12 papers
Demo2Tutorial: From Human Experience to Multimodal Software Tutorials
Zechen Bai, Zhiheng Chen, Yiqi Lin +5
Human experience in digital environments offers a vast, underexplored resource of authentic, untrimmed interactions that contain rich procedural knowledge. We introduce Demo2Tutori…
World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy
Xiaokang Liu, Zechen Bai, Hai Ci +2
Reinforcement learning (RL) can refine Vision-Language-Action (VLA) policies beyond behavior cloning, but real-world RL remains expensive due to extensive rollouts, resets, supervi…
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…
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…
SIGMA: Selective-Interleaved Generation with Multi-Attribute Tokens
Xiaoyan Zhang, Zechen Bai, Haofan Wang +1
Recent unified models such as Bagel demonstrate that paired image-edit data can effectively align multiple visual tasks within a single diffusion transformer. However, these models…
EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models
Zechen Bai, Chen Gao, Mike Zheng Shou
Achieving truly adaptive embodied intelligence requires agents that learn not just by imitating static demonstrations, but by continuously improving through environmental interacti…