NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
158 results for “keyword:"model based"” in ICLR 2027. 41 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Uncertainty-Guided λ-Soft Value Estimation for Sample-Efficient Maximum Entropy Reinforcement Learning▼4.3k2.00
[PDF]Learning World Models with Joint-Embedding Prediction for Single- and Multi-Agent Reinforcement Learning▼1361.33
[PDF]World Models in Robotics and Autonomous Driving: A Survey of the Latency-Fidelity Trade-off and the Case for Unified Scene-Motion Dynamics▲11.00
[PDF]Learning Where to Go: Spectrally Aligned Surrogates and Search for Offline Model-Based Optimization▼4.3k2.00
[PDF]TAPE: A CELLULAR AUTOMATA BENCHMARK FOR EVALUATING RULE-SHIFT GENERALIZATION IN REINFORCEMENT LEARNING▲20k2.67
[PDF]Structured World Models for Sample-Efficient Planning in Partially Known Dynamical Systems▼4.5k2.67
[PDF]Second Thoughts: Exploring and Planning through Comparative Imagination in World Models▲3972.67
[PDF]Beyond Conservatism: Recoverability-Conditioned Exploration for Model-Based Imitation Learning▼4.5k2.67
[PDF]Finding Answers in Thought Matters: Revisiting Evaluation on Large Language Models with Reasoning▼1.2k1.67
Withdrawn or desk rejected (41)
[PDF]What Should I Try Next? Decision-Relevant Counterfactual Information Gain for Active World ModelsWithdrawn1.00
[PDF]Defect Responses in Visual World Models: Long-Horizon Propagation, Gradient Interaction, and Planning OutcomesWithdrawn1.33
[PDF]What Data Makes World Models Better Manipulation Planners? Beyond Successful Demonstrations with Diverse Action ExperienceWithdrawn1.00