Huang

Jinfa's activity

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

upvoted a paper 9 days ago

IdeaTaste: Do LLMs Share the Research Taste of Human Researchers?

Paper • 2611.03424 • Published 11 days ago • 48

upvoted a paper 15 days ago

StreamVibe: Proactive Video Agents for Evolving User Intent

Paper • 2610.34662 • Published 18 days ago • 79

upvoted a paper 24 days ago

Learning to Think and Explore in 3D World

Paper • 2610.21783 • Published 29 days ago • 61

upvoted 3 papers 28 days ago

Learning Self-Orchestration in Decentralized Agent Swarms

Paper • 2610.22322 • Published 29 days ago • 14

3DCodeVerse: Exploring 3D Worlds as Code

Paper • 2610.22341 • Published 29 days ago • 63

SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation

Paper • 2610.22264 • Published 29 days ago • 32

upvoted 7 papers about 1 month ago

Hierarchical Continuous Diffusion Language Models

Paper • 2610.02193 • Published Oct 1 • 72

OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?

Paper • 2609.38079 • Published Sep 29 • 41

EpiCon: Collective Agent Learning through Co-Evolving Multimodal Memory

Paper • 2609.37923 • Published Sep 29 • 9

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

Paper • 2609.38155 • Published Sep 29 • 73

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

Paper • 2609.34309 • Published Sep 28 • 89

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

Paper • 2609.38119 • Published Sep 29 • 11

Recursive Multi-Agent Systems

Paper • 2604.25917 • Published Jul 13 • 160

upvoted 2 papers 2 months ago

Programmable World Model

Paper • 2609.10540 • Published Sep 9 • 69

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

Paper • 2609.06245 • Published Sep 5 • 12

upvoted 4 papers 3 months ago

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

Paper • 2608.20958 • Published Aug 21 • 60

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published Aug 20 • 109

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Paper • 2608.17426 • Published Aug 18 • 48

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

Paper • 2608.05000 • Published Aug 6 • 60

upvoted a paper 4 months ago

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

Paper • 2607.11886 • Published Jul 13 • 57