Gatozu35 (Full Name)

upvoted a collection 21 days ago

Direct Preference Heads (Preprint)

This collection contains the pre-trained, fine-tuned and aligned models for the Direct Preference Heads paper. • 3 items • Updated 1 day ago • 1

upvoted 2 papers about 1 month ago

FlashSpeech: Efficient Zero-Shot Speech Synthesis

Paper • 2404.14700 • Published Apr 23 • 28

TransformerFAM: Feedback attention is working memory

Paper • 2404.09173 • Published Apr 14 • 42

upvoted 2 collections about 2 months ago

Pile-T5

Collection

T5 trained on the Pile with Llama Tokenizer • 4 items • Updated Apr 15 • 16

HGRN2

Collection

HGRN2: Gated Linear RNNs with State Expansion • 1 item • Updated Apr 12 • 1

upvoted a paper about 2 months ago

Seamless: Multilingual Expressive and Streaming Speech Translation

Paper • 2312.05187 • Published Dec 8, 2023 • 7

upvoted a paper 3 months ago

Learning and Leveraging World Models in Visual Representation Learning

Paper • 2403.00504 • Published Mar 1 • 25

upvoted 2 papers 4 months ago

In-Context Principle Learning from Mistakes

Paper • 2402.05403 • Published Feb 8 • 12

The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry

Paper • 2402.04347 • Published Feb 6 • 13

upvoted a collection 4 months ago

LAION-Audio-630k

Collection

Large-scale Audio dataset • 6 items • Updated Jan 23 • 3

upvoted a collection 5 months ago

TransNormerLLM

Collection

TransNormerLLM: A Faster and Better Large Language Model with Improved TransNormer • 10 items • Updated Apr 11 • 3

upvoted a collection 8 months ago

Tiny Series

Collection

Tiny datasets that empower the foundation of Small Language Model! • 11 items • Updated Jan 26 • 31

upvoted a paper 8 months ago

A Large-scale Dataset for Audio-Language Representation Learning

Paper • 2309.11500 • Published Sep 20, 2023 • 9

upvoted a paper 9 months ago

AudioSR: Versatile Audio Super-resolution at Scale

Paper • 2309.07314 • Published Sep 13, 2023 • 23

upvoted 3 papers 11 months ago

upvoted 9 papers 12 months ago

Seeing the World through Your Eyes

Paper • 2306.09348 • Published Jun 15, 2023 • 30

AniFaceDrawing: Anime Portrait Exploration during Your Sketching

Paper • 2306.07476 • Published Jun 13, 2023 • 16

Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation

Paper • 2306.07954 • Published Jun 13, 2023 • 111

One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning

Paper • 2306.07967 • Published Jun 13, 2023 • 23

BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping

Paper • 2306.05544 • Published Jun 8, 2023 • 9

Face0: Instantaneously Conditioning a Text-to-Image Model on a Face

Paper • 2306.06638 • Published Jun 11, 2023 • 16

Benchmarking Neural Network Training Algorithms

Paper • 2306.07179 • Published Jun 12, 2023 • 22

FasterViT: Fast Vision Transformers with Hierarchical Attention

Paper • 2306.06189 • Published Jun 9, 2023 • 29

Retrieval-Enhanced Contrastive Vision-Text Models

Paper • 2306.07196 • Published Jun 12, 2023 • 7

Full Name

AI & ML interests

Organizations

Gatozu35's activity

Direct Preference Heads (Preprint)

FlashSpeech: Efficient Zero-Shot Speech Synthesis

TransformerFAM: Feedback attention is working memory

Pile-T5

HGRN2

Seamless: Multilingual Expressive and Streaming Speech Translation

Learning and Leveraging World Models in Visual Representation Learning

In-Context Principle Learning from Mistakes

The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry

LAION-Audio-630k

TransNormerLLM

Tiny Series

A Large-scale Dataset for Audio-Language Representation Learning

AudioSR: Versatile Audio Super-resolution at Scale

MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers

SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit

Seeing the World through Your Eyes

AniFaceDrawing: Anime Portrait Exploration during Your Sketching

Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation

One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning

BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping

Face0: Instantaneously Conditioning a Text-to-Image Model on a Face

Benchmarking Neural Network Training Algorithms

FasterViT: Fast Vision Transformers with Hierarchical Attention

Retrieval-Enhanced Contrastive Vision-Text Models