LAN YUSHI PRO

yslan's activity

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

upvoted a paper about 2 months ago

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

Paper • 2608.05000 • Published Aug 6 • 64

upvoted a paper 3 months ago

PhysiFormer: Learning to Simulate Mechanics in World Space

Paper • 2606.27364 • Published Jun 25 • 12

upvoted an article 4 months ago

view article

Article

Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action

• 

nvidia

•

Jun 1

• 90

upvoted an article 5 months ago

view article

Article

NEO-unify: Building Native Multimodal Unified Models End to End

• 

sensenova

•

Mar 5

• 182

upvoted a paper 10 months ago

Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation

Paper • 2512.03040 • Published Dec 2, 2025 • 7

upvoted 3 papers about 1 year ago

FastMesh:Efficient Artistic Mesh Generation via Component Decoupling

Paper • 2508.19188 • Published Aug 26, 2025 • 17

STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer

Paper • 2508.10893 • Published Aug 14, 2025 • 31

Reconstructing 4D Spatial Intelligence: A Survey

Paper • 2507.21045 • Published Jul 28, 2025 • 38

upvoted a collection about 1 year ago

V-JEPA 2

Collection

A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann • 8 items • Updated Jun 13, 2025 • 231

upvoted 3 papers over 1 year ago

Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning

Paper • 2506.13654 • Published Jun 16, 2025 • 44

WORLDMEM: Long-term Consistent World Simulation with Memory

Paper • 2504.12369 • Published Apr 16, 2025 • 36

EgoLife: Towards Egocentric Life Assistant

Paper • 2503.03803 • Published Mar 5, 2025 • 48

upvoted 3 papers almost 2 years ago

ObjCtrl-2.5D: Training-free Object Control with Camera Poses

Paper • 2412.07721 • Published Dec 10, 2024 • 9

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE

Paper • 2411.16856 • Published Nov 25, 2024 • 13

GaussianAnything: Interactive Point Cloud Latent Diffusion for 3D Generation

Paper • 2411.08033 • Published Nov 12, 2024 • 25

upvoted a paper about 2 years ago

OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding

Paper • 2406.19389 • Published Jun 27, 2024 • 54

upvoted 2 papers over 2 years ago

Self-Supervised Geometry-Aware Encoder for Style-Based 3D GAN Inversion

Paper • 2212.07409 • Published Dec 14, 2022 • 1

LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation

Paper • 2403.12019 • Published Mar 18, 2024 • 11