10 papers
Show-Harness: Just a VLM Agent Can Play Robots
Yanzhe Chen, Zechen Bai, Zhijun Cao +7
Foundation vision-language models (VLMs) exhibit broad intelligence about the world, yet translating this intelligence into robot control remains challenging. We present Show-Harne…
Where Success Breaks: Failure-Boundary Learning for Robust Vision-Language-Action Models
Yanzhe Chen, Zhijun Cao, Mike Zheng Shou
Vision-language-action (VLA) models adapted through supervised fine-tuning (SFT) inherit a structural asymmetry: expert demonstrations teach the policy where success behavior lies,…
Supervise What Survives: Geometry-Guided VLA Adaptation from Synthetic Robot Videos
Danze Chen, Yanzhe Chen, Qiming Huang +3
Vision-Language-Action (VLA) models require large-scale video-action pairs, yet real teleoperation remains scarce. While generated robot videos offer a scalable alternative, existi…
ActionMap: Robot Policy Learning via Voxel Action Heatmap
Pei Yang, Hai Ci, Yanzhe Chen +3
Vision-language-action (VLA) models have advanced rapidly across backbones, training recipes, and data scale, yet the action decoder, which converts the backbone's hidden state int…
Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation
Yanzhe Chen, Kevin Yuchen Ma, Qi Lv +4
While Vision-Language-Action (VLA) models offer broad general capabilities, deploying them on specific hardware requires real-world adaptation to bridge the embodiment gap. Since r…
Spectral Surgery: Training-Free Refinement of LoRA via Gradient-Guided Singular Value Reweighting
Zailong Tian, Yanzhe Chen, Zhuoheng Han +1
Low-Rank Adaptation (LoRA) improves downstream performance by restricting task updates to a low-rank parameter subspace, yet how this limited capacity is allocated within a trained…
Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance
Yiqi Lin, Guoqiang Liang, Ziyun Zeng +3
Instruction-based video editing has witnessed rapid progress, yet current methods often struggle with precise visual control, as natural language is inherently limited in describin…
Code2Video: A Code-centric Paradigm for Educational Video Generation
Yanzhe Chen, Kevin Qinghong Lin, Mike Zheng Shou
While recent generative models advance pixel-space video synthesis, they remain limited in producing professional educational videos, which demand disciplinary knowledge, precise v…
UniAPO: Unified Multimodal Automated Prompt Optimization
Qipeng Zhu, Yanzhe Chen, Huasong Zhong +5
Prompting is fundamental to unlocking the full potential of large language models. To automate and enhance this process, automatic prompt optimization (APO) has been developed, dem…
UniCode: Cascaded Large-scale Codebooks for Unified Multimodal Understanding and Generation
Yanzhe Chen, Huasong Zhong, Yan Li +1
Unified multimodal large language models (MLLMs) have shown promise in jointly advancing multimodal understanding and generation, with visual codebooks discretizing images into tok…