@_akhaliq - AI Dynamics - Page 103 of 140

Semantic-SAM: Universal Image Segmentation at Any Granularity

By

–

11 July 2023 4h56

Semantic-SAM: Segment and Recognize Anything at Any Granularity paper page: https://
huggingface.co/papers/2307.04
767
… introduce Semantic-SAM, a universal image segmentation model to enable segment and recognize anything at any desired granularity. Our model offers two key advantages:

→ View original post on X — @_akhaliq

11 July 2023

VampNet: Masked Acoustic Token Modeling for Music Generation

By

@_akhaliq

–

11 July 2023 4h53

VampNet: Music Generation via Masked Acoustic Token Modeling

paper page: https://t.co/FScor4pyFy

introduce VampNet, a masked acoustic token modeling approach to music synthesis, compression, inpainting, and variation. We use a variable masking schedule during training which… pic.twitter.com/pjxZlq5yWj
— AK (@_akhaliq) 11 juillet 2023

VampNet: Music Generation via Masked Acoustic Token Modeling paper page: https://
huggingface.co/papers/2307.04
686
… introduce VampNet, a masked acoustic token modeling approach to music synthesis, compression, inpainting, and variation. We use a variable masking schedule during training which

→ View original post on X — @_akhaliq

11 July 2023

Sketch-A-Shape: Zero-Shot Sketch-to-3D Shape Generation

By

@_akhaliq

–

11 July 2023 4h48

Sketch-A-Shape: Zero-Shot Sketch-to-3D Shape Generation paper page: https://
huggingface.co/papers/2307.03
869
… Significant progress has recently been made in creative applications of large pre-trained models for downstream tasks in 3D vision, such as text-to-shape generation. This motivates our

→ View original post on X — @_akhaliq

11 July 2023

Dormitories of Different Countries Generated by Midjourney AI

By

@_akhaliq

–

11 July 2023 1h38

Dormitories of different countries, midjourney AI 1. France

→ View original post on X — @_akhaliq

11 July 2023

Hugging Face Papers Daily Email Distribution

By

@_akhaliq

–

10 July 2023 16h12

https://
huggingface.co/papers daily email just went out

→ View original post on X — @_akhaliq

10 July 2023

Frontier AI Regulation: Managing Emerging Risks to Public Safety

By

@_akhaliq

–

10 July 2023 7h43

Frontier AI Regulation: Managing Emerging Risks to Public Safety paper page: https://
huggingface.co/papers/2307.03
718
… Advanced AI models hold the promise of tremendous benefits for humanity, but society needs to proactively manage the accompanying risks. In this paper, we focus on what we term

→ View original post on X — @_akhaliq

10 July 2023

Generalization Gap in Visual Robotic Imitation Learning

By

@_akhaliq

–

10 July 2023 7h39

Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation paper page: https://
huggingface.co/papers/2307.03
659
… What makes generalization hard for imitation learning in visual robotic manipulation? This question is difficult to approach at face value, but the

→ View original post on X — @_akhaliq

10 July 2023

Gradient Descent as Optimal In-Context Learner in Linear Self-Attention

By

@_akhaliq

–

10 July 2023 7h37

One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention paper page: https://
huggingface.co/papers/2307.03
576
… Recent works have empirically analyzed in-context learning and shown that transformers trained on synthetic linear regression

→ View original post on X — @_akhaliq

10 July 2023

Self-Instruct: Early Stopping for Minimal Instruction Tuning

By

@_akhaliq

–

10 July 2023 7h06

Becoming self-instruct: introducing early stopping criteria for minimal instruct tuning paper page: https://
huggingface.co/papers/2307.03
692
… introduce the Instruction Following Score (IFS), a metric that detects language models' ability to follow instructions. The metric has a dual purpose.

→ View original post on X — @_akhaliq

10 July 2023