Keeping you up to date with the latest trends and best performing architectures in this fast evolvin
We introduce AnyTool, a large language model agent designed to revolutionize the utilization of a va
Large Language Models (LLMs) employ auto-regressive decoding that requires sequential computation, w
Large decoder-only language models (LLMs) are the state-of-the-art models on most of today's NLP tas
Large-scale pretrained transformers have created milestones in text (GPT-3) and text-to-image (DALL-
Information seeking and integration is a complex cognitive task that consumes enormous time and effo
Diffusion models have achieved great progress in image animation due to powerful generative capabili
FinanceBench is a first-of-its-kind test suite for evaluating the performance of LLMs on open book f
Current hair transfer methods struggle to handle diverse and intricate hairstyles, thus limiting the
Data science and engineering workflows often span multiple stages, from warehousing to orchestration
This report introduces FunAudioLLM, a model family designed to enhance natural voice interactions be
As Large Language Models (LLMs) achieve remarkable progress in language understanding and generation
We study how to apply large language models to write grounded and organized long-form articles from
Latest advances have achieved realistic virtual try-on (VTON) through localized garment inpainting u
Human video generation is a dynamic and rapidly evolving task that aims to synthesize 2D human body
The rapid advancement of large language models (LLMs) has paved the way for the development of highl
With the remarkable advancements in image generation and open-form text generation, the creation of
While language models (LMs) have shown potential across a range of decision-making tasks, their reli
Portrait Animation aims to synthesize a lifelike video from a single source image, using it as an ap
Recent advancements in large language models (LLMs) have significantly advanced the automation of so
Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks tradi
