With such multi-dimension and multi-scale factorization, our MorphMLP block can achieve a great accuracy-computation balance.
Ranked #18 on Action Recognition on Something-Something V2 (using extra training data)
We introduce the problem of disentangling time-lapse sequences in a way that allows separate, after-the-fact control of overall trends, cyclic effects, and random effects in the images, and describe a technique based on data-driven generative models that achieves this goal.
By evaluating on a number of benchmark test sets, we find that ChatGPT performs competitively with commercial translation products (e. g., Google Translate) on high-resource European languages but lags behind significantly on low-resource or distant languages.
Our Fast-BEV consists of five parts, We novelly propose (1) a lightweight deployment-friendly view transformation which fast transfers 2D image feature to 3D voxel space, (2) an multi-scale image encoder which leverages multi-scale information for better performance, (3) an efficient BEV encoder which is particularly designed to speed up on-vehicle inference.
Text-to-image synthesis has recently seen significant progress thanks to large pretrained language models, large-scale training data, and the introduction of scalable model families such as diffusion and autoregressive models.
Ranked #14 on Text-to-Image Generation on COCO
Retrieval-Augmented Language Modeling (RALM) methods, that condition a language model (LM) on relevant documents from a grounding corpus during generation, have been shown to significantly improve language modeling while also providing a natural source attribution mechanism.
We study the design decisions of publicly available instruction tuning methods, and break down the development of Flan 2022 (Chung et al., 2022).