Related papers: RAVEN: In-Context Learning with Retrieval-Augmente…
Humans can quickly learn a new word from a few illustrative examples, and then systematically and flexibly use it in novel contexts. Yet the abilities of current language models for few-shot word learning, and methods for improving these…
Visual In-Context Learning (VICL) has emerged as a powerful paradigm, enabling models to perform novel visual tasks by learning from in-context examples. The dominant "retrieve-then-prompt" approach typically relies on selecting the single…
Recent breakthroughs in reasoning models have markedly advanced the reasoning capabilities of large language models, particularly via training on tasks with verifiable rewards. Yet, a significant gap persists in their adaptation to real…
Automatic speech recognition (ASR) has benefited from advances in pretrained speech and language models, yet most systems remain constrained to monolingual settings and short, isolated utterances. While recent efforts in context-aware ASR…
Large language models exhibit a remarkable capacity for in-context learning, where they learn to solve tasks given a few examples. Recent work has shown that transformers can be trained to perform simple regression tasks in-context. This…
Tabular foundation models have shown strong performance across various tabular learning tasks via in-context learning, offering robust generalization without any downstream finetuning. However, their inference-time costs remain high,…
We present a live demonstration for RAVEN, a real-time audio-visual speech enhancement system designed to run entirely on a CPU. In single-channel, audio-only settings, speech enhancement is traditionally approached as the task of…
A Comparison of Independent and Joint Fine-tuning Strategies for Retrieval-Augmented Generation Download PDF Neal Gregory Lawton, Alfy Samuel, Anoop Kumar, Daben Liu Published: 20 Aug 2025, Retrieval augmented generation (RAG) is a popular…
The ability to integrate context, including perceptual and temporal cues, plays a pivotal role in grounding the meaning of a linguistic utterance. In order to measure to what extent current vision-and-language models master this ability, we…
Federated learning is a prime candidate for distributed machine learning at the network edge due to the low communication complexity and privacy protection among other attractive properties. However, existing algorithms face issues with…
This paper explores the elusive mechanism underpinning in-context learning in Large Language Models (LLMs). Our work provides a novel perspective by examining in-context learning via the lens of surface repetitions. We quantitatively…
Although Retrieval-Augmented Large Language Models (RALMs) demonstrate their superiority in terms of factuality, they do not consistently outperform the original retrieval-free Language Models (LMs). Our experiments reveal that this…
To better support information retrieval tasks such as web search and open-domain question answering, growing effort is made to develop retrieval-oriented language models, e.g., RetroMAE and many others. Most of the existing works focus on…
Large-scale language models have shown the ability to adapt to a new task via conditioning on a few demonstrations (i.e., in-context learning). However, in the vision-language domain, most large-scale pre-trained vision-language (VL) models…
Reinforcement learning (RL) has shown an outstanding capability for solving complex computational problems. However, most RL algorithms lack an explicit method that would allow learning from contextual information. Humans use context to…
Recently, Transformer-based encoder-decoder models have demonstrated strong performance in multilingual speech recognition. However, the decoder's autoregressive nature and large size introduce significant bottlenecks during inference.…
Current State-of-the-Art models in Named Entity Recognition (NER) are neural models with a Conditional Random Field (CRF) as the final network layer, and pre-trained "contextual embeddings". The CRF layer is used to facilitate global…
Retrieval-augmented language models show promise in addressing issues like outdated information and hallucinations in language models (LMs). However, current research faces two main problems: 1) determining what information to retrieve, and…
Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code…
With approximately 7,000 languages spoken worldwide, current large language models (LLMs) support only a small subset. Prior research indicates LLMs can learn new languages for certain tasks without supervised data. We extend this…