Vasily Konovalov

Vasily's activity

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

authored a paper 29 days ago

Multimodal Evaluation of Russian-language Architectures

Paper • 2511.15552 • Published Nov 19 • 78

upvoted a paper 29 days ago

Multimodal Evaluation of Russian-language Architectures

Paper • 2511.15552 • Published Nov 19 • 78

upvoted a paper about 1 month ago

GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms

Paper • 2511.17592 • Published Nov 17 • 118

upvoted a paper 2 months ago

Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs

Paper • 2510.11288 • Published Oct 13 • 48

authored a paper 2 months ago

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

Paper • 2510.04849 • Published Oct 6 • 114

upvoted 3 papers 2 months ago

The Rogue Scalpel: Activation Steering Compromises LLM Safety

Paper • 2509.22067 • Published Sep 26 • 27

OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features

Paper • 2509.22033 • Published Sep 26 • 18

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

Paper • 2510.04849 • Published Oct 6 • 114

commented a paper 2 months ago

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

Paper • 2510.04849 • Published Oct 6 • 114 •

7

upvoted 3 papers 6 months ago

T-LoRA: Single Image Diffusion Model Customization Without Overfitting

Paper • 2507.05964 • Published Jul 8 • 119

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

Paper • 2506.19103 • Published Jun 23 • 42

DreamBoothDPO: Improving Personalized Generation using Direct Preference Optimization

Paper • 2505.20975 • Published May 27 • 36

upvoted 4 papers 7 months ago

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

Paper • 2506.06751 • Published Jun 7 • 71

Image Reconstruction as a Tool for Feature Analysis

Paper • 2506.07803 • Published Jun 9 • 29

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts

Paper • 2506.05229 • Published Jun 5 • 38

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

Paper • 2505.22569 • Published May 28 • 56

authored a paper 7 months ago

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

Paper • 2505.21115 • Published May 27 • 140

upvoted 2 papers 7 months ago

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

Paper • 2505.21115 • Published May 27 • 140

AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment

Paper • 2506.04089 • Published Jun 4 • 47

authored a paper 7 months ago

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

Paper • 2505.07704 • Published May 12 • 29