AI - AI Dynamics

CoTracker: Joint Video Motion Tracking Method

By

–

18 July 2023 4h54

CoTracker: It is Better to Track Together

paper page: https://t.co/1qLLHp17nA

Methods for video motion prediction either estimate jointly the instantaneous motion of all points in a given video frame using optical flow or independently track the motion of individual points… pic.twitter.com/nkO28Kkf8Y
— AK (@_akhaliq) 18 juillet 2023

CoTracker: It is Better to Track Together paper page: https://
huggingface.co/papers/2307.07
635
… Methods for video motion prediction either estimate jointly the instantaneous motion of all points in a given video frame using optical flow or independently track the motion of individual points

Diffusion Models Outperform GANs in Image Classification Tasks

By

–

18 July 2023 4h44

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

→ View original post on X — @xai

Positive Long-Term Future Vision for Artificial Intelligence

By

@xai

–

18 July 2023 4h23

What best describes your view for a positive future on a long time horizon?

AlpaGasus: Training Better Alpaca Models with Less Data

By

–

18 July 2023 3h49

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

–

18 July 2023 3h36

BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs

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/QW4crgX9fy
— AK (@_akhaliq) 18 juillet 2023

BuboGPT: 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