DONGRYEOLLEE

drlee1's activity

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

upvoted a paper 1 day ago

Multi-Block Diffusion Language Models

Paper • 2606.29215 • Published 3 days ago • 29

upvoted a paper 7 days ago

Improved Large Language Diffusion Models

Paper • 2606.25331 • Published 9 days ago • 43

upvoted a paper 9 days ago

Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention

Paper • 2606.20945 • Published 15 days ago • 76

upvoted a paper 15 days ago

Learning from the Self-future: On-policy Self-distillation for dLLMs

Paper • 2606.18195 • Published 17 days ago • 76

upvoted a paper 17 days ago

FastContext: Training Efficient Repository Explorer for Coding Agents

Paper • 2606.14066 • Published 21 days ago • 93

upvoted 2 papers 18 days ago

MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling

Paper • 2606.13473 • Published 22 days ago • 92

MiniMax Sparse Attention

Paper • 2606.13392 • Published 22 days ago • 148

upvoted 2 papers 22 days ago

MoBA: Mixture of Block Attention for Long-Context LLMs

Paper • 2502.13189 • Published Feb 18, 2025 • 19

SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research

Paper • 2606.09730 • Published 25 days ago • 54

upvoted 2 papers 28 days ago

Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning

Paper • 2605.30039 • Published May 29 • 20

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters

Paper • 2606.02437 • Published Jun 1 • 236

upvoted 6 papers about 1 month ago

K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts

Paper • 2606.02404 • Published Jun 1 • 59

GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment

Paper • 2605.19577 • Published May 19 • 59

Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps

Paper • 2605.16928 • Published May 16 • 97

Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion

Paper • 2605.12825 • Published May 12 • 12

Refusal in Language Models Is Mediated by a Single Direction

Paper • 2406.11717 • Published Jun 17, 2024 • 15

Long Context Pre-Training with Lighthouse Attention

Paper • 2605.06554 • Published May 7 • 31

upvoted an article about 2 months ago

view article

Article

SmolLM - blazingly fast and remarkably powerful

• 
• 
• +1

loubnabnl, anton-l, eliebak

•

Jul 16, 2024

• 460

upvoted a paper 3 months ago

HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents

Paper • 2604.07430 • Published Apr 8 • 182

upvoted a paper 4 months ago

FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use

Paper • 2603.08262 • Published Mar 9 • 42