Daniil Gavrilov

kefirski's activity

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

authored a paper 12 days ago

F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare

Paper • 2602.06717 • Published 15 days ago • 71

authored 2 papers 7 months ago

Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success

Paper • 2508.04280 • Published Aug 6, 2025 • 35

Teach Old SAEs New Domain Tricks with Boosting

Paper • 2507.12990 • Published Jul 17, 2025 • 12

authored a paper 9 months ago

Train Sparse Autoencoders Efficiently by Utilizing Features Correlation

Paper • 2505.22255 • Published May 28, 2025 • 24

authored 3 papers about 1 year ago

You Do Not Fully Utilize Transformer's Representation Capacity

Paper • 2502.09245 • Published Feb 13, 2025 • 37

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Paper • 2502.03032 • Published Feb 5, 2025 • 60

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published Feb 3, 2025 • 113

authored 3 papers over 1 year ago

Mechanistic Permutability: Match Features Across Layers

Paper • 2410.07656 • Published Oct 10, 2024 • 20

Classifiers are Better Experts for Controllable Text Generation

Paper • 2205.07276 • Published May 15, 2022

PALBERT: Teaching ALBERT to Ponder

Paper • 2204.03276 • Published Apr 7, 2022

authored 3 papers almost 2 years ago

Learn Your Reference Model for Real Good Alignment

Paper • 2404.09656 • Published Apr 15, 2024 • 90

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

authored a paper about 2 years ago

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

Paper • 2402.10644 • Published Feb 16, 2024 • 81