Andron00e (Andrei Semenov)

upvoted a paper 11 days ago

Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders

Paper • 2410.22366 • Published 15 days ago • 73

upvoted a paper 2 months ago

Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization

Paper • 2409.00492 • Published Aug 31 • 11

upvoted a collection 4 months ago

MatMulfree LM

Collection

Pre-trined models for Matmulfree LM. • 4 items • Updated Jun 10 • 25

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 • 86

upvoted an article 5 months ago

Article

🧨 Diffusers welcomes Stable Diffusion 3

Jun 12

• 92

upvoted an article 7 months ago

Article

Welcome Llama 3 - Meta's new open LLM

Apr 18

• 278

upvoted 2 collections 7 months ago

Meta Llama 3

Collection

This collection hosts the transformers and original repos of the Meta Llama 3 and Llama Guard 2 releases • 5 items • Updated Sep 25 • 682

Papers-to-read

Collection

9 items • Updated Apr 25 • 2

upvoted 3 papers 7 months ago

upvoted 5 papers 8 months ago

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Paper • 2312.00752 • Published Dec 1, 2023 • 138

Synth^2: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings

Paper • 2403.07750 • Published Mar 12 • 21

Stealing Part of a Production Language Model

Paper • 2403.06634 • Published Mar 11 • 90

DeepSeek-VL: Towards Real-World Vision-Language Understanding

Paper • 2403.05525 • Published Mar 8 • 39

VisionLLaMA: A Unified LLaMA Interface for Vision Tasks

Paper • 2403.00522 • Published Mar 1 • 44

upvoted a paper 9 months ago

FiT: Flexible Vision Transformer for Diffusion Model

Paper • 2402.12376 • Published Feb 19 • 48

Andrei Semenov

AI & ML interests

Organizations

Andron00e's activity

Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders

Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization

MatMulfree LM

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

🧨 Diffusers welcomes Stable Diffusion 3

Welcome Llama 3 - Meta's new open LLM

Meta Llama 3

Papers-to-read

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

YaART: Yet Another ART Rendering Technology

Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Synth^2: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings

Stealing Part of a Production Language Model

DeepSeek-VL: Towards Real-World Vision-Language Understanding

VisionLLaMA: A Unified LLaMA Interface for Vision Tasks

FiT: Flexible Vision Transformer for Diffusion Model