Hyun, Jeongseok

js-hyun's activity

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

upvoted a paper about 20 hours ago

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

Paper • 2603.12262 • Published 5 days ago • 26

upvoted a paper 5 days ago

Flash-KMeans: Fast and Memory-Efficient Exact K-Means

Paper • 2603.09229 • Published 8 days ago • 74

upvoted a paper 26 days ago

TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions

Paper • 2602.08711 • Published Feb 9 • 28

upvoted 2 papers about 1 month ago

HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache Sharing

Paper • 2602.03560 • Published Feb 3 • 47

OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models

Paper • 2602.04804 • Published Feb 4 • 48

updated a dataset about 1 month ago

js-hyun/STTM_output_backup

Updated Feb 2 • 8

published a dataset about 1 month ago

js-hyun/STTM_output_backup

Updated Feb 2 • 8

updated 2 datasets about 1 month ago

CIPLab-Video/decaf-rvos-revos

Updated Feb 2 • 48

js-hyun/DecAF_final_output

Updated Feb 2 • 8

published a dataset about 1 month ago

js-hyun/DecAF_final_output

Updated Feb 2 • 8

updated 2 datasets about 1 month ago

CIPLab-Video/decaf-rvos-davis17

Viewer • Updated Feb 2 • 12.4k • 16

CIPLab-Video/decaf-rvos-reasonvos

Viewer • Updated Feb 2 • 19.8k • 9

published 3 datasets about 1 month ago

CIPLab-Video/decaf-rvos-revos

Updated Feb 2 • 48

CIPLab-Video/decaf-rvos-reasonvos

Viewer • Updated Feb 2 • 19.8k • 9

CIPLab-Video/decaf-rvos-davis17

Viewer • Updated Feb 2 • 12.4k • 16

updated a dataset about 1 month ago

js-hyun/decaf-rvos-dataset

Updated Feb 2 • 9

published a dataset about 1 month ago

js-hyun/decaf-rvos-dataset

Updated Feb 2 • 9

upvoted 3 papers about 2 months ago

Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers

Paper • 2601.17367 • Published Jan 24 • 34

VideoMaMa: Mask-Guided Video Matting via Generative Prior

Paper • 2601.14255 • Published Jan 20 • 15

SAMTok: Representing Any Mask with Two Words

Paper • 2601.16093 • Published Jan 22 • 43