Max Pavlov

undoing's activity

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

upvoted a paper 7 months ago

Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers

Paper • 2504.20752 • Published Apr 29 • 92

upvoted a collection 8 months ago

Kimina Prover Preview

Collection

State-of-the-Art Models for Formal Mathematical Reasoning • 5 items • Updated Apr 28 • 33

upvoted a paper 9 months ago

Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders

Paper • 2503.03601 • Published Mar 5 • 232

upvoted a collection over 1 year ago

🔍 Interpretability & Analysis of LMs

Collection

Outstanding research in LM interpretability and evaluation, summarized • 134 items • Updated Oct 20 • 116

upvoted 5 papers about 2 years ago

SmartPlay : A Benchmark for LLMs as Intelligent Agents

Paper • 2310.01557 • Published Oct 2, 2023 • 13

VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning

Paper • 2309.15091 • Published Sep 26, 2023 • 34

Calibrating LLM-Based Evaluator

Paper • 2309.13308 • Published Sep 23, 2023 • 12

SCREWS: A Modular Framework for Reasoning with Revisions

Paper • 2309.13075 • Published Sep 20, 2023 • 17

CodePlan: Repository-level Coding using LLMs and Planning

Paper • 2309.12499 • Published Sep 21, 2023 • 79