arxiv:2510.16333
JunhaSong
junha1125
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 hour ago
Omni-Modal LLMs Know More Than They Say upvoted a paper about 3 hours ago
Speculative Forcing for Efficient Autoregressive Video Generation upvoted a paper 1 day ago
Learning Transferable World-Action Models from Task-Paired Human VideosOrganizations
None yet
models 4
junha1125/gaze-attention-qwen3-4b-384-onevision
Image-Text-to-Text • 5B • Updated • 39 • 1
junha1125/gaze-attention-qwen3-4b-video
Video-Text-to-Text • 5B • Updated • 50 • 1
junha1125/gaze-attention-qwen3-4b-512
Image-Text-to-Text • 5B • Updated • 38 • 1
junha1125/gaze-attention-qwen3-4b-384
Image-Text-to-Text • 5B • Updated • 49 • 1