Diffusion Models Beat GANs on Image Classification paper page: https://
huggingface.co/papers/2307.08
702
… While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model which uses a
@_akhaliq
-
Diffusion Models Outperform GANs in Image Classification Tasks
By
–
-
AlpaGasus: Training Better Alpaca Models with Less Data
By
–
AlpaGasus: Training A Better Alpaca with Fewer Data paper page: https://
huggingface.co/papers/2307.08
701
… Large language models~(LLMs) obtain instruction-following capability through instruction-finetuning (IFT) on supervised instruction/response data. However, widely used IFT datasets (e.g., -
BuboGPT: Visual Grounding in Multi-Modal Large Language Models
By
–
BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs
— AK (@_akhaliq) 18 juillet 2023
paper page: https://t.co/e6caibcFrJ
LLMs have demonstrated remarkable abilities at interacting with humans through language, especially with the usage of instruction-following data. Recent advancements in LLMs, such as… pic.twitter.com/QW4crgX9fyBuboGPT: Enabling Visual Grounding in Multi-Modal LLMs paper page: https://
huggingface.co/papers/2307.08
581
… LLMs have demonstrated remarkable abilities at interacting with humans through language, especially with the usage of instruction-following data. Recent advancements in LLMs, such as -
FlashAttention-2: Faster Attention with Better Parallelism
By
–
FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning paper: https://
tridao.me/publications/f
lash2/flash2.pdf
…
github: https://
github.com/Dao-AILab/flas
h-attention
… Scaling Transformers to longer sequence lengths has been a major problem in the last several years, promising to improve performance -
AI Restored 1896 Lumière Brothers Boules Game Footage
By
–
AI restored footage from 1896 showing family and friends of the Lumiére brothers playing a game of Boules at the Lumiére house in La Ciotat, France by HistoryColored pic.twitter.com/STxs93IPz3
— AK (@_akhaliq) 17 juillet 2023AI restored footage from 1896 showing family and friends of the Lumiére brothers playing a game of Boules at the Lumiére house in La Ciotat, France by HistoryColored
-
Hugging Face Papers Email Newsletter Released July 17
By
–
https://
huggingface.co/papers email for 17 July is out -
NIFTY: Neural Fields for Human-Object Interaction Motion Synthesis
By
–
NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis paper page: https://
huggingface.co/papers/2307.07
511
… address the problem of generating realistic 3D motions of humans interacting with objects in a scene. Our key idea is to create a neural interaction field attached to a -
DreamTeacher: Self-Supervised Image Backbone Pretraining with Generative Models
By
–
DreamTeacher: Pretraining Image Backbones with Deep Generative Models
— AK (@_akhaliq) 17 juillet 2023
paper page: https://t.co/Qi11fZk0hC
introduce a self-supervised feature representation learning framework DreamTeacher that utilizes generative networks for pre-training downstream image backbones. We propose… pic.twitter.com/5DqigmtU8cDreamTeacher: Pretraining Image Backbones with Deep Generative Models paper page: https://
huggingface.co/papers/2307.07
487
… introduce a self-supervised feature representation learning framework DreamTeacher that utilizes generative networks for pre-training downstream image backbones. We propose -
Mega-TTS 2: Zero-Shot Text-to-Speech with Arbitrary Length Prompts
By
–
Mega-TTS 2: Zero-Shot Text-to-Speech with Arbitrary Length Speech Prompts paper page: https://
huggingface.co/papers/2307.07
218
… Zero-shot text-to-speech aims at synthesizing voices with unseen speech prompts. Previous large-scale multispeaker TTS models have successfully achieved this goal with -
Learning to Retrieve In-Context Examples for Large Language Models
By
–
Learning to Retrieve In-Context Examples for Large Language Models paper page: https://
huggingface.co/papers/2307.07
164
… Large language models (LLMs) have demonstrated their ability to learn in-context, allowing them to perform various tasks based on a few input-output examples. However, the