QuanjianSong

QuanjianSong's activity

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

upvoted a paper 3 days ago

minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models

Paper • 2605.30263 • Published 4 days ago • 49

upvoted 3 papers 5 days ago

WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation

Paper • 2605.25874 • Published 7 days ago • 100

Rethinking Cross-Layer Information Routing in Diffusion Transformers

Paper • 2605.20708 • Published 12 days ago • 109

DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning

Paper • 2605.25604 • Published 7 days ago • 132

upvoted a paper 6 days ago

Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration

Paper • 2605.17423 • Published 15 days ago • 31

updated a dataset 8 days ago

QuanjianSong/HGC-Bench

Viewer • Updated 8 days ago • 481 • 730 • 2

upvoted a paper 8 days ago

FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization

Paper • 2605.15824 • Published 17 days ago • 64

liked a dataset 8 days ago

QuanjianSong/HGC-Bench

Viewer • Updated 8 days ago • 481 • 730 • 2

published a dataset 8 days ago

QuanjianSong/HGC-Bench

Viewer • Updated 8 days ago • 481 • 730 • 2

updated a dataset 8 days ago

QuanjianSong/EgoExo-Synthetic

Viewer • Updated 8 days ago • 7.89k • 5.41k • 1

upvoted a paper 10 days ago

D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models

Paper • 2605.05204 • Published 26 days ago • 27

upvoted a paper 12 days ago

CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization

Paper • 2605.19436 • Published 13 days ago • 14

upvoted 7 papers 13 days ago

Stress-Testing the Reasoning Competence of LLMs With Proofs Under Minimal Formalism

Paper • 2605.12524 • Published Apr 7 • 4

No One Knows the State of the Art in Geospatial Foundation Models

Paper • 2605.12678 • Published 20 days ago • 3

AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting

Paper • 2506.01015 • Published 18 days ago • 3

Raster2Seq: Polygon Sequence Generation for Floorplan Reconstruction

Paper • 2602.09016 • Published 21 days ago • 5

Physics-R1: An Audited Olympiad Corpus and Recipe for Visual Physics Reasoning

Paper • 2605.14040 • Published 19 days ago • 5

Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution

Paper • 2605.15138 • Published 18 days ago • 6

Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization

Paper • 2605.15980 • Published 17 days ago • 36

submitted a paper to Daily Papers 14 days ago

OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation

Paper • 2605.12038 • Published 20 days ago • 4