2 10

Daniil Gavrilov

kefirski

AI & ML interests

hustle

Recent Activity

authored a paper about 13 hours ago

Train Sparse Autoencoders Efficiently by Utilizing Features Correlation

upvoted a paper 3 days ago

Train Sparse Autoencoders Efficiently by Utilizing Features Correlation

authored a paper 3 months ago

You Do Not Fully Utilize Transformer's Representation Capacity

View all activity

Organizations

kefirski's activity

authored a paper about 13 hours ago

Train Sparse Autoencoders Efficiently by Utilizing Features Correlation

Paper • 2505.22255 • Published 5 days ago • 20

upvoted a paper 3 days ago

Train Sparse Autoencoders Efficiently by Utilizing Features Correlation

Paper • 2505.22255 • Published 5 days ago • 20

authored a paper 3 months ago

You Do Not Fully Utilize Transformer's Representation Capacity

Paper • 2502.09245 • Published Feb 13 • 38

upvoted a paper 3 months ago

You Do Not Fully Utilize Transformer's Representation Capacity

Paper • 2502.09245 • Published Feb 13 • 38

authored a paper 4 months ago

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Paper • 2502.03032 • Published Feb 5 • 61

upvoted a paper 4 months ago

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Paper • 2502.03032 • Published Feb 5 • 61

commented a paper 4 months ago

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Paper • 2502.03032 • Published Feb 5 • 61 •

authored a paper 4 months ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published Feb 3 • 115

upvoted a paper 4 months ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published Feb 3 • 115

upvoted a paper 8 months ago

Mechanistic Permutability: Match Features Across Layers

Paper • 2410.07656 • Published Oct 10, 2024 • 19

commented a paper 8 months ago

Mechanistic Permutability: Match Features Across Layers

Paper • 2410.07656 • Published Oct 10, 2024 • 19 •

authored 3 papers 8 months ago

upvoted 2 papers 12 months ago

BPO: Supercharging Online Preference Learning by Adhering to the Proximity of Behavior LLM

Paper • 2406.12168 • Published Jun 18, 2024 • 7

XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning

Paper • 2406.08973 • Published Jun 13, 2024 • 90

authored 3 papers about 1 year ago

Learn Your Reference Model for Real Good Alignment

Paper • 2404.09656 • Published Apr 15, 2024 • 88

Implicit Unlikelihood Training: Improving Neural Text Generation with Reinforcement Learning

Paper • 2101.04229 • Published Jan 11, 2021

Self-Attentive Model for Headline Generation

Paper • 1901.07786 • Published Jan 23, 2019

upvoted a paper about 1 year ago

Learn Your Reference Model for Real Good Alignment

Paper • 2404.09656 • Published Apr 15, 2024 • 88