詹佳豪

JohnZhan's activity

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

upvoted a paper 5 days ago

TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing

Paper • 2611.06741 • Published 7 days ago • 44

upvoted a paper 28 days ago

FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching

Paper • 2610.17552 • Published 29 days ago • 31

upvoted a paper 29 days ago

SpatialASM: Internalizing Active Mentalization for Spatial Reasoning

Paper • 2610.13832 • Published Oct 9 • 20

liked a model about 1 month ago

ruchangyao/FlashVSR_plus

Video-to-Video • Updated 28 days ago • 1.19k • 36

upvoted 2 papers about 1 month ago

SGF+: Decoupling Gradient Flows for Autoregressive Video Generation

Paper • 2610.10429 • Published Oct 7 • 44

DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation

Paper • 2610.03543 • Published Oct 2 • 82

submitted a paper to Daily Papers about 1 month ago

DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation

Paper • 2610.03543 • Published Oct 2 • 82

authored 7 papers about 1 month ago

Code2Logic: Game-Code-Driven Data Synthesis for Enhancing VLMs General Reasoning

Paper • 2505.13886 • Published May 20, 2025 • 11

Fake it till You Make it: Reward Modeling as Discriminative Prediction

Paper • 2506.13846 • Published Jun 16, 2025

MAC: A Live Benchmark for Multimodal Large Language Models in Scientific Understanding

Paper • 2508.15802 • Published Aug 14, 2025

CML-Bench: A Framework for Evaluating and Enhancing LLM-Powered Movie Scripts Generation

Paper • 2510.06231 • Published Oct 1, 2025

Agentic Visual Generation: From Generative Models to Agentic Control

Paper • 2609.06758 • Published Sep 6 • 21

MotionInsight: Diagnosing Object Motion Deficiencies in Generated Videos

Paper • 2609.37030 • Published Sep 29 • 1

DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation

Paper • 2610.03543 • Published Oct 2 • 82

updated a model about 1 month ago

JohnZhan/MotionInsight-8B

Video-Text-to-Text • 832k • Updated Oct 3 • 47 • 2

liked a model about 1 month ago

JohnZhan/DuoMatching

Updated Oct 2 • 4

updated a model about 1 month ago

JohnZhan/DuoMatching

Updated Oct 2 • 4

published a model about 1 month ago

JohnZhan/DuoMatching

Updated Oct 2 • 4

published a model 2 months ago

JohnZhan/MotionInsight-8B

Video-Text-to-Text • 832k • Updated Oct 3 • 47 • 2

upvoted a paper 4 months ago

Color Pass-Through via Camera-Display Coupling

Paper • 2607.12746 • Published Jul 14 • 19