Poster Number Paper Title
61 Enhancing Robot Safety via MLLM-Based Semantic Interpretation of Failure Data
62 Robot Policy Evaluation for Sim-to-Real Transfer: A Benchmarking Perspective
63 Don’t Touch Me There! Comfortability with Robot Touch Across Different Roles and Settings
64 Flexible Multitask Learning with Factorized Diffusion Policy
65 Action understanding as a social-cognitive benchmark for human-aligned robotics
66 Is Your Imitation Learning Policy Better Than Mine? Policy Comparison with Near-Optimal Stopping
67 Evaluating a Multi-Modal Robotic Approach for Deconstruction Inspection: A POP-Based Comparison with a Manual Approach
68 AutoEval: Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real World
69 Using Language and Road Manuals to Inform Map Reconstruction for Autonomous Driving
70 Efficient Evaluation of Multi-Task Robot Policies With Active Experiment Selection
71 STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation
72 CUPID: Curating Data your Robot Loves with Influence Functions
73 Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies
74 Trustworthy Conceptual Explanations for Neural Networks in Robot Decision-Making
Enhancing Robot Safety via MLLM-Based Semantic Interpretation of Failure Data
Robot Policy Evaluation for Sim-to-Real Transfer: A Benchmarking Perspective
Don’t Touch Me There! Comfortability with Robot Touch Across Different Roles and Settings
Flexible Multitask Learning with Factorized Diffusion Policy
Action understanding as a social-cognitive benchmark for human-aligned robotics
Is Your Imitation Learning Policy Better Than Mine? Policy Comparison with Near-Optimal Stopping
Evaluating a Multi-Modal Robotic Approach for Deconstruction Inspection: A POP-Based Comparison with a Manual Approach
AutoEval: Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real World
Using Language and Road Manuals to Inform Map Reconstruction for Autonomous Driving
Efficient Evaluation of Multi-Task Robot Policies With Active Experiment Selection
STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation
CUPID: Curating Data your Robot Loves with Influence Functions
Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies
Trustworthy Conceptual Explanations for Neural Networks in Robot Decision-Making