Keeping you up to date with the latest trends and best performing architectures in this fast evolvin
Despite Large Language Models (LLMs) like GPT-4 achieving impressive results in function-level code
In this work, we introduce Unique3D, a novel image-to-3D framework for efficiently generating high-q
We present DeepSeek-Coder-V2, an open-source Mixture-of-Experts (MoE) code language model that achie
The conventional recipe for maximizing model accuracy is to (1) train multiple models with various h
There are two common ways in which developers are incorporating proprietary and domain-specific data
Software engineers are increasingly adding semantic search capabilities to applications using a stra
Language agents perform complex tasks by using tools to execute each step precisely. However, most e
To extend the context length of Transformer-based large language models (LLMs) and improve comprehen
Retrieval Augmented Generation (RAG) enhances the abilities of Large Language Models (LLMs) by enabl
Simultaneous speech-to-speech translation (Simul-S2ST, a.k.a streaming speech translation) outputs t
We introduce VASA, a framework for generating lifelike talking faces with appealing visual affective
The misuse of large language models (LLMs) has drawn significant attention from the general public a
Large Language Models (LLMs) are often described as being instances of foundation models - that is,
We introduce Buffer of Thoughts (BoT), a novel and versatile thought-augmented reasoning approach fo
Knowledge Graphs (KGs) represent human-crafted factual knowledge in the form of triplets (head, rela
We introduce AutoCoder, the first Large Language Model to surpass GPT-4 Turbo (April 2024) and GPT-4
With impressive achievements made, artificial intelligence is on the path forward to artificial gene
Generative pre-trained large language models (LLMs) have demonstrated impressive performance over a
Large language models (LLMs) often generate content that contains factual errors when responding to
End-to-end transformer-based detectors (DETRs) have shown exceptional performance in both closed-set
