Huang

Jinfa's activity

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

upvoted a paper 7 days ago

Hierarchical Continuous Diffusion Language Models

Paper • 2610.02193 • Published 9 days ago • 91

authored 4 papers 8 days ago

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs

Paper • 2506.05260 • Published Jun 5, 2025

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation

Paper • 2607.23265 • Published Aug 3 • 1

TimePLE: Rethinking Temporal Representation for Video Temporal Grounding

Paper • 2607.23951 • Published Jul 27 • 1

VideoLoop: Looped Working Memory Against Semantic Thrashing in Long-Form Video Agents

Paper • 2609.38119 • Published 11 days ago • 12

upvoted 5 papers 9 days ago

OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?

Paper • 2609.38079 • Published 11 days ago • 56

EpiCon: Collective Agent Learning through Co-Evolving Multimodal Memory

Paper • 2609.37923 • Published 11 days ago • 9

Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies

Paper • 2609.38155 • Published 11 days ago • 115

MaLiang-Harness: A Programmable Path to Image and Video Generation

Paper • 2609.34309 • Published 12 days ago • 413

VideoLoop: Looped Working Memory Against Semantic Thrashing in Long-Form Video Agents

Paper • 2609.38119 • Published 11 days ago • 12

submitted a paper to Daily Papers 9 days ago

VideoLoop: Looped Working Memory Against Semantic Thrashing in Long-Form Video Agents

Paper • 2609.38119 • Published 11 days ago • 12

upvoted a paper 9 days ago

Recursive Multi-Agent Systems

Paper • 2604.25917 • Published Jul 13 • 240

upvoted a paper 27 days ago

Programmable World Model

Paper • 2609.10540 • Published about 1 month ago • 114

upvoted a paper 30 days ago

VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification

Paper • 2609.06245 • Published Sep 5 • 28

upvoted a paper about 1 month ago

TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming

Paper • 2608.20958 • Published Aug 21 • 60

upvoted 2 papers about 2 months ago

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published Aug 20 • 176

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Paper • 2608.17426 • Published Aug 18 • 161

liked 2 models about 2 months ago

Lightricks/LTX-2.5

Image-to-Video • Updated 7 days ago • 1.69M • 7k

meta-models/Muse-Glimmer-30B

Image-Text-to-Text • 30B • Updated Aug 11 • 259k • • 1.99k

upvoted a paper 2 months ago

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

Paper • 2608.05000 • Published Aug 6 • 65