Keeping you up to date with the latest trends and best performing architectures in this fast evolvin
In this paper, we present a new embedding model, called M3-Embedding, which is distinguished for its
By providing external information to large language models (LLMs), tool augmentation (including retr
As Large Language Models (LLMs) continue to advance in their ability to write human-like text, a key
We introduce Chronos, a simple yet effective framework for pretrained probabilistic time series mode
Advancing the frontier of subquadratic architectures for Language Models (LMs) is crucial in the rap
We present SplattingAvatar, a hybrid 3D representation of photorealistic human avatars with Gaussian
Recent advancements on Large Language Models (LLMs) enable AI Agents to automatically generate and e
Training Large Language Models (LLMs) presents significant memory challenges, predominantly due to t
This technical report introduces TripoSR, a 3D reconstruction model leveraging transformer architect
Denoising diffusion models have emerged as a powerful tool for various image generation and editing
Recent research, such as BitNet, is paving the way for a new era of 1-bit Large Language Models (LLM
We introduce Bonito, an open-source model for conditional task generation: the task of converting un
Prompt engineering is a challenging and important task due to the high sensitivity of Large Language
Sora is a text-to-video generative AI model, released by OpenAI in February 2024. The model is train
Large Language Models (LLMs) are typically trained in two phases: pre-training on large internet-sca
Transformers have emerged as the architecture of choice for many state-of-the-art AI models, showcas
Large language models (LLMs) have accomplished remarkable reasoning performance in various domains.
All text-based language problems can be reduced to either generation or embedding. Current models on
Among the widely used parameter-efficient finetuning (PEFT) methods, LoRA and its variants have gain
The conventional recipe for maximizing model accuracy is to (1) train multiple models with various h
