Minji Kim

byminji's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset about 19 hours ago

byminji/VideoChat2-IT-clean

Updated about 19 hours ago • 3

updated a collection about 19 hours ago

Map-the-Flow

Collection

Model collection for the ICLR 2026 paper "Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs" • 4 items • Updated about 19 hours ago

published a dataset about 20 hours ago

byminji/VideoChat2-IT-clean

Updated about 19 hours ago • 3

updated a collection 2 days ago

Map-the-Flow

Collection

Model collection for the ICLR 2026 paper "Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs" • 4 items • Updated about 19 hours ago

updated a model 2 days ago

byminji/TC-CLIP

Updated 3 days ago

updated 2 models 3 days ago

byminji/Mini-InternVL-4B-Video-FT

4B • Updated 3 days ago • 14

byminji/LLaVA-NeXT-13B-Video-FT

13B • Updated 4 days ago • 8

published a model 3 days ago

byminji/TC-CLIP

Updated 3 days ago

updated a model 4 days ago

byminji/LLaVA-NeXT-7B-Video-FT

7B • Updated 4 days ago • 3

published 3 models 4 days ago

byminji/Mini-InternVL-4B-Video-FT

4B • Updated 3 days ago • 14

byminji/LLaVA-NeXT-13B-Video-FT

13B • Updated 4 days ago • 8

byminji/LLaVA-NeXT-7B-Video-FT

7B • Updated 4 days ago • 3

authored 2 papers about 1 month ago

Towards Sequence-Level Training for Visual Tracking

Paper • 2208.05810 • Published Aug 11, 2022

Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking

Paper • 2205.11179 • Published May 23, 2022

authored a paper 4 months ago

Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs

Paper • 2510.13251 • Published Oct 15, 2025 • 14

upvoted a paper 4 months ago

Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs

Paper • 2510.13251 • Published Oct 15, 2025 • 14

upvoted a paper 8 months ago

Token Bottleneck: One Token to Remember Dynamics

Paper • 2507.06543 • Published Jul 9, 2025 • 20

authored a paper over 1 year ago

Leveraging Temporal Contextualization for Video Action Recognition

Paper • 2404.09490 • Published Apr 15, 2024