2 40 11

Ju He

turkeyju

https://tacju.github.io/

TACJu

AI & ML interests

None yet

Recent Activity

published a model 1 day ago

turkeyju/code

authored a paper 4 days ago

PartImageNet: A Large, High-Quality Dataset of Parts

authored a paper 4 days ago

A Simple Video Segmenter by Tracking Objects Along Axial Trajectories

View all activity

Organizations

turkeyju's activity

published a model 1 day ago

turkeyju/code

Updated 1 day ago

authored 3 papers 4 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 9 days ago • 12

upvoted a paper 8 days ago

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

Paper • 2504.21855 • Published 9 days ago • 12

upvoted 4 papers 21 days ago

WORLDMEM: Long-term Consistent World Simulation with Memory

Paper • 2504.12369 • Published 23 days ago • 32

Antidistillation Sampling

Paper • 2504.13146 • Published 22 days ago • 60

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

Paper • 2504.13181 • Published 22 days ago • 34

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

Paper • 2504.12626 • Published 23 days ago • 48

upvoted a paper 22 days ago

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

Paper • 2504.10483 • Published 25 days ago • 21

upvoted a paper 23 days ago

Seedream 3.0 Technical Report

Paper • 2504.11346 • Published 25 days ago • 55

upvoted 2 papers 24 days ago

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

Paper • 2504.08791 • Published Apr 7 • 130

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

Paper • 2504.10479 • Published 25 days ago • 255

upvoted 3 papers 25 days ago

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

Paper • 2504.08388 • Published 29 days ago • 39

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

Paper • 2504.08736 • Published 28 days ago • 47

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

Paper • 2504.08685 • Published 29 days ago • 123

upvoted a paper 28 days ago

"Principal Components" Enable A New Language of Images

Paper • 2503.08685 • Published Mar 11 • 12

liked a dataset 29 days ago

RyanWW/Spatial457

Updated 19 days ago • 248 • 3

upvoted a paper 29 days ago

DDT: Decoupled Diffusion Transformer

Paper • 2504.05741 • Published Apr 8 • 73

upvoted a paper about 1 month ago

Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought

Paper • 2504.05599 • Published Apr 8 • 81