Related papers: PLAID: An Efficient Engine for Late Interaction Re…

Motivated by the growing demand for retrieval systems that operate across modalities, we introduce llama-nemoretriever-colembed, a unified text-image retrieval model that delivers state-of-the-art performance across multiple benchmarks. We…

Large-scale pre-trained language models such as BERT have contributed significantly to the development of NLP. However, those models require large computational resources, making it difficult to be applied to mobile devices where computing…

While scaling laws have been continuously validated in large language models (LLMs) with increasing model parameters, the inherent tension between the inference demands of LLMs and the limited resources of edge devices poses a critical…

This paper describes a compact and effective model for low-latency passage retrieval in conversational search based on learned dense representations. Prior to our work, the state-of-the-art approach uses a multi-stage pipeline comprising…

Retrieval-augmented generation (RAG) is now standard for knowledge-intensive LLM tasks, but most systems still treat every query as fresh, repeatedly re-retrieving long passages and re-reasoning from scratch, inflating tokens, latency, and…

Large Language Models (LLMs) have demonstrated success across many benchmarks. However, they still exhibit limitations in long-context scenarios, primarily due to their short effective context length, quadratic computational complexity, and…

Unsupervised large-scale vision-language pre-training has shown promising advances on various downstream tasks. Existing methods often model the cross-modal interaction either via the similarity of the global feature of each modality which…

This study investigates the position bias in information retrieval, where models tend to overemphasize content at the beginning of passages while neglecting semantically relevant information that appears later. To analyze the extent and…

Lifelong user modeling, which leverages users' long-term behavior sequences for CTR prediction, has been widely applied in personalized services. Existing methods generally adopted a two-stage "retrieval-refinement" strategy to balance…

AI applications increasingly depend on long-context inference, where LLMs consume substantial context to support stronger reasoning. Common examples include retrieval-augmented generation, agent memory layers, and multi-agent orchestration.…

Large language models (LLMs) enhanced with retrieval-augmented generation (RAG) have introduced a new paradigm for web search. However, the limited context awareness of LLMs degrades their performance on RAG tasks. Existing methods to…

Deploying Vision Transformers on edge devices is challenging due to their high computational complexity, while full offloading to cloud resources presents significant latency overheads. We propose a novel collaborative inference framework,…

Large-scale pre-trained language models such as BERT have brought significant improvements to NLP applications. However, they are also notorious for being slow in inference, which makes them difficult to deploy in real-time applications. We…

The increasing volume of medical images poses challenges for radiologists in retrieving relevant cases. Content-based image retrieval (CBIR) systems offer potential for efficient access to similar cases, yet lack standardized evaluation and…

Decentralized Federated Learning (DFL) struggles with the slow adaptation of late-joining delayed clients and high communication costs in asynchronous environments. These limitations significantly hinder overall performance. To address…

Retrieval-Augmented Generation (RAG) has become a cornerstone technique for enhancing large language models (LLMs) with external knowledge. However, current RAG systems face two critical limitations: (1) they inefficiently retrieve…

Latency is a major concern for web rendering engines like those in Chrome, Safari, and Firefox. These engines reduce latency by using an incremental layout algorithm to redraw the page when the user interacts with it. In such an algorithm,…

Multi-turn dialogues are essential in many real-world applications of large language models, such as chatbots and virtual assistants. As conversation histories become longer, existing large language models face increasing computational and…

We proposed a new technique to accelerate sampling methods for solving difficult optimization problems. Our method investigates the intrinsic connection between posterior distribution sampling and optimization with Langevin dynamics, and…

End-to-end autonomous driving models trained solely with imitation learning (IL) often suffer from poor generalization. In contrast, reinforcement learning (RL) promotes exploration through reward maximization but faces challenges such as…