Profiles2024-2026
Wenxuan Song
The Hong Kong University of Science and Technology
3Papers
0Last author
6Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers3
- Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action ModelAuthor 2 of 8ICLR 2026 · 145 citations
- Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denosing Diffusion ProcessAuthor 2 of 8ICLR 2026 · 20 citations
- ProFD: Prompt-Guided Feature Disentangling for Occluded Person Re-IdentificationAuthor 3 of 6ACM MM 2024 · 18 citations
