JunhaoZhuang

JunhaoZhuang's activity

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

upvoted 2 papers about 12 hours ago

Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction

Paper • 2610.12299 • Published 3 days ago • 47

SuperNav: An Agentic Navigation System for Any Task in Any Scene

Paper • 2610.12126 • Published 3 days ago • 66

upvoted 3 papers 3 days ago

Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness

Paper • 2610.08621 • Published 5 days ago • 87

SGF+: Decoupling Gradient Flows for Autoregressive Video Generation

Paper • 2610.10429 • Published 4 days ago • 55

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

Paper • 2610.03543 • Published 9 days ago • 93

upvoted a paper 23 days ago

Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control

Paper • 2609.17909 • Published 26 days ago • 47

upvoted 2 papers about 1 month ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published Sep 1 • 479

ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training

Paper • 2609.00188 • Published Aug 31 • 54

upvoted 2 papers about 2 months ago

EchoWM: Open and Enterable Omnimodal World Models

Paper • 2608.23189 • Published Aug 24 • 81

Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds

Paper • 2608.23383 • Published Aug 24 • 19

upvoted a paper 3 months ago

Self Gradient Forcing: Native Long Video Extrapolation

Paper • 2607.20368 • Published Jul 22 • 38

upvoted a paper 4 months ago

Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation

Paper • 2606.04527 • Published Jun 3 • 29

upvoted a paper 6 months ago

AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model

Paper • 2604.19747 • Published Apr 21 • 41

upvoted a collection 6 months ago

PowerPaint

Collection

PowerPaint is the first versatile image inpainting model that simultaneously achieves state-of-the-art results in various inpainting tasks. • 4 items • Updated Apr 15 • 1

upvoted a paper 10 months ago

LongVie 2: Multimodal Controllable Ultra-Long Video World Model

Paper • 2512.13604 • Published Dec 15, 2025 • 76

upvoted a paper 12 months ago

Video-As-Prompt: Unified Semantic Control for Video Generation

Paper • 2510.20888 • Published Oct 23, 2025 • 51

upvoted a collection 12 months ago

FlashVSR

Collection

Towards Real-Time Diffusion-Based Streaming Video Super-Resolution • 3 items • Updated Nov 5, 2025 • 4

upvoted 2 papers 12 months ago

FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution

Paper • 2510.12747 • Published Oct 14, 2025 • 40

GIR-Bench: Versatile Benchmark for Generating Images with Reasoning

Paper • 2510.11026 • Published Oct 13, 2025 • 18

upvoted a paper about 1 year ago

ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing

Paper • 2508.10881 • Published Aug 14, 2025 • 54