15 papers
The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering
Yuqian Fu, Tianwen Qian, Yanjun Li +30
EgoCross is a cross-domain egocentric video question answering benchmark designed to evaluate whether multimodal large language models can generalize beyond common daily-life scena…
No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs
Haojian Huang, Harold Haodong Chen, Meng Luo +6
We introduce VidPair-Halluc, a new benchmark for evaluating video hallucination in large video models (LVMs) under rigorous and controlled conditions. Unlike previous benchmarks th…
AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding
Qize Yu, Jiadi You, Yuran Wang +12
Vision-Language-Action (VLA) models leverage the rich world knowledge of pretrained vision-language models (VLMs) to enable instruction-following robotic manipulation. However, the…
WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents
Yehang Zhang, Jianchong Su, Haojian Huang +7
To assist humans over extended periods in real homes, embodied agents must remember user routines, world states, and past interactions. Existing long-term memory benchmarks mainly…
The Right Inference Strategy Is All You Need: Nearly Training-Free Domain-Wise Inference for EgoCross Challenge
Leyi Wu, Yifan Zhao, Jinjie Zhang +2
EgoCross evaluates multimodal large language models on egocentric video question answering under substantial domain shift, where test videos come from surgery, industrial assembly,…
RoboStressBench: Benchmarking VLM Robustness to Physical Visual Stress in Embodied Scenes
Leyi Wu, Yifan Zhao, Jinjie Zhang +11
Vision-Language Models (VLMs) have shown strong visual understanding and are increasingly deployed in embodied AI systems, where reliable perception under real conditions is essent…
Affordance Agent Harness: Verification-Gated Skill Orchestration
Haojian Huang, Jiahao Shi, Yinchuan Li +1
Affordance grounding requires identifying where and how an agent should interact in open-world scenes, where actionable regions are often small, occluded, reflective, and visually…
Panoramic Affordance Prediction
Zixin Zhang, Chenfei Liao, Hongfei Zhang +10
Affordance prediction serves as a critical bridge between perception and action in embodied AI. However, existing research is confined to pinhole camera models, which suffer from n…
ActionCodec: What Makes for Good Action Tokenizers
Zibin Dong, Yicheng Liu, Shiduo Zhang +8
Vision-Language-Action (VLA) models leveraging the native autoregressive paradigm of Vision-Language Models (VLMs) have demonstrated superior instruction-following and training eff…
STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization
Hao Li, Qi Lv, Rui Shao +4
Transforming complex actions into discrete skill abstractions has demonstrated strong potential for robotic manipulation. Existing approaches mainly leverage latent variable models…
Conditioning Matters: Training Diffusion Policies is Faster Than You Think
Zibin Dong, Yicheng Liu, Yinchuan Li +2
Diffusion policies have emerged as a mainstream paradigm for building vision-language-action (VLA) models. Although they demonstrate strong robot control capabilities, their traini…
EmbodiedMAE: A Unified 3D Multi-Modal Representation for Robot Manipulation
Zibin Dong, Fei Ni, Yifu Yuan +2
We present EmbodiedMAE, a unified 3D multi-modal representation for robot manipulation. Current approaches suffer from significant domain gaps between training datasets and robot m…
Few-Shot Vision-Language Action-Incremental Policy Learning
Mingchen Song, Xiang Deng, Guoqiang Zhong +5
Recently, Transformer-based robotic manipulation methods utilize multi-view spatial representations and language instructions to learn robot motion trajectories by leveraging numer…
Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic Manipulation
Qi Lv, Hao Li, Xiang Deng +6
Despite the significant success of imitation learning in robotic manipulation, its application to bimanual tasks remains highly challenging. Existing approaches mainly learn a poli…
3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds
Hengshuo Chu, Xiang Deng, Qi Lv +4
3D Affordance detection is a challenging problem with broad applications on various robotic tasks. Existing methods typically formulate the detection paradigm as a label-based sema…