Yi Jung PRO

YJ-142150's activity

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

upvoted 2 papers 2 days ago

CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation

Paper • 2605.25378 • Published 7 days ago • 53

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

Paper • 2605.30280 • Published 4 days ago • 100

upvoted a paper 3 days ago

Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

Paper • 2605.28816 • Published 5 days ago • 404

upvoted a paper 4 days ago

Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction

Paper • 2605.26230 • Published 7 days ago • 39

upvoted 2 papers 8 days ago

SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation

Paper • 2605.22536 • Published 11 days ago • 28

Unsupervised Process Reward Models

Paper • 2605.10158 • Published 21 days ago • 26

upvoted a paper 9 days ago

WorldKV: Efficient World Memory with World Retrieval and Compression

Paper • 2605.22718 • Published 11 days ago • 41

upvoted a paper 11 days ago

Fast 4D Mesh Generation by Spatio-Temporal Attention Chains

Paper • 2605.19786 • Published 13 days ago • 10

upvoted 3 papers 12 days ago

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models

Paper • 2605.17672 • Published 15 days ago • 22

KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration

Paper • 2605.14278 • Published 18 days ago • 37

LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation

Paper • 2605.18739 • Published 14 days ago • 111

upvoted 2 papers 16 days ago

Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video

Paper • 2605.15182 • Published 18 days ago • 39

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Paper • 2605.15178 • Published 18 days ago • 84

upvoted 5 papers 17 days ago

Many-Shot CoT-ICL: Making In-Context Learning Truly Learn

Paper • 2605.13511 • Published 19 days ago • 32

Qwen-Image-VAE-2.0 Technical Report

Paper • 2605.13565 • Published 19 days ago • 60

Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling

Paper • 2605.13062 • Published 19 days ago • 33

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

Paper • 2605.13779 • Published 19 days ago • 219

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation

Paper • 2605.13724 • Published 19 days ago • 101

upvoted 2 papers about 1 month ago

Vista4D: Video Reshooting with 4D Point Clouds

Paper • 2604.21915 • Published Apr 23 • 12

MultiWorld: Scalable Multi-Agent Multi-View Video World Models

Paper • 2604.18564 • Published Apr 20 • 46