Alexey Dontsov

therem's activity

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

upvoted 2 papers 14 days ago

Learn Your Reference Model for Real Good Alignment

Paper • 2404.09656 • Published Apr 15, 2024 • 87

ProcessBench: Identifying Process Errors in Mathematical Reasoning

Paper • 2412.06559 • Published Dec 9, 2024 • 83

upvoted a paper 21 days ago

Aether: Geometric-Aware Unified World Modeling

Paper • 2503.18945 • Published 22 days ago • 27

authored a paper 21 days ago

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Paper • 2503.18878 • Published 22 days ago • 113

upvoted a paper 21 days ago

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Paper • 2503.18878 • Published 22 days ago • 113

commented a paper 21 days ago

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Paper • 2503.18878 • Published 22 days ago • 113 •

2

upvoted a paper 25 days ago

One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation

Paper • 2503.13358 • Published 29 days ago • 95

updated a dataset 27 days ago

therem/CLEAR

Viewer • Updated 27 days ago • 51.4k • 1.81k • 8

liked a dataset 28 days ago

open-r1/codeforces-cots

Viewer • Updated 18 days ago • 254k • 12.3k • 140

upvoted a paper about 1 month ago

RuCCoD: Towards Automated ICD Coding in Russian

Paper • 2502.21263 • Published Feb 28 • 131

liked a dataset about 2 months ago

EleutherAI/hendrycks_math

Viewer • Updated Jan 12 • 12.5k • 36.9k • 34

upvoted 3 papers about 2 months ago

LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers

Paper • 2502.15007 • Published Feb 20 • 172

How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?

Paper • 2502.14502 • Published Feb 20 • 89

Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity

Paper • 2502.13063 • Published Feb 18 • 69

upvoted a collection 2 months ago

🧠 Reasoning datasets

Collection

Datasets with reasoning traces for math and code released by the community • 21 items • Updated 38 minutes ago • 126

upvoted 3 papers 2 months ago

SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators

Paper • 2502.06394 • Published Feb 10 • 90

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Paper • 2502.03032 • Published Feb 5 • 60

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published Feb 3 • 115

upvoted a paper 3 months ago

SRMT: Shared Memory for Multi-agent Lifelong Pathfinding

Paper • 2501.13200 • Published Jan 22 • 68

upvoted a collection 3 months ago

Purging corrupted capabilities across language models

Collection

Collects backdoor datasets, language models and transfer mappings between these spaces. • 6 items • Updated Dec 17, 2024 • 3