Hyun, Jeongseok

js-hyun's activity

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

upvoted 2 papers about 7 hours ago

SAMTok: Representing Any Mask with Two Words

Paper • 2601.16093 • Published 2 days ago • 34

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Paper • 2601.14724 • Published 3 days ago • 59

upvoted a paper 10 days ago

Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning

Paper • 2601.06943 • Published 13 days ago • 206

upvoted a paper 12 days ago

VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice

Paper • 2601.05175 • Published 16 days ago • 34

upvoted a paper 15 days ago

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Paper • 2601.05242 • Published 16 days ago • 204

upvoted a paper 17 days ago

K-EXAONE Technical Report

Paper • 2601.01739 • Published 20 days ago • 87

upvoted a paper 23 days ago

End-to-End Test-Time Training for Long Context

Paper • 2512.23675 • Published 26 days ago • 20

upvoted 2 papers 29 days ago

NVIDIA Nemotron 3: Efficient and Open Intelligence

Paper • 2512.20856 • Published Dec 24, 2025 • 35

Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Paper • 2512.20848 • Published Dec 23, 2025 • 35

upvoted 2 papers about 1 month ago

QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management

Paper • 2512.12967 • Published Dec 15, 2025 • 107

Sliding Window Attention Adaptation

Paper • 2512.10411 • Published Dec 11, 2025 • 20

upvoted a paper about 2 months ago

ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement Learning

Paper • 2512.02835 • Published Dec 2, 2025 • 10

updated a dataset about 2 months ago

js-hyun/decaf_data

Viewer • Updated Dec 8, 2025 • 32.3k • 5

published a dataset about 2 months ago

js-hyun/decaf_data

Viewer • Updated Dec 8, 2025 • 32.3k • 5

upvoted 3 papers about 2 months ago

Qwen3-VL Technical Report

Paper • 2511.21631 • Published Nov 26, 2025 • 151

Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout

Paper • 2511.20649 • Published Nov 25, 2025 • 48

LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

Paper • 2511.20785 • Published Nov 25, 2025 • 184

upvoted 3 papers 2 months ago

VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models

Paper • 2511.11007 • Published Nov 14, 2025 • 15

REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding

Paper • 2511.13026 • Published Nov 17, 2025 • 26

VIDEOP2R: Video Understanding from Perception to Reasoning

Paper • 2511.11113 • Published Nov 14, 2025 • 111