Related papers: Constrained Auto-Regressive Decoding Constrains Ge…

Retrieval-Augmented Generation (RAG) has emerged as a standard framework for knowledge-intensive NLP tasks, combining large language models (LLMs) with document retrieval from external corpora. Despite its widespread use, most RAG pipelines…

Large language models (LLMs) have demonstrated remarkable capabilities in a wide range of tasks, yet their application to specialized domains remains challenging due to the need for deep expertise. Retrieval-Augmented generation (RAG) has…

Recently, retrieval-augmented text generation attracted increasing attention of the computational linguistics community. Compared with conventional generation models, retrieval-augmented text generation has remarkable advantages and…

Recent advances in large language models (LLMs) have demonstrated impressive capabilities in code-related tasks, such as code generation and automated program repair. Despite their promising performance, most existing approaches for code…

The reconstruction of X-rays CT images from sparse or limited-angle geometries is a highly challenging task. The lack of data typically results in artifacts in the reconstructed image and may even lead to object distortions. For this…

Retrieval-Augmented Generation (RAG) has become a pivotal paradigm for Large Language Models (LLMs), yet current approaches struggle with visually rich documents by treating text and images as isolated retrieval targets. Existing methods…

Long document retrieval aims to fetch query-relevant documents from a large-scale collection, where knowledge distillation has become de facto to improve a retriever by mimicking a heterogeneous yet powerful cross-encoder. However, in…

Retrieval-Augmented Generation (RAG) has emerged as a widely adopted approach for knowledge injection during large language model (LLM) inference in recent years. However, due to their limited ability to exploit fine-grained inter-document…

Retrieval-Augmented Generation (RAG) has emerged as a critical technique for enhancing large language model (LLM) capabilities. However, practitioners face significant challenges when making RAG deployment decisions. While existing research…

Despite the huge progress in myriad generation tasks, pretrained language models (LMs) such as GPT2 still tend to generate repetitive texts with maximization-based decoding algorithms for open-ended generation. We attribute their…

Retrieval-augmented generation (RAG) has seen many empirical successes in recent years by aiding the LLM with external knowledge. However, its theoretical aspect has remained mostly unexplored. In this paper, we propose the first…

Many natural language generation tasks, such as abstractive summarization and text simplification, are paraphrase-orientated. In these tasks, copying and rewriting are two main writing modes. Most previous sequence-to-sequence (Seq2Seq)…

Predicting stable and metastable structures is central to molecular and materials discovery, but remains limited by the cost of searching high-dimensional energy landscapes. Deep generative models offer efficient structure sampling, yet…

Retrieval-Augmented Generation (RAG) systems commonly use chunking strategies for retrieval, which enhance large language models (LLMs) by enabling them to access external knowledge, ensuring that the retrieved information is up-to-date and…

Generative models are widely used for unsupervised learning with various applications, including data compression and signal restoration. Training methods for such systems focus on the generality of the network given limited amount of…

Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image. While…

We present a novel approach for constrained Bayesian inference. Unlike current methods, our approach does not require convexity of the constraint set. We reduce the constrained variational inference to a parametric optimization over the…

Designing an embedding retrieval system requires navigating a complex design space of conflicting trade-offs between efficiency and effectiveness. This work structures these decisions as a vertical traversal of the system design stack. We…

Continuous visual autoregressive (AR) models have demonstrated promising performance in image generation. However, the heavy autoregressive inference burden imposes significant overhead. In Large Language Models (LLMs), speculative decoding…

In the last few years the systematic adoption of deep learning to visual generation has produced impressive results that, amongst others, definitely benefit from the massive exploration of convolutional architectures. In this paper, we…