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
315 results for “keyword:"robot manipulation"” in ICLR 2027. 120 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]LIBERO-RECOVER: Beyond Task Success Towards Failure Recovery in Robotic Manipulation Models▼1.2k3.00
[PDF]SimpleTouch: Can Vision-Language-Action Models Master Contact-Rich Manipulation Without Tactile Policy Pretraining?▲14k3.00
[PDF]CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models▼5.8k2.33
[PDF]Vision-Language-Action Models are Inherent Verifiers: Test-Time-Scaling via Likelihood-Based Visual Prompting▼4.3k2.00
[PDF]Thinking in Trajectories: Structured Exploration for Vision-Language-Action Reinforcement Learning▲3952.67
[PDF]DGA-VLA: A Lightweight Depth-Guided Grasp Enhancement for VLA Models without Retraining▲11k2.00
[PDF]What Makes Two Robot Failures the Same? Learning Recoverability Functions for Zero-Shot Robot Recovery▼1.2k1.67
[PDF]Beyond Positive Bias: Customizing and Correcting Generative Robot Policies via Negative Guidance▼4.3k2.00
[PDF]CoRe-WAM: Condition-Aligned Distillation and Recurrent Action Refinement for Efficient World-Action Models▼4.5k2.67
[PDF]RoboHarn-Evo: Evolving Hierarchical Physical Knowledge for Self-Improving Robotic Manipulation▼1.2k1.67
[PDF]RoMAN-Flow: Taming Autoregressive Normalizing Flows for Offline Reinforcement Learning in Robotic Manipulation▼5.8k2.33
[PDF]Phys-WorldBench: A Unified Benchmark for Evaluating Embodied World Models from Passive Prediction to Active Intervention▲5103.00
[PDF]Flowing With Purpose: Latent Action Guided Flow Matching Policies For Robotic Manipulation▼4.3k2.00
[PDF]RoboValue: A Fine-Grained Sim-and-Real Benchmark for Unified Evaluation of Robotic Value Models▼5.8k2.33
[PDF]LIBERO-Industry: Benchmarking Robotic Manipulation under Industrial Process Constraints▲3.0k2.33
[PDF]FutureDuet: Decoupling Observation Access from Future Supervision in World Action Models▼4.5k2.67
[PDF]WALA: Learning Executable Latent Actions from Action-Labeled Demonstrations and Action-Free Videos▼5.8k2.33
[PDF]Equivariance Begins at the Source: Characterizing Compatible Sources for Generative Robot Policies▲5103.00
[PDF]Give the Policy Its View Back: Recovering Frozen Visuomotor Policies from Camera Drift▲8.9k2.75
Withdrawn or desk rejected (120)
[PDF]Defect Responses in Visual World Models: Long-Horizon Propagation, Gradient Interaction, and Planning OutcomesWithdrawn1.33
[PDF]WorldMirror: Agentic Real-to-Sim Generation of Interactive Worlds from In-the-Wild Robot DemonstrationsWithdrawn1.67
[PDF]Is Online Interaction Necessary for Recovery? A Minimalist Approach to Robust Planning via PerturbationWithdrawn1.33
[PDF]Revision, Not Restart: Revisable Visual Plans for Closed-Loop World-Action ModelsDesk rejected2.00
[PDF]PRODUCT-SET DEFICIENCY: A TRAINING -FREE MEASURE OF JOINT-ACTION COUPLING IN MULTI -ROBOT TASKSWithdrawn1.67