Daniil Laptev

dlaptev's activity

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

authored 3 papers 1 day ago

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

Paper • 2509.06608 • Published Sep 8, 2025

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

Paper • 2505.24473 • Published May 30, 2025

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

Paper • 2606.12138 • Published 8 days ago • 6

upvoted a paper 1 day ago

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

Paper • 2606.12138 • Published 8 days ago • 6

upvoted a paper 8 days ago

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

Paper • 2606.10029 • Published 9 days ago • 12

upvoted a paper 16 days ago

Trust-Region Behavior Blending for On-Policy Distillation

Paper • 2605.31159 • Published 20 days ago • 66

upvoted a paper 4 months ago

Next Embedding Prediction Makes World Models Stronger

Paper • 2603.02765 • Published Mar 3 • 21

liked a Space 4 months ago

Running

Featured

25

Chasing the Counting Manifold in Open LLMs

📚

25

Counting manifolds in open LLMs from behavior to SAEs.

upvoted 2 papers 4 months ago

ESSA: Evolutionary Strategies for Scalable Alignment

Paper • 2507.04453 • Published Jul 6, 2025 • 5

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

Paper • 2602.06717 • Published Feb 6 • 75

upvoted a paper 6 months ago

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

Paper • 2512.10430 • Published Dec 11, 2025 • 119

upvoted a paper 7 months ago

Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story

Paper • 2511.15210 • Published Nov 19, 2025 • 91

liked a model 9 months ago

t-tech/flex-sae

Updated Oct 27, 2025 • 2 • 12

upvoted a paper 10 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

authored a paper 11 months ago

Teach Old SAEs New Domain Tricks with Boosting

Paper • 2507.12990 • Published Jul 17, 2025 • 12

upvoted a paper 11 months ago

Teach Old SAEs New Domain Tricks with Boosting

Paper • 2507.12990 • Published Jul 17, 2025 • 12

authored a paper about 1 year ago

Train Sparse Autoencoders Efficiently by Utilizing Features Correlation

Paper • 2505.22255 • Published May 28, 2025 • 24

upvoted a paper about 1 year ago

Train Sparse Autoencoders Efficiently by Utilizing Features Correlation

Paper • 2505.22255 • Published May 28, 2025 • 24

commented a paper about 1 year ago

Train Sparse Autoencoders Efficiently by Utilizing Features Correlation

Paper • 2505.22255 • Published May 28, 2025 • 24 •

2

upvoted a collection about 1 year ago

Reasoning, Thinking, RL and Test-Time Scaling

Collection

261 items • Updated Nov 22, 2025 • 15