7 30 12

Nikita Sushko

chameleon-lizard

http://chameleon-lizard.ru:81

chameleon-lizard

AI & ML interests

NLP, Multilingual Models, Multiagent Systems

Recent Activity

new activity 6 days ago

featherless-ai/Qwerky-QwQ-32B:Is the source code for this conversion available?

upvoted a paper 14 days ago

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

upvoted a paper 15 days ago

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

View all activity

Organizations

chameleon-lizard's activity

New activity in featherless-ai/Qwerky-QwQ-32B 6 days ago

Is the source code for this conversion available?

#1 opened 6 days ago by

chameleon-lizard

upvoted a paper 14 days ago

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

Paper • 2503.18878 • Published 14 days ago • 112

upvoted a paper 15 days ago

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

Paper • 2503.16660 • Published 18 days ago • 71

upvoted a paper 18 days ago

One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation

Paper • 2503.13358 • Published 21 days ago • 93

upvoted a paper 19 days ago

RWKV-7 "Goose" with Expressive Dynamic State Evolution

Paper • 2503.14456 • Published 20 days ago • 136

upvoted 2 papers 28 days ago

EuroBERT: Scaling Multilingual Encoders for European Languages

Paper • 2503.05500 • Published Mar 7 • 76

RuCCoD: Towards Automated ICD Coding in Russian

Paper • 2502.21263 • Published Feb 28 • 131

upvoted a collection about 1 month ago

SynthDetoxM

Collection

Data and models from NAACL 2025 paper "SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators" by Moskovskiy et al. • 4 items • Updated Mar 6 • 2

upvoted a paper about 1 month ago

When an LLM is apprehensive about its answers -- and when its uncertainty is justified

Paper • 2503.01688 • Published Mar 3 • 20

updated a dataset about 1 month ago

chameleon-lizard/judge_correlation

Viewer • Updated Mar 3 • 3.2k • 74

published a dataset about 1 month ago

chameleon-lizard/judge_correlation

Viewer • Updated Mar 3 • 3.2k • 74

liked a dataset about 1 month ago

OpenLeecher/lmsys_chat_1m_clean

Viewer • Updated Dec 31, 2024 • 273k • 927 • 75

upvoted a paper about 1 month ago

GHOST 2.0: generative high-fidelity one shot transfer of heads

Paper • 2502.18417 • Published Feb 25 • 66

updated a dataset about 1 month ago

chameleon-lizard/DTF-comments-DPO

Viewer • Updated Feb 24 • 2.39k • 62

upvoted a paper about 1 month ago

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

Paper • 2502.15007 • Published Feb 20 • 171

upvoted a paper about 2 months ago

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

Paper • 2502.14502 • Published Feb 20 • 89

published a dataset about 2 months ago

chameleon-lizard/DTF-comments-DPO

Viewer • Updated Feb 24 • 2.39k • 62

upvoted 2 papers about 2 months ago

Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity

Paper • 2502.13063 • Published Feb 18 • 69

LM2: Large Memory Models

Paper • 2502.06049 • Published Feb 9 • 30

authored a paper about 2 months ago

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

Paper • 2502.06394 • Published Feb 10 • 90