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
175 results for “keyword:"imitation"” in ICLR 2027. 42 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]JointLoom: Compact-State GPU Simulation and Streaming Imitation Learning for Multi-Agent Pathfinding▼4.3k2.00
[PDF]ObjectBinder-VLA: Permutation-Consistent Multi-View Grounding and Intent-Conditioned Dynamics▼4.3k2.00
[PDF]Conditional Policy Advantage: Changing the Expert or Test Physics Can Reverse Policy Rankings▲11.00
[PDF]Beyond Token-Average Loss: Rebalancing Control and Binding in Agent Policy Distillation▼1.2k1.67
[PDF]Decoder Silencing: Cloned GUI Agents Know When to Ask, and Greedy Decoding Discards It▼4.3k2.00
[PDF]When Connectomic Wiring Hinders Imitation: Interface Constraints and the Latency of Sensory Access▼4.3k2.00
[PDF]Excitation Collapse in In-Context Control: Symmetric Freezing and Symmetry-Broken Imitation▼4.3k2.00
[PDF]Representation Sufficiency for Closed-Loop Control: Decision Risk and the Occupancy Bridge▼1.2k1.67
[PDF]Dual-Process Atomic Skill Learning: Decoupling Semantic Reasoning and Real-Time Control▼4.3k2.75
[PDF]What Behavior Cloning Gives and Takes: Action Learning and Visual Reorganization in VLAs▼1361.33
[PDF]Offline Imitation Error as a Model-Selection Proxy Under Distribution Shift: Evidence from Real-Camera Active PTZ Control▼5.8k2.33
[PDF]Does Imitation Learning Preserve Expert Performance Across Task Execution Speeds? A Benchmark Study▲3.0k2.33
[PDF]RethinkDrive: Supervision Targets for Lightweight Trajectory Refinement in End-to-End Driving▼4.3k2.00
[PDF]JaxNaviSim: A GPU-Accelerated, Data-Driven Simulator and Learning Benchmark for Maritime Navigation▼3.7k2.25
[PDF]Breaking the Historical Action Shortcut: Mitigating Visual Modality Collapse in Gaming VLA Models via Historical Action Noise Injection▼5.9k2.50
[PDF]Robotic Optical Coherence Tomography-Guided Geometric Modeling of Soft Tissue: 3D Representations for Data-Driven Closed-Loop Shape Control▼5.8k2.33
[PDF]Learning Recurrent Belief Representations for Diffusion Policies with Predictive World Modeling▼4.3k2.00
Withdrawn or desk rejected (42)
[PDF]Reshaping Action Flow: Behavior Correction for Flow-Matching Vision-Language-Action PoliciesWithdrawn2.00
[PDF]Closed-Loop Satellite Collision Avoidance: A Benchmark and Planner-Guided Learning FrameworkWithdrawn1.67
[PDF]Sequence-Structured Decision Learning for Branch-and-Bound in Mixed-Integer Linear ProgrammingDesk rejected
[PDF]DemoPrior: Learning Unseen Robot Tasks from a Single Demonstration with Action-Space PriorsWithdrawn2.00