Jiang Lihan

lhjiang's activity

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

upvoted a paper 3 minutes ago

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models

Paper • 2605.21573 • Published 5 days ago • 50

upvoted a paper 6 days ago

Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis

Paper • 2605.18451 • Published 7 days ago • 40

upvoted 2 papers 10 days ago

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Paper • 2605.15178 • Published 11 days ago • 81

Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video

Paper • 2605.15182 • Published 11 days ago • 39

upvoted a paper 11 days ago

Qwen-Image-VAE-2.0 Technical Report

Paper • 2605.13565 • Published 12 days ago • 59

submitted a paper to Daily Papers 11 days ago

Qwen-Image-VAE-2.0 Technical Report

Paper • 2605.13565 • Published 12 days ago • 59

upvoted a paper 12 days ago

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

Paper • 2605.12500 • Published 13 days ago • 186

upvoted a paper 13 days ago

Qwen-Image-2.0 Technical Report

Paper • 2605.10730 • Published 14 days ago • 107

submitted a paper to Daily Papers 13 days ago

Qwen-Image-2.0 Technical Report

Paper • 2605.10730 • Published 14 days ago • 107

upvoted a paper 30 days ago

Context Unrolling in Omni Models

Paper • 2604.21921 • Published Apr 23 • 13

upvoted 2 papers about 2 months ago

LPM 1.0: Video-based Character Performance Model

Paper • 2604.07823 • Published Apr 9 • 80

EgoSim: Egocentric World Simulator for Embodied Interaction Generation

Paper • 2604.01001 • Published Apr 1 • 38

upvoted 3 papers 3 months ago

Utonia: Toward One Encoder for All Point Clouds

Paper • 2603.03283 • Published Mar 3 • 185

MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE

Paper • 2602.08961 • Published Feb 9 • 5

WorldCompass: Reinforcement Learning for Long-Horizon World Models

Paper • 2602.09022 • Published Feb 9 • 21

upvoted 2 papers 4 months ago

SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation

Paper • 2602.02402 • Published Feb 2 • 32

PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction

Paper • 2601.22046 • Published Jan 29 • 21

upvoted a paper 5 months ago

RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation

Paper • 2601.05241 • Published Jan 8 • 24

upvoted a paper 6 months ago

DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling

Paper • 2512.03000 • Published Dec 2, 2025 • 37

authored a paper 7 months ago

AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views

Paper • 2505.23716 • Published May 29, 2025 • 31