Alexey Malakhov

ZeL1k7's activity

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

liked a Space 2 days ago

Running

Featured

20

Chasing the Counting Manifold in Open LLMs

📚

20

Counting manifolds in open LLMs from behavior to SAEs.

authored a paper 14 days ago

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

Paper • 2602.06717 • Published 17 days ago • 71

upvoted a paper 14 days ago

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

Paper • 2602.06717 • Published 17 days ago • 71

upvoted 3 papers 2 months ago

INTELLECT-3: Technical Report

Paper • 2512.16144 • Published Dec 18, 2025 • 20

Olmo 3

Paper • 2512.13961 • Published Dec 15, 2025 • 29

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

Paper • 2512.10430 • Published Dec 11, 2025 • 115

upvoted a paper 3 months ago

ESSA: Evolutionary Strategies for Scalable Alignment

Paper • 2507.04453 • Published Jul 6, 2025 • 5

authored a paper 3 months ago

ESSA: Evolutionary Strategies for Scalable Alignment

Paper • 2507.04453 • Published Jul 6, 2025 • 5

liked a model 5 months ago

t-tech/flex-sae

Updated Oct 27, 2025 • 4 • 12

commented a paper 6 months ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published Feb 3, 2025 • 113 •

3

upvoted a paper 6 months ago

G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration

Paper • 2508.11379 • Published Aug 15, 2025 • 12

upvoted 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

upvoted a paper 9 months ago

Train Sparse Autoencoders Efficiently by Utilizing Features Correlation

Paper • 2505.22255 • Published May 28, 2025 • 24

upvoted 2 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

authored a paper about 1 year ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published Feb 3, 2025 • 113

upvoted a paper about 1 year ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published Feb 3, 2025 • 113

updated 2 models about 1 year ago

t-tech/T-lite-it-1.0

8B • Updated Dec 13, 2024 • 2.03k • 99

t-tech/T-pro-it-1.0

Updated Dec 13, 2024 • 239 • 115