Wenxuan Song
Wenxuan123
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 6 hours ago
Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning
upvoted
a
paper
about 1 month ago
HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models
upvoted
a
paper
about 2 months ago
UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios
Organizations
None yet