T-Tech

company

AI & ML interests

Scientific research; Natural language processing: speech analytics, search engines, dialogue systems; A family of LLMs; Speech technologies; Fraud prevention technologies; Computer vision; Recommender systems; Time series analysis

Recent Activity

elephantmipt new activity 23 days ago

t-tech/flex-sae:Update tag

elephantmipt updated a model about 2 months ago

t-tech/flex-sae

elephantmipt updated a collection about 2 months ago

Kernels

View all activity

elephantmipt

in t-tech/flex-sae 23 days ago

Update tag

#1 opened 23 days ago by

danieldk

elephantmipt

updated a model about 2 months ago

t-tech/flex-sae

Updated 23 days ago • 12

elephantmipt

updated a collection about 2 months ago

Kernels

Collection

1 item • Updated Oct 1

elephantmipt

published a model about 2 months ago

t-tech/flex-sae

Updated 23 days ago • 12

kliakhnovich

updated a dataset about 2 months ago

t-tech/T-ECD

Updated Sep 26 • 18.4k • 26

kliakhnovich

published a dataset about 2 months ago

t-tech/T-ECD

Updated Sep 26 • 18.4k • 26

kefirski

authored a paper 3 months ago

Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success

Paper • 2508.04280 • Published Aug 6 • 35

kefirski

authored a paper 4 months ago

Teach Old SAEs New Domain Tricks with Boosting

Paper • 2507.12990 • Published Jul 17 • 11

elephantmipt

authored a paper 4 months ago

Teach Old SAEs New Domain Tricks with Boosting

Paper • 2507.12990 • Published Jul 17 • 11

oltsy

authored a paper 4 months ago

Translate your gibberish: black-box adversarial attack on machine translation systems

Paper • 2303.10974 • Published Mar 20, 2023

elephantmipt

authored a paper 6 months ago

Train Sparse Autoencoders Efficiently by Utilizing Features Correlation

Paper • 2505.22255 • Published May 28 • 24

kefirski

authored a paper 6 months ago

Train Sparse Autoencoders Efficiently by Utilizing Features Correlation

Paper • 2505.22255 • Published May 28 • 24

elephantmipt

authored a paper 9 months ago

You Do Not Fully Utilize Transformer's Representation Capacity

Paper • 2502.09245 • Published Feb 13 • 37

kefirski

authored a paper 9 months ago

You Do Not Fully Utilize Transformer's Representation Capacity

Paper • 2502.09245 • Published Feb 13 • 37

kefirski

authored a paper 10 months ago

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Paper • 2502.03032 • Published Feb 5 • 60

elephantmipt

authored a paper 10 months ago

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Paper • 2502.03032 • Published Feb 5 • 60

kefirski

authored a paper 10 months ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published Feb 3 • 113

ZeL1k7

authored a paper 10 months ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published Feb 3 • 113

elephantmipt

authored 2 papers about 1 year ago

Classifiers are Better Experts for Controllable Text Generation

Paper • 2205.07276 • Published May 15, 2022

Mechanistic Permutability: Match Features Across Layers

Paper • 2410.07656 • Published Oct 10, 2024 • 20

AI & ML interests

Recent Activity

Team members 17

t-tech's activity

Update tag