Minghui Jia

Maxwell-Jia's activity

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

upvoted a collection 12 days ago

Qwen3-VL

Collection

37 items • Updated about 11 hours ago • 351

upvoted 2 papers 21 days ago

Training-Free Group Relative Policy Optimization

Paper • 2510.08191 • Published 24 days ago • 43

Agent Learning via Early Experience

Paper • 2510.08558 • Published 23 days ago • 255

upvoted a paper 23 days ago

Efficient Medical VIE via Reinforcement Learning

Paper • 2506.13363 • Published Jun 16 • 31

upvoted a paper 3 months ago

Group Sequence Policy Optimization

Paper • 2507.18071 • Published Jul 24 • 306

upvoted 3 papers 4 months ago

VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning

Paper • 2507.13348 • Published Jul 17 • 75

A Survey of Context Engineering for Large Language Models

Paper • 2507.13334 • Published Jul 17 • 257

GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Paper • 2507.01006 • Published Jul 1 • 237

upvoted 2 papers 5 months ago

Reinforcement Pre-Training

Paper • 2506.08007 • Published Jun 9 • 262

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published Jun 2 • 185

upvoted a paper 6 months ago

Seed1.5-VL Technical Report

Paper • 2505.07062 • Published May 11 • 151

upvoted a paper 7 months ago

Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?

Paper • 2504.00509 • Published Apr 1 • 22

upvoted an article 7 months ago

view article

Article

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

Mar 12

• 468

upvoted 4 papers 8 months ago

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Paper • 2503.16419 • Published Mar 20 • 75

Chain of Draft: Thinking Faster by Writing Less

Paper • 2502.18600 • Published Feb 25 • 49

LightThinker: Thinking Step-by-Step Compression

Paper • 2502.15589 • Published Feb 21 • 31

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Paper • 2502.14739 • Published Feb 20 • 104

upvoted 3 papers 9 months ago

FoNE: Precise Single-Token Number Embeddings via Fourier Features

Paper • 2502.09741 • Published Feb 13 • 15

Large Language Diffusion Models

Paper • 2502.09992 • Published Feb 14 • 122

Humanity's Last Exam

Paper • 2501.14249 • Published Jan 24 • 76