Minghui Jia

Maxwell-Jia's activity

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

upvoted a paper 3 days ago

LLM-in-Sandbox Elicits General Agentic Intelligence

Paper • 2601.16206 • Published 3 days ago • 69

upvoted a paper 13 days ago

Spec-o3: A Tool-Augmented Vision-Language Agent for Rare Celestial Object Candidate Vetting via Automated Spectral Inspection

Paper • 2601.06498 • Published 16 days ago • 1

upvoted a paper 3 months ago

In-the-Flow Agentic System Optimization for Effective Planning and Tool Use

Paper • 2510.05592 • Published Oct 7, 2025 • 107

upvoted a collection 3 months ago

Qwen3-VL

Collection

37 items • Updated 26 days ago • 604

upvoted 3 papers 4 months ago

Training-Free Group Relative Policy Optimization

Paper • 2510.08191 • Published Oct 9, 2025 • 44

Agent Learning via Early Experience

Paper • 2510.08558 • Published Oct 9, 2025 • 272

Efficient Medical VIE via Reinforcement Learning

Paper • 2506.13363 • Published Jun 16, 2025 • 31

upvoted 3 papers 6 months ago

Group Sequence Policy Optimization

Paper • 2507.18071 • Published Jul 24, 2025 • 316

VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning

Paper • 2507.13348 • Published Jul 17, 2025 • 79

A Survey of Context Engineering for Large Language Models

Paper • 2507.13334 • Published Jul 17, 2025 • 260

upvoted a paper 7 months ago

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

Paper • 2507.01006 • Published Jul 1, 2025 • 250

upvoted 2 papers 8 months ago

Reinforcement Pre-Training

Paper • 2506.08007 • Published Jun 9, 2025 • 263

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

Paper • 2506.01939 • Published Jun 2, 2025 • 187

upvoted a paper 9 months ago

Seed1.5-VL Technical Report

Paper • 2505.07062 • Published May 11, 2025 • 154

upvoted a paper 10 months ago

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

Paper • 2504.00509 • Published Apr 1, 2025 • 23

upvoted an article 10 months ago

view article

Article

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

• 
• 
• +2

Mar 12, 2025

•

483

upvoted a paper 10 months ago

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

Paper • 2503.16419 • Published Mar 20, 2025 • 77

upvoted 3 papers 11 months ago

Chain of Draft: Thinking Faster by Writing Less

Paper • 2502.18600 • Published Feb 25, 2025 • 50

LightThinker: Thinking Step-by-Step Compression

Paper • 2502.15589 • Published Feb 21, 2025 • 31

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Paper • 2502.14739 • Published Feb 20, 2025 • 107