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
911 results for “keyword:"dr"” in ICLR 2027. 266 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Space-sampled Value Decay: Forgetting Mechanisms for Non-stationary Reinforcement Learning▲3.0k2.33
[PDF]AgentDriftBench: Measuring Adaptation Dynamics of LLM Agents under Mid-Evaluation Environment Drift▼1361.33
[PDF]Learning composable time-unconditional molecular energy landscapes for zero-shot environmental transfer▼1.2k1.67
[PDF]TSea: A Large-Scale Dataset of Synthetic Ternary Complexes for Molecular Glue Modeling▲3.0k2.33
[PDF]MOLFRA: Online Alignment of Multimodal Molecular Flows via Forward-Process Reinforcement Learning▲6.1k2.00
[PDF]Gauge and Drift: Separating Commanded Change from Error Accumulation in Autoregressive Generation▼5.8k2.33
[PDF]RAVEL: Collision-Verified State Augmentation for Long-Context Recurrent Language Models▲6.1k2.00
[PDF]Seeing Risk Before It Happens: Risk-Augmented World Model for Anticipatory Driving Risk Understanding▼5.8k2.33
[PDF]When Should the Decision Change? Counterfactual Probing of Vision-Language Models for Autonomous Driving▼4.3k2.00
[PDF]Gaussian for Gaussian: Unifying Feature Representation and Rendering in Feed-Forward Driving Scene Reconstruction▼4.5k2.25
[PDF]MCD-EEG: Can a Non-Stationary Spatio-Temporal EEG Benchmark Evaluate Brainprint Recognition Across Tasks, Re-caps, and Populations?▲3.0k2.33
[PDF]TrajForward: Feed-Forward Dynamic 3D Gaussian Reconstruction for Urban Driving Scenes with Explicit Motion Trajectories▼1.2k3.00
[PDF]One Encoding, Continuous Lead Times: Coherent Atmospheric Representations with Compositional Finite-Time Flows▼1361.33
[PDF]MAX-Cache: Motion-Aligned Activation Reuse with Mismatch-Guided Selective Recomputation for Efficient Autoregressive Video Diffusion▲3952.67
[PDF]MirageDrive: Semantically Aligned Appearance Transfer with an Exemplar for Multi-View Driving Scene Generation▼5.8k2.33
[PDF]DreamIF: Intention-Guided Sparse Dynamics Prediction for Long-Horizon Vision-Language-Action Manipulation▲6.1k2.00
[PDF]EquiSolv: O(3)-Equivariant Neural Networks for Predicting Protein Solvation Energy Fields▼13k2.00
[PDF]Do World-Action Models Need Dense World Context? Progressive Sparse Forcing for Action DiTs▲3952.67
[PDF]CovaTide: Covalent Topology-Conditioned All-Atom Flow Matching For Linear and Cyclic Peptide Design▲5103.00
Withdrawn or desk rejected (266)
[PDF]Machine Love: Emergent Bonding Behavior in Large Language Models and Its Implications for AI SafetyDesk rejected
[PDF]Probing Interaction Awareness in Trajectory Prediction with Counterfactual PerturbationsDesk rejected
[PDF]Auto-JEPA: A Latent World Model of Continuous Intent for End-to-End Autonomous DrivingWithdrawn1.67