1 citations · 1 across the 4 of their papers we have counts for
6 papers
World-Calibrated Proposal-to-Action Flow for Vision-Language-Action Models
Jie He, Wei Li, Junwen Tong +3
Flow-based Vision-Language-Action (VLA) policies generate action chunks by transporting samples from a task-agnostic isotropic Gaussian source. As this source is conditioned on nei…
Scaling Versatile 3D Assets Editing with a Million-Scale Dataset
Badi Li, Tianxin Huang, Yu Zhou +3
Although recent 3D generative models produce increasingly realistic assets, controllable 3D asset editing remains challenging. Existing methods are limited by scarce training data,…
Task Editing for Generalizable 3D Visuomotor Policy Learning
Jian-Jian Jiang, YiHan Yang, Lan Wei +6
3D visuomotor policies offer a promising direction for complex robotic manipulation, as depth maps and point clouds provide rich geometric information for spatial reasoning. Howeve…
Distilling LLM Prior to Flow Model for Generalizable Agent's Imagination in Object Goal Navigation
Badi Li, Ren-jie Lu, Yu Zhou +2
The Object Goal Navigation (ObjectNav) task challenges agents to locate a specified object in an unseen environment by imagining unobserved regions of the scene. Prior approaches r…
Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks
Yu Zhou, Dian Zheng, Qijie Mo +3
In this work, we present DEcoupLEd Distillation To Erase (DELETE), a general and strong unlearning method for any class-centric tasks. To derive this, we first propose a theoretica…
VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness
Dian Zheng, Ziqi Huang, Hongbo Liu +9
Video generation has advanced significantly, evolving from producing unrealistic outputs to generating videos that appear visually convincing and temporally coherent. To evaluate t…