Accepted paper list
Robot Skill Puzzles: Decentralized Skill Priors for Humanoid–Environment Interaction
Paired Action-Intervention Audits for Foundation-Model Robot Planning
A Pragmatist Robot: Learning to Plan Tasks by Experiencing the Real World
DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?
Post-Training Vision--Language--Action Models to Attend Less
OMG: Omni-Modal Motion Generation for Generalist Humanoid Control
Planning Where to Look: Foundation-Model-Guided Active View Planning for Reliable Manipulation
Dense to MoE Adaptation for Efficient Vision Language Action Policies
Coarse-to-Control: Action-Token Planning for Vision-Language-Action Models
Spatially-Enhanced Recurrent Memory and Perception Pretraining for Long-Range Mapless Navigation from Egocentric Vision
Adapting Generalist Robot Policies with Semantic Reinforcement Learning
Green for Go, Red for No: Visual Grounding via Semantic Segmentation for VLA Navigation Policies
Discrete-Continuous Factor Graph Inference for Vision-and-Language Navigation
Act to See: Structured Articulated Representations through Robot Interaction
Reducing Temporal Redundancy for Efficient Vision-Language-Action Inference
What Matters in RL-Based Methods for Object-Goal Navigation? An Empirical Study and A Unified Framework
HeRo-Nav: Heterogeneous Multi-Robot Collaboration for Semantic Navigation with Vision Language Models
Discriminative Barrier Functions for Safe Adversarial Imitation Learning from Observation
A Planner-Centered Study of Robust Latent World Models
Emergent Neural Automaton Policies: Learning Symbolic Structure from Visuomotor Trajectories
Zero-Shot Generative World Priors for Planning and Object Reaching in Partially Observed Rooms
MEMORA: Embodied Action Memory from Egocentric Videos for Reasoning and Planning
Stable 3D Tokens for Foundation-Model Robot Planning