2 9

Daniil Gavrilov

kefirski

AI & ML interests

hustle

Recent Activity

authored a paper 5 days ago

You Do Not Fully Utilize Transformer's Representation Capacity

upvoted a paper 5 days ago

You Do Not Fully Utilize Transformer's Representation Capacity

authored a paper 17 days ago

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

View all activity

Organizations

kefirski's activity

authored a paper 5 days ago

You Do Not Fully Utilize Transformer's Representation Capacity

Paper • 2502.09245 • Published 11 days ago • 30

upvoted a paper 5 days ago

You Do Not Fully Utilize Transformer's Representation Capacity

Paper • 2502.09245 • Published 11 days ago • 30

authored a paper 17 days ago

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Paper • 2502.03032 • Published 19 days ago • 55

upvoted a paper 17 days ago

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Paper • 2502.03032 • Published 19 days ago • 55

commented a paper 17 days ago

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Paper • 2502.03032 • Published 19 days ago • 55 •

authored a paper 20 days ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published 21 days ago • 111

upvoted a paper 20 days ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published 21 days ago • 111

upvoted a paper 4 months ago

Mechanistic Permutability: Match Features Across Layers

Paper • 2410.07656 • Published Oct 10, 2024 • 18

commented a paper 4 months ago

Mechanistic Permutability: Match Features Across Layers

Paper • 2410.07656 • Published Oct 10, 2024 • 18 •

authored 3 papers 4 months ago

upvoted 2 papers 8 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 • 87

authored 3 papers 10 months ago

Learn Your Reference Model for Real Good Alignment

Paper • 2404.09656 • Published Apr 15, 2024 • 84

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 10 months ago

Learn Your Reference Model for Real Good Alignment

Paper • 2404.09656 • Published Apr 15, 2024 • 84

upvoted a paper 12 months ago

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Paper • 2403.03507 • Published Mar 6, 2024 • 185

authored a paper about 1 year ago

Linear Transformers with Learnable Kernel Functions are Better In-Context Models

Paper • 2402.10644 • Published Feb 16, 2024 • 80