Keeping you up to date with the latest trends and best performing architectures in this fast evolvin
Current language models fall short in understanding aspects of the world not easily described in wor
Harnessing the power of human-annotated data through Supervised Fine-Tuning (SFT) is pivotal for adv
We study the fractal structure of language, aiming to provide a precise formalism for quantifying pr
While dense retrieval has been shown to be effective and efficient across tasks and languages, it re
Neural information retrieval (IR) has greatly advanced search and other knowledge-intensive language
Abstract Systems for Open-Domain Question Answering (OpenQA) generally depend on a retriever for fin
Pre-trained language models are increasingly important components across multiple information retrie
Retrieval-augmented language models can better adapt to changes in world state and incorporate long-
Large language models (LLMs) inevitably exhibit hallucinations since the accuracy of generated texts
The rapid development of large language models has revolutionized code intelligence in software deve
Recent years have witnessed remarkable advances in artificial intelligence generated content(AIGC),
Language models (LMs) have become ubiquitous in both NLP research and in commercial product offering
Large language models (LLMs) are trained on massive internet corpora that often contain copyrighted
Fine-tuning large pre-trained models is an effective transfer mechanism in NLP. However, in the pres
Transformer has been considered the dominating neural architecture in NLP and CV, mostly under super
With the widespread use of large language models (LLMs) in NLP tasks, researchers have discovered th
The ML community is rapidly exploring techniques for prompting language models (LMs) and for stackin
Learned representations are a central component in modern ML systems, serving a multitude of downstr
Vision Transformers (ViT) have been shown to attain highly competitive performance for a wide range
Is vision good enough for language? Recent advancements in multimodal models primarily stem from the
