Daniil Gavrilov

kefirski's activity

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

liked a Space 17 days ago

Running

44

T-Search: an open agentic retriever

🔎

44

Open agentic retriever for hard multi-step search

authored 2 papers 21 days ago

Rank-Then-Act: Reward-Free Control from Frame-Order Progress

Paper • 2607.01897 • Published Jul 2 • 7

Qantara: Bridge-Flow Training for Multi-Paradigm JEPA Control

Paper • 2607.04978 • Published Jul 6 • 7

upvoted a paper about 1 month ago

Qantara: Bridge-Flow Training for Multi-Paradigm JEPA Control

Paper • 2607.04978 • Published Jul 6 • 7

authored 2 papers about 2 months ago

Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders

Paper • 2606.12138 • Published Jun 10 • 8

Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders

Paper • 2606.10029 • Published Jun 8 • 12

upvoted a paper 2 months ago

Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders

Paper • 2606.10029 • Published Jun 8 • 12

authored 4 papers 2 months ago

ESSA: Evolutionary Strategies for Scalable Alignment

Paper • 2507.04453 • Published Jul 6, 2025 • 5

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy

Paper • 2505.24473 • Published May 30, 2025

Steering LLM Reasoning Through Bias-Only Adaptation

Paper • 2505.18706 • Published May 24, 2025

Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors

Paper • 2509.06608 • Published Sep 8, 2025

upvoted a paper 2 months ago

Trust-Region Behavior Blending for On-Policy Distillation

Paper • 2605.31159 • Published May 29 • 69

authored a paper 2 months ago

Trust-Region Behavior Blending for On-Policy Distillation

Paper • 2605.31159 • Published May 29 • 69

authored a paper 5 months ago

Next Embedding Prediction Makes World Models Stronger

Paper • 2603.02765 • Published Mar 3 • 21

upvoted a paper 5 months ago

Next Embedding Prediction Makes World Models Stronger

Paper • 2603.02765 • Published Mar 3 • 21

liked a Space 6 months ago

Running

Featured

25

Chasing the Counting Manifold in Open LLMs

📚

25

Counting manifolds in open LLMs from behavior to SAEs.

upvoted a collection 6 months ago

Blogposts

Collection

2 items • Updated 17 days ago • 6

authored a paper 6 months ago

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

Paper • 2602.06717 • Published Feb 6 • 76

upvoted a paper 6 months ago

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

Paper • 2602.06717 • Published Feb 6 • 76

upvoted a paper 8 months ago

T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground

Paper • 2512.10430 • Published Dec 11, 2025 • 121