in wireless communication", "authors": [ "Tongxin Li", "Mayank Bakshi", "Pulkit Grover" ], "year": 2016, "venue": "SPAWC", "publication": "IEEE International Workshop on Signal Processing Advances in Wireless Communications", "doi": "10.1109/SPAWC.2016.7536775", "themes": [ "structure" ], "question": "What energy is required to decode a sparse signal?", "summary": "A communication complexity model measures the energy required to move information during support recovery. Upper and lower bounds show how adaptive message scheduling can reduce decoding energy, with an application to multiuser detection in wireless systems.", "path": "/research/papers/energy-sensing/", "entry_type": "inproceedings", "primary_url": "https://doi.org/10.1109/SPAWC.2016.7536775", "theme_names": [ "Information and network learning" ], "keywords": [ "information theory", "graph learning", "sample complexity", "compressed sensing", "graph neural networks", "Riemannian geometry" ], "citation": "Tongxin Li, Mayank Bakshi, Pulkit Grover. Fundamental limits and achievable strategies for low energy compressed sensing with applications in wireless communication. IEEE International Workshop on Signal Processing Advances in Wireless Communications, 2016. https://doi.org/10.1109/SPAWC.2016.7536775", "canonical_url": "https://tongxin.me/research/papers/energy-sensing/" }, { "id": "group-testing", "title": "Group Testing with Prior Statistics", "authors": [ "Tongxin Li", "Chun Lam Chan", "Wenhao Huang", "Tarik Kaced", "Sidharth Jaggi" ], "year": 2014, "venue": "ISIT", "publication": "IEEE International Symposium on Information Theory", "doi": "10.1109/ISIT.2014.6875253", "themes": [ "structure", "predictions" ], "question": "How can prior probabilities reduce the number of group tests?", "summary": "Adaptive and nonadaptive testing algorithms exploit heterogeneous prior probabilities of defective items. Under the stated independence and sparsity assumptions, their measurement requirements approach information theoretic lower bounds up to explicit constant factors.", "path": "/research/papers/group-testing/", "entry_type": "inproceedings", "primary_url": "https://doi.org/10.1109/ISIT.2014.6875253", "theme_names": [ "Information and network learning", "Learning with predictions" ], "keywords": [ "information theory", "graph learning", "sample complexity", "compressed sensing", "graph neural networks", "Riemannian geometry", "learning augmented algorithms", "algorithms with predictions", "competitive analysis", "robustness", "consistency", "online optimization" ], "citation": "Tongxin Li, Chun Lam Chan, Wenhao Huang, Tarik Kaced, Sidharth Jaggi. Group Testing with Prior Statistics. IEEE International Symposium on Information Theory, 2014. https://doi.org/10.1109/ISIT.2014.6875253", "canonical_url": "https://tongxin.me/research/papers/group-testing/" } ], "connections": [ { "id": "advice-to-control", "from": "predictions", "to": "control", "title": "From prediction error to control performance", "description": "Trust adaptation in linear quadratic control and perturbation bounds for MPC connect the quality of a forecast to the cost of acting on it. Nonlinear certification adds stability to this picture.", "papers": [ "robust-lqc", "bounded-regret-mpc", "certified-policies", "disc" ] }, { "id": "context-to-control", "from": "agents", "to": "control", "title": "From language context to constrained actions", "description": "INSTRUCT MPC translates human instructions into disturbance predictions. World model certification and VigilMPC study complementary ways of deciding which learned models can support reliable planning and safe updates.", "papers": [ "instruct-mpc", "world-models", "vigilmpc" ] }, { "id": "predictions-to-agents", "from": "predictions", "to": "agents", "title": "Algorithms guide learned decision makers", "description": "Q value advice and imperfect transition forecasts provide structured information for reinforcement learning. LEAD applies a related principle by supporting language agents with dueling bandit algorithms.", "papers": [ "q-value-advice", "bellman-jensen", "lead" ] }, { "id": "control-to-energy", "from": "control", "to": "energy", "title": "Guarantees meet physical infrastructure", "description": "Aggregate flexibility communicates feasible actions for coordinated charging. Robust dispatch and safe water control connect performance guarantees to operational costs and physical constraints.", "papers": [ "aggregate-flexibility", "information-aggregation", "robust-grid", "water-control" ] }, { "id": "context-to-energy", "from": "agents", "to": "energy", "title": "Context becomes an energy system input", "description": "OpenCEM motivates shared contextual energy benchmarks. INSTRUCT MPC uses instructions for control, while counterfactual load forecasting represents news events as interventions on electricity demand.", "papers": [ "opencem", "instruct-mpc", "counterfactual-load" ] }, { "id": "advice-to-games", "from": "predictions", "to": "games", "title": "Prediction errors become strategic risks", "description": "In strategic environments, advice quality affects both opportunity and risk. The Bayesian game and repeated game results expose limits on combining exploitation with protection against inaccurate beliefs.", "papers": [ "safe-play", "strategic-advice" ] }, { "id": "games-to-energy", "from": "games", "to": "energy", "title": "Coordination through information and incentives", "description": "Virtual power plants use renewable predictions to coordinate consumers. Energy sharing and transportation games model how charging demand, prices, and network constraints interact.", "papers": [ "vpp-predictions", "coupled-networks", "equitable-models" ] }, { "id": "structure-to-energy", "from": "structure", "to": "energy", "title": "Recovering structure from limited measurements", "description": "Graph recovery estimates electrical network parameters. Charging curve clustering and energy disaggregation recover useful structure from observed behavior and aggregate meter readings.", "papers": [ "graph-recovery", "charging-clusters", "dualnilm" ] } ], "open_directions": [ { "id": "certified-context", "title": "Certified contextual control", "question": "Can contextual and world model updates be certified before they affect a physical system?", "description": "Connect language conditioned predictions with local world model guarantees and feasibility checks. An open challenge is preserving safety when both the context and the learned dynamics change during operation.", "themes": [ "agents", "control", "predictions" ], "papers": [ "instruct-mpc", "world-models", "vigilmpc" ] }, { "id": "useful-predictions", "title": "Prediction quality as a decision resource", "question": "Which prediction errors actually matter for the decision being made?", "description": "Move from a single forecast accuracy score to guarantees that reflect the prediction, the task, and the affected transitions. This suggests adaptive confidence allocation across sources, horizons, and latent disturbances.", "themes": [ "predictions", "agents", "structure" ], "papers": [ "prediction-specific", "disc", "q-value-advice", "bellman-jensen" ] }, { "id": "coordinated-infrastructure", "title": "Coordinated low carbon infrastructure", "question": "Can distributed energy and water resources adapt together under changing conditions?", "description": "Combine local feasibility summaries with distributed predictive control and contextual energy models. Open questions include communication limits, distribution shift, and guarantees across coupled physical networks.", "themes": [ "energy", "control", "structure" ], "papers": [ "predsls", "aggregate-flexibility", "ood-charging", "water-control", "opencem" ] }, { "id": "accountable-agents", "title": "Accountable learning across agents", "question": "How should shared models balance efficiency, strategic risk, and equity?", "description": "Connect the downstream objectives of public models to robust strategic decision making. A key challenge is evaluating advice when its benefits and failures are distributed unevenly across participating agents.", "themes": [ "games", "predictions", "agents" ], "papers": [ "equitable-models", "safe-play", "strategic-advice", "lead" ] } ] }