Xueguang Ma's picture

Xueguang Ma PRO

MrLight

·

MXueguang

AI & ML interests

None yet

Recent Activity

upvoted a collection 5 days ago

Qwen3-Embedding

liked a dataset 6 days ago

TIGER-Lab/One-Shot-CFT-Data

upvoted a collection 7 days ago

VISA: RAG with Visual Source Attribution

View all activity

Organizations

MrLight's activity

upvoted a collection 5 days ago

Qwen3-Embedding

6 items • Updated 5 days ago • 79

upvoted a collection 7 days ago

VISA: RAG with Visual Source Attribution

8 items • Updated 9 days ago • 2

upvoted a paper 13 days ago

GraphOmni: A Comprehensive and Extendable Benchmark Framework for Large Language Models on Graph-theoretic Tasks

Paper • 2504.12764 • Published Apr 17 • 41

upvoted 2 papers 14 days ago

REARANK: Reasoning Re-ranking Agent via Reinforcement Learning

Paper • 2505.20046 • Published 15 days ago • 17

Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers

Paper • 2505.21497 • Published 14 days ago • 96

upvoted a paper 18 days ago

Fixing Data That Hurts Performance: Cascading LLMs to Relabel Hard Negatives for Robust Information Retrieval

Paper • 2505.16967 • Published 19 days ago • 22

upvoted 3 papers 19 days ago

Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning

Paper • 2505.15966 • Published 20 days ago • 51

QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design

Paper • 2505.16175 • Published 20 days ago • 39

Reward Reasoning Model

Paper • 2505.14674 • Published 21 days ago • 35

upvoted a collection 21 days ago

General-Reasoner

Advancing LLMs' general reasoning capabilities • 8 items • Updated 20 days ago • 3

upvoted 3 papers 21 days ago

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation

Paper • 2505.14640 • Published 21 days ago • 14

General-Reasoner: Advancing LLM Reasoning Across All Domains

Paper • 2505.14652 • Published 21 days ago • 22

Tevatron 2.0: Unified Document Retrieval Toolkit across Scale, Language, and Modality

Paper • 2505.02466 • Published May 5 • 1

upvoted 4 papers about 2 months ago

Document Screenshot Retrievers are Vulnerable to Pixel Poisoning Attacks

Paper • 2501.16902 • Published Jan 28 • 1

DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers

Paper • 2502.18460 • Published Feb 25 • 3

ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations

Paper • 2504.00824 • Published Apr 1 • 43

VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning

Paper • 2504.08837 • Published Apr 10 • 43

upvoted a collection about 2 months ago

DRAMA

A collection of small (sub-1B) multilingual dense retrievers that generalize well across a number of tasks and languages. • 3 items • Updated Feb 26 • 7

upvoted a paper 2 months ago

MoCha: Towards Movie-Grade Talking Character Synthesis

Paper • 2503.23307 • Published Mar 30 • 135

upvoted a paper 3 months ago

Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers

Paper • 2503.11579 • Published Mar 14 • 20