Junhan ZHU

Alrightlone's activity

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

upvoted a paper 2 days ago

EarlyTom: Early Token Compression Completes Fast Video Understanding

Paper • 2605.30010 • Published 4 days ago • 27

upvoted a paper 9 days ago

RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution

Paper • 2605.21195 • Published 12 days ago • 18

upvoted a paper 18 days ago

PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks

Paper • 2605.10977 • Published 23 days ago • 10

upvoted 4 papers about 1 month ago

Seedance 2.0: Advancing Video Generation for World Complexity

Paper • 2604.14148 • Published Apr 15 • 163

Qwen3.5-Omni Technical Report

Paper • 2604.15804 • Published Apr 17 • 59

Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips

Paper • 2502.07408 • Published Apr 16 • 59

Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play

Paper • 2509.25541 • Published Sep 29, 2025 • 142

upvoted 3 collections about 2 months ago

OBS-Diff

Collection

2 items • Updated Apr 14 • 1

Ouro-2.6B-quantization

Collection

8 items • Updated Apr 15 • 1

Ouro-1.4B-Quantization

Collection

8 items • Updated Apr 14 • 1

upvoted 7 papers about 2 months ago

Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

Paper • 2604.08995 • Published Apr 10 • 51

WildDet3D: Scaling Promptable 3D Detection in the Wild

Paper • 2604.08626 • Published Apr 9 • 247

DMax: Aggressive Parallel Decoding for dLLMs

Paper • 2604.08302 • Published Apr 9 • 53

INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling

Paper • 2604.07209 • Published Apr 8 • 38

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published Apr 6 • 114

Token Warping Helps MLLMs Look from Nearby Viewpoints

Paper • 2604.02870 • Published Apr 3 • 34

HippoCamp: Benchmarking Contextual Agents on Personal Computers

Paper • 2604.01221 • Published Apr 1 • 30

upvoted an article 2 months ago

view article

Article

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

• 

sensenova

•

Mar 5

• 163

upvoted 2 papers 2 months ago

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Paper • 2603.19312 • Published Mar 13 • 46

LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs

Paper • 2603.19217 • Published Mar 19 • 28