[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 7 days ago
byminji/DBTrimKV-Qwen3-VL-8B-Thinking-eb4-m4pct20 published a model 7 days ago
byminji/DBTrimKV-Qwen3-VL-8B-Thinking-eb4-m4pct20 updated a model 10 days ago
byminji/DBTrimKV-Qwen3-VL-8B-Thinking-full-mixture-frames768Organizations
models 6
byminji/DBTrimKV-Qwen3-VL-8B-Thinking-eb4-m4pct20
Updated • 12
byminji/DBTrimKV-Qwen3-VL-8B-Thinking-full-mixture-frames768
Updated • 11
byminji/TC-CLIP
Video-Text-to-Text • Updated • 2
byminji/LLaVA-NeXT-13B-Video-FT
Video-Text-to-Text • 13B • Updated • 7
byminji/LLaVA-NeXT-7B-Video-FT
Video-Text-to-Text • 7B • Updated • 8
byminji/Mini-InternVL-4B-Video-FT
Video-Text-to-Text • 4B • Updated • 101