Hyun, Jeongseok

js-hyun's activity

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

upvoted a paper 7 days ago

Planning with Reasoning using Vision Language World Model

Paper • 2509.02722 • Published 9 days ago • 16

upvoted a paper 12 days ago

Autoregressive Universal Video Segmentation Model

Paper • 2508.19242 • Published 16 days ago • 26

upvoted a paper 18 days ago

NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

Paper • 2508.14444 • Published 23 days ago • 36

upvoted a paper 22 days ago

LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

Paper • 2508.14041 • Published 23 days ago • 57

upvoted a paper 23 days ago

Ovis2.5 Technical Report

Paper • 2508.11737 • Published 27 days ago • 108

upvoted 6 papers about 1 month ago

Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity

Paper • 2508.05609 • Published Aug 7 • 29

Qwen-Image Technical Report

Paper • 2508.02324 • Published Aug 4 • 245

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens

Paper • 2508.01191 • Published Aug 2 • 235

Representation Shift: Unifying Token Compression with FlashAttention

Paper • 2508.00367 • Published Aug 1 • 15

Multimodal Referring Segmentation: A Survey

Paper • 2508.00265 • Published Aug 1 • 8

PixNerd: Pixel Neural Field Diffusion

Paper • 2507.23268 • Published Jul 31 • 51

upvoted 3 papers about 2 months ago

EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes

Paper • 2507.11407 • Published Jul 15 • 57

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation

Paper • 2507.10524 • Published Jul 14 • 69

Dynamic Chunking for End-to-End Hierarchical Sequence Modeling

Paper • 2507.07955 • Published Jul 10 • 24

upvoted a paper 2 months ago

Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs

Paper • 2507.07990 • Published Jul 10 • 45

upvoted a paper 3 months ago

SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models

Paper • 2504.11468 • Published Apr 10 • 29

upvoted a paper 4 months ago

UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations

Paper • 2505.08787 • Published May 13 • 14

upvoted 2 papers 5 months ago

It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization

Paper • 2504.13173 • Published Apr 17 • 19

CCMNet: Leveraging Calibrated Color Correction Matrices for Cross-Camera Color Constancy

Paper • 2504.07959 • Published Apr 10 • 11

upvoted a paper 8 months ago

Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks

Paper • 2501.08326 • Published Jan 14 • 34