Ju He's picture

Ju He

turkeyju

·

https://tacju.github.io/

TACJu

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

WORLDMEM: Long-term Consistent World Simulation with Memory

upvoted a paper 2 days ago

Antidistillation Sampling

upvoted a paper 2 days ago

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

View all activity

Organizations

turkeyju's activity

upvoted 4 papers 2 days ago

WORLDMEM: Long-term Consistent World Simulation with Memory

Paper • 2504.12369 • Published 4 days ago • 28

Antidistillation Sampling

Paper • 2504.13146 • Published 3 days ago • 55

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

Paper • 2504.13181 • Published 3 days ago • 20

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

Paper • 2504.12626 • Published 3 days ago • 38

upvoted a paper 3 days ago

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

Paper • 2504.10483 • Published 6 days ago • 19

upvoted a paper 4 days ago

Seedream 3.0 Technical Report

Paper • 2504.11346 • Published 5 days ago • 37

upvoted 2 papers 5 days ago

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

Paper • 2504.08791 • Published 13 days ago • 114

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

Paper • 2504.10479 • Published 6 days ago • 226

upvoted 3 papers 6 days ago

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

Paper • 2504.08388 • Published 9 days ago • 38

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

Paper • 2504.08736 • Published 9 days ago • 46

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

Paper • 2504.08685 • Published 9 days ago • 118

upvoted a paper 9 days ago

"Principal Components" Enable A New Language of Images

Paper • 2503.08685 • Published Mar 11 • 12

upvoted a paper 10 days ago

DDT: Decoupled Diffusion Transformer

Paper • 2504.05741 • Published 12 days ago • 71

upvoted 4 papers 11 days ago

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

Paper • 2504.05599 • Published 13 days ago • 79

Less-to-More Generalization: Unlocking More Controllability by In-Context Generation

Paper • 2504.02160 • Published 18 days ago • 33

OmniSVG: A Unified Scalable Vector Graphics Generation Model

Paper • 2504.06263 • Published 12 days ago • 144

Hogwild! Inference: Parallel LLM Generation via Concurrent Attention

Paper • 2504.06261 • Published 12 days ago • 101

upvoted 2 papers 12 days ago

Rethinking Reflection in Pre-Training

Paper • 2504.04022 • Published 16 days ago • 75

One-Minute Video Generation with Test-Time Training

Paper • 2504.05298 • Published 13 days ago • 94

upvoted a paper 19 days ago

What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models

Paper • 2503.24235 • Published 20 days ago • 52