Thomas Wolf's picture

Thomas Wolf PRO

thomwolf

·

https://thomwolf.io

AI & ML interests

NLP and open-source :-)

Recent Activity

upvoted a paper about 6 hours ago

LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment

upvoted a paper 1 day ago

Solving Quantitative Reasoning Problems with Language Models

upvoted a collection 4 days ago

View all activity

Articles

LeMaterial: an open source initiative to accelerate materials discovery and research

FineVideo: behind the scenes

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

A failed experiment: Infini-Attention, and why we should keep trying?

Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent

Constitutional AI with Open LLMs

Open LLM Leaderboard: DROP deep dive

What's going on with the Open LLM Leaderboard?

Can foundation models label data like humans?

Organizations

thomwolf's activity

upvoted a paper about 6 hours ago

LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment

Paper • 2412.04814 • Published 12 days ago • 44

upvoted a paper 1 day ago

Solving Quantitative Reasoning Problems with Language Models

Paper • 2206.14858 • Published Jun 29, 2022 • 1

upvoted a collection 4 days ago

GUI agents

A collection of papers on GUI agents • 3 items • Updated 4 days ago • 4

upvoted a paper 4 days ago

AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials

Paper • 2412.09605 • Published 5 days ago • 24

upvoted a collection 6 days ago

🥂 FineWeb2

3 items • Updated 10 days ago • 9

upvoted a collection 13 days ago

🤖 Agents

21 items • Updated 7 days ago • 57

upvoted a paper 13 days ago

ShowUI: One Vision-Language-Action Model for GUI Visual Agent

Paper • 2411.17465 • Published 21 days ago • 76

upvoted a paper 23 days ago

Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations

Paper • 2411.00640 • Published Nov 1 • 3

upvoted an article 29 days ago

Article

The Rise of Agentic Data Generation

By

•

Jul 15

• 78

upvoted 2 papers about 1 month ago

BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays

Paper • 2410.21969 • Published Oct 29 • 9

Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent

Paper • 2411.02265 • Published Nov 4 • 24

upvoted an article about 2 months ago

Article

Breaking Barriers: The Critical Role of Art and Design in Advancing AI Capabilities

By

•

Jan 15

• 3

upvoted a collection 2 months ago

LoLCATS

Linearizing LLMs with high quality and efficiency. We linearize the full Llama 3.1 model family -- 8b, 70b, 405b -- for the first time! • 4 items • Updated Oct 14 • 14

upvoted 2 papers 2 months ago

DSBench: How Far Are Data Science Agents to Becoming Data Science Experts?

Paper • 2409.07703 • Published Sep 12 • 66

EuroLLM: Multilingual Language Models for Europe

Paper • 2409.16235 • Published Sep 24 • 25

upvoted 2 papers 3 months ago

Diffusion Policy Policy Optimization

Paper • 2409.00588 • Published Sep 1 • 19

Affordance-based Robot Manipulation with Flow Matching

Paper • 2409.01083 • Published Sep 2 • 18

upvoted an article 4 months ago

Article

The 5 Most Under-Rated Tools on Hugging Face

Aug 22

• 86

upvoted 2 collections 4 months ago

InternLM2.5

14 items • Updated Sep 14 • 70

🪐 SmolLM

A series of smol LLMs: 135M, 360M and 1.7B. We release base and Instruct models as well as the training corpus and some WebGPU demos • 12 items • Updated Aug 18 • 204