dooho lee

BlueYellowGreen's activity

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

upvoted an article about 24 hours ago

view article

Article

Qwen3.5: Nobody Agrees on Attention Anymore

• 

Feb 17

•

19

upvoted a paper 1 day ago

Voxtral TTS

Paper • 2603.25551 • Published 2 days ago • 25

upvoted an article 1 day ago

view article

Article

Introducing Cohere-transcribe: state-of-the-art speech recognition

• 

2 days ago

•

17

upvoted 9 papers 4 days ago

Mixture-of-Depths Attention

Paper • 2603.15619 • Published 12 days ago • 79

Attention Residuals

Paper • 2603.15031 • Published 12 days ago • 163

Omnilingual MT: Machine Translation for 1,600 Languages

Paper • 2603.16309 • Published 11 days ago • 20

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild

Paper • 2603.17187 • Published 11 days ago • 132

Efficient Reasoning with Balanced Thinking

Paper • 2603.12372 • Published 16 days ago • 143

ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models

Paper • 2603.19466 • Published 9 days ago • 40

Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models

Paper • 2603.17051 • Published 11 days ago • 105

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning

Paper • 2603.17024 • Published 11 days ago • 104

Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

Paper • 2603.21986 • Published 5 days ago • 114

upvoted 2 papers 12 days ago

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Paper • 2603.12201 • Published 16 days ago • 52

Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

Paper • 2603.12255 • Published 16 days ago • 90

upvoted 3 papers 15 days ago

LLM2Vec-Gen: Generative Embeddings from Large Language Models

Paper • 2603.10913 • Published 17 days ago • 43

Flash-KMeans: Fast and Memory-Efficient Exact K-Means

Paper • 2603.09229 • Published 18 days ago • 80

OpenClaw-RL: Train Any Agent Simply by Talking

Paper • 2603.10165 • Published 18 days ago • 143

upvoted 2 papers 16 days ago

Fish Audio S2 Technical Report

Paper • 2603.08823 • Published 19 days ago • 36

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

Paper • 2603.09206 • Published 18 days ago • 52

upvoted an article 17 days ago

view article

Article

MARL: Runtime Middleware That Reduces LLM Hallucination Without Fine-Tuning

• 

19 days ago

•

15