Ju He

turkeyju's activity

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

upvoted a paper 2 days ago

Seed1.5-VL Technical Report

Paper • 2505.07062 • Published 5 days ago • 119

published a model 7 days ago

turkeyju/code

Updated 7 days ago

authored 3 papers 10 days ago

PartImageNet: A Large, High-Quality Dataset of Parts

Paper • 2112.00933 • Published Dec 2, 2021

A Simple Video Segmenter by Tracking Objects Along Axial Trajectories

Paper • 2311.18537 • Published Nov 30, 2023

ReVision: High-Quality, Low-Cost Video Generation with Explicit 3D Physics Modeling for Complex Motion and Interaction

Paper • 2504.21855 • Published 16 days ago • 12

upvoted a paper 15 days ago

ReVision: High-Quality, Low-Cost Video Generation with Explicit 3D Physics Modeling for Complex Motion and Interaction

Paper • 2504.21855 • Published 16 days ago • 12

upvoted 5 papers 28 days ago

WORLDMEM: Long-term Consistent World Simulation with Memory

Paper • 2504.12369 • Published 30 days ago • 33

Antidistillation Sampling

Paper • 2504.13146 • Published 29 days ago • 61

Perception Encoder: The best visual embeddings are not at the output of the network

Paper • 2504.13181 • Published 29 days ago • 34

Packing Input Frame Context in Next-Frame Prediction Models for Video Generation

Paper • 2504.12626 • Published 29 days ago • 48

REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers

Paper • 2504.10483 • Published Apr 14 • 21

upvoted a paper 29 days ago

Seedream 3.0 Technical Report

Paper • 2504.11346 • Published about 1 month ago • 59

upvoted 6 papers about 1 month ago

PRIMA.CPP: Speeding Up 70B-Scale LLM Inference on Low-Resource Everyday Home Clusters

Paper • 2504.08791 • Published Apr 7 • 131

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Paper • 2504.10479 • Published Apr 14 • 255

MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft

Paper • 2504.08388 • Published Apr 11 • 39

GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation

Paper • 2504.08736 • Published Apr 11 • 47

Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model

Paper • 2504.08685 • Published Apr 11 • 123

"Principal Components" Enable A New Language of Images

Paper • 2503.08685 • Published Mar 11 • 12

liked a dataset about 1 month ago

RyanWW/Spatial457

Updated 25 days ago • 411 • 3

upvoted a paper about 1 month ago

DDT: Decoupled Diffusion Transformer

Paper • 2504.05741 • Published Apr 8 • 73