12 papers
Generalized Odds for Ordinal Outcomes: A Causal Inference Framework Adjusting for Covariates
Runnian Huang, Dandan Shi, Lan Liu +1
Background: Generalized Odds (Gen Odds) provide summaries for ordinal outcomes without requiring the proportional odds assumption. However, conventional Gen Odds compares independe…
EgoMatrix: Physically Faithful Dexterous Robot Demonstrations from Egocentric Human Videos
Ziheng Wang, Yanming Shao, Ting Mao +4
Egocentric human videos offer a scalable alternative to robot teleoperation for collecting dexterous manipulation data. However, two challenges limit their use as reliable training…
OmniHOI: Dexterous Hand-Object Interaction from Monocular Human Video
Ting Mao, Yanming Shao, Ziheng Wang +4
Monocular videos of human manipulation provide abundant dexterous demonstrations, yet reconstructing hand-object interaction from a single view and transferring it to robot hands r…
DexJoCo-X: Benchmarking Action Representations for Multi-Hand Dexterous Manipulation
Xiangwei Jiang, Yao Mu, Lixin Duan +1
As dexterous hands proliferate, collecting data and training policies separately for every morphology becomes increasingly impractical. Scalable cross-embodiment learning therefore…
SA-VLA: State-aware tokenizer for improving Vision-Language-Action Models' performance
Tengyue Jiang, Chunpu Xu, Jiayue Kang +1
Discrete action tokenization provides a compact interface for autoregressive VLA policies, but accurately recovering continuous robot actions from discrete codes remains challengin…
BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models
Zhongxi Chen, Yifan Han, Bin Qiu +8
Vision-Language-Action (VLA) policies provide strong behavioral priors for dexterous manipulation, yet adapting them on real robots remains challenging because high-DoF contact fai…
Q-VGM: Q-Guided Value-Gradient Matching for Offline-to-Online RL of Flow-Matching VLA Policies
Ziqian Wang, Rui Zhang, Yitian Liu +3
We propose Q-Guided Value-Gradient Matching (Q-VGM), an offline-to-online RL method for fine-tuning flow-matching vision-language-action policies with a learned critic. Directly ap…
PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World
Yunhan Yang, Chunshi Wang, Junliang Ye +7
Synthesizing physics-grounded 3D assets is a critical bottleneck for interactive virtual worlds and embodied AI. Existing methods predominantly focus on static geometry, overlookin…
JailWAM: Jailbreaking World Action Models in Robot Control
Hanqing Liu, Songping Wang, Jiahuan Long +9
World Action Models (WAMs) have emerged as a promising paradigm for robotic manipulation, enabling physical interaction across diverse tasks and environments. However, their abilit…
DexHiL: A Human-in-the-Loop Framework for Vision-Language-Action Model Post-Training in Dexterous Manipulation
Yifan Han, Zhongxi Chen, Yuxuan Zhao +5
While Vision-Language-Action (VLA) models have demonstrated promising generalization capabilities in robotic manipulation, deploying them on specific and complex downstream tasks s…
FMimic: Foundation Models are Fine-grained Action Learners from Human Videos
Guangyan Chen, Meiling Wang, Te Cui +8
Visual imitation learning (VIL) provides an efficient and intuitive strategy for robotic systems to acquire novel skills. Recent advancements in foundation models, particularly Vis…
VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions
Guanyan Chen, Meiling Wang, Te Cui +9
Visual imitation learning (VIL) provides an efficient and intuitive strategy for robotic systems to acquire novel skills. Recent advancements in Vision Language Models (VLMs) have…