Nikita Balagansky

elephantmipt's activity

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

upvoted a paper 13 days ago

Alchemist: Turning Public Text-to-Image Data into Generative Gold

Paper • 2505.19297 • Published May 25 • 81

upvoted a paper about 1 month ago

Train Sparse Autoencoders Efficiently by Utilizing Features Correlation

Paper • 2505.22255 • Published May 28 • 23

upvoted 2 papers 4 months ago

Scale-wise Distillation of Diffusion Models

Paper • 2503.16397 • Published Mar 20 • 42

Transformers without Normalization

Paper • 2503.10622 • Published Mar 13 • 167

upvoted 2 papers 5 months ago

You Do Not Fully Utilize Transformer's Representation Capacity

Paper • 2502.09245 • Published Feb 13 • 38

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published Feb 3 • 115

upvoted a paper 9 months ago

Mechanistic Permutability: Match Features Across Layers

Paper • 2410.07656 • Published Oct 10, 2024 • 20

upvoted 4 papers about 1 year ago

XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning

Paper • 2406.08973 • Published Jun 13, 2024 • 90

Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

Paper • 2405.21060 • Published May 31, 2024 • 68

Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

Paper • 2404.02258 • Published Apr 2, 2024 • 106

Learn Your Reference Model for Real Good Alignment

Paper • 2404.09656 • Published Apr 15, 2024 • 88