Mikhail Salnikov

msalnikov's activity

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

upvoted a paper 20 days ago

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

Paper • 2510.11288 • Published 27 days ago • 46

upvoted a paper 23 days ago

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

Paper • 2510.04849 • Published Oct 6 • 111

upvoted a paper about 2 months ago

<think> So let's replace this phrase with insult... </think> Lessons learned from generation of toxic texts with LLMs

Paper • 2509.08358 • Published Sep 10 • 13

upvoted a paper 4 months ago

T-LoRA: Single Image Diffusion Model Customization Without Overfitting

Paper • 2507.05964 • Published Jul 8 • 118

upvoted 3 papers 5 months ago

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

Paper • 2506.06395 • Published Jun 5 • 131

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

Paper • 2506.06751 • Published Jun 7 • 71

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

Paper • 2505.21115 • Published May 27 • 139

upvoted a paper 6 months ago

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

Paper • 2505.07704 • Published May 12 • 29

upvoted 2 papers 8 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

RuCCoD: Towards Automated ICD Coding in Russian

Paper • 2502.21263 • Published Feb 28 • 132

upvoted 3 papers 9 months ago

LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers

Paper • 2502.15007 • Published Feb 20 • 174

How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?

Paper • 2502.14502 • Published Feb 20 • 91

SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators

Paper • 2502.06394 • Published Feb 10 • 89

upvoted a paper about 2 years ago

Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion

Paper • 2310.03502 • Published Oct 5, 2023 • 78