RethinkingSafety@RSS2026

Accepted Papers

All papers will participate in a poster session.

Poster Location: Building 11, Level B3, Room 101

Please print A0 portrait oriented posters.

Camera Ready Submissions Due: July 11, 11:59 PM AOE

Uncertainty Quantification for Flow-Based VLAs (Spotlight)

Ralf Römer, Maximilian Seeliger, Saida Liu , Ben Sturgis, Marco Bagatella, Daniel Marta, Andreas Krause, Angela P. Schoellig

Anticipating Unintended Robot Behaviors with Side Effect Critics (Spotlight)

Ryan Lindeborg, Richard Peng, Ayush Jain, Jesse Zhang, Abrar Anwar, Jesse Thomason

S2-NAMO: Semantically Safe Navigation Among Movable Obstacles (Spotlight)

Hyeongchan Ham, Boseok Kim, Minwoo Song, Heejin Ahn

Decoding Task Progress from VLA Representations (Spotlight)

Atiksh Bhardwaj, Edward Duan, Prithwish Dan, Wei-Chiu Ma, Preston Culbertson

Data-Efficient Verification of Black-box Controllers via Flow Matching and Conformal Inference (Spotlight)

Dhruv Metha Ramesh, Sumanth Tangirala, Mufang Ying, Riddhima Medatwal, Ewerton Vieira, Abdeslam Boularias, Ying Hung, Kostas Bekris

Decomposing VAM Uncertainty: Training-Free and Supervised Probes for Robot Failure Detectio

Liza Dahiya, Naman Kumar, Ziyin Xiong, Andrea Bajcsy

Green for Go, Red for No: Visual Grounding via Semantic Segmentation for VLA Navigation Policies

Adrian Szvoren, Dimitrios Kanoulas, Nilufer Tuptuk

Safe Imitation Learning under Partial Observability: A Wasserstein Belief-Space Analysis

Tianqi Zhu

GNFF: A Graph-based Negative Feedback fine-tuning Technique to Prevent Deceptive Alignment and Improve Robotic Safety using Large Language Models

Aniket Deroy

Validation Loss Is Not a Safety Signal

Joy Zheyun Yang, Socrates Osorio

Evaluating the Benefits of CoT in Long-Tail Autonomous Driving Scenarios

Michelle Li, Matthew Foutter, Daniele Gammelli, Jadelynn Dao, Marco Pavone

Initiation Safety: A Missing Dimension in Generalist-Robot Safety

Zhijin Meng, Francisco Cruz

Page updated

Report abuse