Nikita Sushko

chameleon-lizard's activity

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

upvoted a paper 5 days ago

Heeding the Inner Voice: Aligning ControlNet Training via Intermediate Features Feedback

Paper • 2507.02321 • Published 7 days ago • 38

upvoted a paper 8 days ago

Listener-Rewarded Thinking in VLMs for Image Preferences

Paper • 2506.22832 • Published 11 days ago • 24

upvoted a paper 9 days ago

Learning to Skip the Middle Layers of Transformers

Paper • 2506.21103 • Published 13 days ago • 16

upvoted a paper 13 days ago

Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistency Models

Paper • 2506.19103 • Published 16 days ago • 42

upvoted a paper 22 days ago

DreamBoothDPO: Improving Personalized Generation using Direct Preference Optimization

Paper • 2505.20975 • Published May 27 • 36

upvoted a paper 27 days ago

Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models

Paper • 2506.06395 • Published Jun 5 • 126

upvoted a paper 28 days ago

Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models

Paper • 2506.06751 • Published Jun 7 • 72

upvoted 2 papers 29 days ago

Image Reconstruction as a Tool for Feature Analysis

Paper • 2506.07803 • Published about 1 month ago • 29

ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Models

Paper • 2505.22569 • Published May 28 • 56

upvoted 5 papers about 1 month ago

Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA

Paper • 2505.21115 • Published May 27 • 135

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

Paper • 2506.05209 • Published Jun 5 • 42

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts

Paper • 2506.05229 • Published Jun 5 • 37

Exploring the Latent Capacity of LLMs for One-Step Text Generation

Paper • 2505.21189 • Published May 27 • 62

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

Paper • 2505.14669 • Published May 20 • 76

upvoted 2 papers about 2 months ago

Risk-Averse Reinforcement Learning with Itakura-Saito Loss

Paper • 2505.16925 • Published May 22 • 25

Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images

Paper • 2505.07704 • Published May 12 • 30

liked a dataset about 2 months ago

ZeroAgency/ru-big-russian-dataset

Viewer • Updated Apr 18 • 1.73M • 474 • 13

upvoted a paper 2 months ago

Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers

Paper • 2504.20752 • Published Apr 29 • 92

upvoted 2 papers 4 months ago

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Paper • 2503.18878 • Published Mar 24 • 119

When Less is Enough: Adaptive Token Reduction for Efficient Image Representation

Paper • 2503.16660 • Published Mar 20 • 73