arxiv:2510.09426
DongJae Shin PRO
ShinDJ
AI & ML interests
NLP, LLM, Vision-Langauge Model
Recent Activity
liked a model about 14 hours ago
google/gemma-4-12B upvoted a paper about 17 hours ago
Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments upvoted a paper 3 days ago
SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer