7 6

Anton Razzhigaev

razzant

https://t.me/abstractDL

razzant

AI & ML interests

Language models, multimodal models, knowledge graphs, chatbots

Recent Activity

authored a paper 23 days ago

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

upvoted a paper 23 days ago

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

authored a paper about 1 month ago

Universal Adversarial Attack on Aligned Multimodal LLMs

View all activity

Organizations

razzant's activity

authored a paper 23 days ago

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

Paper • 2503.18878 • Published 23 days ago • 114

upvoted a paper 23 days ago

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

Paper • 2503.18878 • Published 23 days ago • 114

authored 2 papers about 1 month ago

Universal Adversarial Attack on Aligned Multimodal LLMs

Paper • 2502.07987 • Published Feb 11

Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders

Paper • 2503.03601 • Published Mar 5 • 228

commented a paper about 1 month ago

Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders

Paper • 2503.03601 • Published Mar 5 • 228 •

authored a paper about 2 months ago

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

Paper • 2502.15007 • Published Feb 20 • 172

commented a paper about 2 months ago

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

Paper • 2502.15007 • Published Feb 20 • 172 •

commented a paper 3 months ago

Entropy-Guided Attention for Private LLMs

Paper • 2501.03489 • Published Jan 7 • 14 •

upvoted a paper 3 months ago

Entropy-Guided Attention for Private LLMs

Paper • 2501.03489 • Published Jan 7 • 14

upvoted a paper 9 months ago

The Llama 3 Herd of Models

Paper • 2407.21783 • Published Jul 31, 2024 • 115

upvoted a paper 10 months ago

The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing

Paper • 2406.10601 • Published Jun 15, 2024 • 70

upvoted a collection 10 months ago

🔍 Interpretability & Analysis of LMs

Collection

Outstanding research in LM interpretability and evaluation, summarized • 107 items • Updated 4 days ago • 98

upvoted a paper 11 months ago

Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian

Paper • 2405.13929 • Published May 22, 2024 • 54

authored a paper 11 months ago

Your Transformer is Secretly Linear

Paper • 2405.12250 • Published May 19, 2024 • 159

authored 4 papers about 1 year ago

OmniFusion Technical Report

Paper • 2404.06212 • Published Apr 9, 2024 • 78

The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models

Paper • 2311.05928 • Published Nov 10, 2023 • 1

Black-Box Face Recovery from Identity Features

Paper • 2007.13635 • Published Jul 27, 2020

MEKER: Memory Efficient Knowledge Embedding Representation for Link Prediction and Question Answering

Paper • 2204.10629 • Published Apr 22, 2022

authored a paper over 1 year ago

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

Paper • 2310.03502 • Published Oct 5, 2023 • 79