Xueguang Ma PRO

MrLight's activity

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

upvoted a paper 22 days ago

TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models

Paper • 2512.02014 • Published 28 days ago • 69

upvoted a paper 26 days ago

Guided Self-Evolving LLMs with Minimal Human Supervision

Paper • 2512.02472 • Published 27 days ago • 50

upvoted a paper about 1 month ago

General Agentic Memory Via Deep Research

Paper • 2511.18423 • Published Nov 23 • 160

upvoted 4 papers 3 months ago

BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions

Paper • 2510.10666 • Published Oct 12 • 27

UniVideo: Unified Understanding, Generation, and Editing for Videos

Paper • 2510.08377 • Published Oct 9 • 71

VideoScore2: Think before You Score in Generative Video Evaluation

Paper • 2509.22799 • Published Sep 26 • 25

Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning

Paper • 2509.22824 • Published Sep 26 • 20

upvoted 6 papers 4 months ago

Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

Paper • 2509.07980 • Published Sep 9 • 101

Reverse-Engineered Reasoning for Open-Ended Generation

Paper • 2509.06160 • Published Sep 7 • 149

Open Data Synthesis For Deep Research

Paper • 2509.00375 • Published Aug 30 • 70

UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

Paper • 2509.02544 • Published Sep 2 • 124

SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning

Paper • 2509.02479 • Published Sep 2 • 83

VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use

Paper • 2509.01055 • Published Sep 1 • 76

upvoted a collection 4 months ago

BrowseComp-Plus

Collection

7 items • Updated Oct 17 • 7

upvoted 4 papers 5 months ago

WideSearch: Benchmarking Agentic Broad Info-Seeking

Paper • 2508.07999 • Published Aug 11 • 110

ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability

Paper • 2508.07050 • Published Aug 9 • 117

BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

Paper • 2508.06600 • Published Aug 8 • 41

R-Zero: Self-Evolving Reasoning LLM from Zero Data

Paper • 2508.05004 • Published Aug 7 • 129

upvoted a paper 6 months ago

NeuralOS: Towards Simulating Operating Systems via Neural Generative Models

Paper • 2507.08800 • Published Jul 11 • 80

upvoted a paper 7 months ago

Reinforcement Pre-Training

Paper • 2506.08007 • Published Jun 9 • 263