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
291 results for “keyword:"robot learning"” in ICLR 2027. 79 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]AHA-WAM: Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing▲14k3.00
[PDF]ThoughtVLA: Evolving Thought Trajectories for Continual Vision-Language-Action Adaptation▼5.8k2.33
[PDF]DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning▲153.33
[PDF]Temporally Centered SIGReg Improves LeWorldModel Representations for Robot Policy Learning▼4.3k2.00
[PDF]What Should a VLM Tell an Action Expert? Comparing Conditioning Interfaces for Long-Horizon Furniture Assembly▼1361.33
[PDF]PerturBot: Breaking Shortcut Priors in Vision-Language-Action Models with Perturbative Training▲5103.00
[PDF]Not Every Step Is Progress: Event-Grounded Credit Reassignment for Robot Policy Learning▲3.0k2.33
[PDF]SCHEMA: Scalable Harness-Guided Temporal Quality Metadata Construction for Robotic Manipulation Learning▼4.5k2.25
[PDF]Xperience-0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience▲5103.00
[PDF]WARD: Watching Actions via Latent-Space Reachability for Runtime Backdoor Defense in VLA Models▼1.2k3.00
Withdrawn or desk rejected (79)
[PDF]PragyaMD: Parameter-Efficient Adaptation of Humanoid Motion Generators to Indic LanguagesDesk rejected
[PDF]Body Schema Policy: Learning a Body-Aware Vision-Action Interface for Efficient Humanoid Loco-ManipulationDesk rejected
[PDF]WorldMirror: Agentic Real-to-Sim Generation of Interactive Worlds from In-the-Wild Robot DemonstrationsWithdrawn1.67
[PDF]SURE: Spatiotemporal Uncertainty Representation for Efficient Vision-Language-Action LearningWithdrawn2.00