[ICLR 2026] Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs
🤝 Open to Collab
Minji Kim
byminji
AI & ML interests
Video Understanding, Vision and Language Models, Multimodal Large Langauge Models
Recent Activity
updated a model about 13 hours ago
byminji/DBTrimKV-Qwen3-VL-8B-Thinking-full-mixture-frames768 published a model about 13 hours ago
byminji/DBTrimKV-Qwen3-VL-8B-Thinking-full-mixture-frames768 upvoted a paper 5 months ago
Grounding World Simulation Models in a Real-World MetropolisOrganizations
models 5
byminji/DBTrimKV-Qwen3-VL-8B-Thinking-full-mixture-frames768
Updated
byminji/TC-CLIP
Video-Text-to-Text • Updated • 2
byminji/LLaVA-NeXT-13B-Video-FT
Video-Text-to-Text • 13B • Updated • 5
byminji/LLaVA-NeXT-7B-Video-FT
Video-Text-to-Text • 7B • Updated • 5
byminji/Mini-InternVL-4B-Video-FT
Video-Text-to-Text • 4B • Updated • 99