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
11 results for “keyword:"robot safety"” in ICLR 2027. 5 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Uncovering Vulnerability of Vision-Language-Action Models under Joint-Level Physical Faults▼5.8k2.33
[PDF]ActForesight: Predictive Safety for Embodied Agents with Action-Conditioned Visual Futures and Motion Monitoring▼1.2k1.67
[PDF]Learning from Runtime Feedback with Failure-Bank Self-Evolution for Vision-Language-Action Models▼5.8k2.33
[PDF]Beyond Positive Bias: Customizing and Correcting Generative Robot Policies via Negative Guidance▼4.3k2.00