etomoscow (Daniil Moskovskiy)

upvoted a paper 6 days ago

CLEAR: Character Unlearning in Textual and Visual Modalities

Paper • 2410.18057 • Published 13 days ago • 193

upvoted an article 28 days ago

Article

Abliterating Refusal and Code LLMs

By

•

Jul 26

• 2

upvoted a paper about 2 months ago

Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing

Paper • 2409.01322 • Published Sep 2 • 94

upvoted an article 2 months ago

Article

Hyperparameter Search with Transformers and Ray Tune

Nov 2, 2020

• 2

upvoted 2 papers 2 months ago

D2LLM: Decomposed and Distilled Large Language Models for Semantic Search

Paper • 2406.17262 • Published Jun 25 • 1

The Russian-focused embedders' exploration: ruMTEB benchmark and Russian embedding model design

Paper • 2408.12503 • Published Aug 22 • 21

upvoted a collection 2 months ago

RU-MTEB

Collection

18 items • Updated Jun 5 • 8

upvoted 3 papers 4 months ago

upvoted a paper 5 months ago

XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning

Paper • 2406.08973 • Published Jun 13 • 85

upvoted an article 5 months ago

Article

Uncensor any LLM with abliteration

By

•

Jun 13

• 358

upvoted a paper 6 months ago

Your Transformer is Secretly Linear

Paper • 2405.12250 • Published May 19 • 150

upvoted a paper 7 months ago

OmniFusion Technical Report

Paper • 2404.06212 • Published Apr 9 • 74

upvoted a collection 9 months ago

MoEs papers reading list

Collection

60 items • Updated about 17 hours ago • 134

Daniil Moskovskiy

AI & ML interests

Organizations

etomoscow's activity

CLEAR: Character Unlearning in Textual and Visual Modalities

Abliterating Refusal and Code LLMs

Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing

Hyperparameter Search with Transformers and Ray Tune

D2LLM: Decomposed and Distilled Large Language Models for Semantic Search

The Russian-focused embedders' exploration: ruMTEB benchmark and Russian embedding model design

RU-MTEB

Not All Language Model Features Are Linear

Preference Tuning For Toxicity Mitigation Generalizes Across Languages

Aligning Diffusion Models with Noise-Conditioned Perception

XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning

Uncensor any LLM with abliteration

Your Transformer is Secretly Linear

OmniFusion Technical Report

MoEs papers reading list