Nikita Sushko

chameleon-lizard's activity

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

upvoted a paper 2 days ago

A Data-Centric Framework for Addressing Phonetic and Prosodic Challenges in Russian Speech Generative Models

Paper • 2507.13563 • Published 5 days ago • 48

upvoted a paper 5 days ago

RiemannLoRA: A Unified Riemannian Framework for Ambiguity-Free LoRA Optimization

Paper • 2507.12142 • Published 7 days ago • 35

upvoted a paper 12 days ago

T-LoRA: Single Image Diffusion Model Customization Without Overfitting

Paper • 2507.05964 • Published 15 days ago • 108

upvoted an article 13 days ago

view article

Article

SmolLM3: smol, multilingual, long-context reasoner

By and 22 others •

15 days ago

• 569

upvoted a paper 19 days ago

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

Paper • 2507.02321 • Published 20 days ago • 38

upvoted a paper 22 days ago

Listener-Rewarded Thinking in VLMs for Image Preferences

Paper • 2506.22832 • Published 25 days ago • 24

upvoted a paper 23 days ago

Learning to Skip the Middle Layers of Transformers

Paper • 2506.21103 • Published 27 days ago • 16

upvoted a paper 27 days ago

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

Paper • 2506.19103 • Published 30 days ago • 43

upvoted 6 papers about 1 month ago

DreamBoothDPO: Improving Personalized Generation using Direct Preference Optimization

Paper • 2505.20975 • Published May 27 • 36

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

Paper • 2506.06395 • Published Jun 5 • 129

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

Paper • 2506.06751 • Published Jun 7 • 72

Image Reconstruction as a Tool for Feature Analysis

Paper • 2506.07803 • Published Jun 9 • 29

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

Paper • 2505.22569 • Published May 28 • 56

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

Paper • 2505.21115 • Published May 27 • 135

upvoted 4 papers about 2 months ago

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

Paper • 2506.05209 • Published Jun 5 • 43

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 • 78

upvoted 2 papers 2 months ago

Risk-Averse Reinforcement Learning with Itakura-Saito Loss

Paper • 2505.16925 • Published May 22 • 26

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

Paper • 2505.07704 • Published May 12 • 30