Xueguang Ma's picture

Xueguang Ma PRO

MrLight

·

MXueguang

AI & ML interests

None yet

Recent Activity

updated a model about 11 hours ago

Tevatron/Qwen2.5-Omni-7B-Thinker

published a model about 11 hours ago

Tevatron/Qwen2.5-Omni-7B-Thinker

updated a collection about 12 hours ago

tevatron-v2-data

View all activity

Organizations

MrLight's activity

upvoted a paper 7 days ago

MoCha: Towards Movie-Grade Talking Character Synthesis

Paper • 2503.23307 • Published 9 days ago • 103

upvoted a paper 22 days ago

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

Paper • 2503.11579 • Published 25 days ago • 18

upvoted an article 25 days ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.21k

upvoted a collection 26 days ago

Rank-R1

Setwise rankers with reasoning ability • 6 items • Updated Mar 7 • 2

upvoted a paper about 1 month ago

ABC: Achieving Better Control of Multimodal Embeddings using VLMs

Paper • 2503.00329 • Published Mar 1 • 18

upvoted a collection about 2 months ago

tevatron-v2-data

14 items • Updated about 12 hours ago • 3

upvoted 2 papers 2 months ago

PixelWorld: Towards Perceiving Everything as Pixels

Paper • 2501.19339 • Published Jan 31 • 17

Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate

Paper • 2501.17703 • Published Jan 29 • 58

upvoted a paper 4 months ago

MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale

Paper • 2412.05237 • Published Dec 6, 2024 • 48

upvoted 2 papers 5 months ago

OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision

Paper • 2411.07199 • Published Nov 11, 2024 • 50

OmniGen: Unified Image Generation

Paper • 2409.11340 • Published Sep 17, 2024 • 115

upvoted a paper 7 months ago

Augmenting Black-box LLMs with Medical Textbooks for Clinical Question Answering

Paper • 2309.02233 • Published Sep 5, 2023 • 1

upvoted a collection 7 months ago

VisionLM

902 items • Updated about 6 hours ago • 51

upvoted 2 papers 7 months ago

WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild

Paper • 2409.03753 • Published Sep 5, 2024 • 19

Zero-Shot Listwise Document Reranking with a Large Language Model

Paper • 2305.02156 • Published May 3, 2023 • 2

upvoted a collection 8 months ago

Awesome Visual Embedding

9 items • Updated Jul 23, 2024 • 4

upvoted 3 papers 10 months ago

MantisScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation

Paper • 2406.15252 • Published Jun 21, 2024 • 16

LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs

Paper • 2406.15319 • Published Jun 21, 2024 • 65

Fine-Tuning LLaMA for Multi-Stage Text Retrieval

Paper • 2310.08319 • Published Oct 12, 2023 • 4