Related papers: Vectorizing the Trie: Efficient Constrained Decodi…

Multilingual Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to perform knowledge-intensive tasks in multilingual settings by leveraging retrieved documents as external evidence. However, when the retrieved…

This chapter explores advancements in decoding strategies for large language models (LLMs), focusing on enhancing the Locally Typical Sampling (LTS) algorithm. Traditional decoding methods, such as top-k and nucleus sampling, often struggle…

The recent many-fold increase in the size of deep neural networks makes efficient distributed training challenging. Many proposals exploit the compressibility of the gradients and propose lossy compression techniques to speed up the…

Existing multimodal large model-based image compression frameworks often rely on a fragmented integration of semantic retrieval, latent compression, and generative models, resulting in suboptimal performance in both reconstruction fidelity…

Retrieval-Augmented Generation (RAG) enhances coding tasks by incorporating retrieved code examples into prompts. However, lengthy prompts, often exceeding tens of thousands of tokens, introduce challenges related to limited context windows…

Large language models (LLMs) have rapidly grown in scale, creating substantial memory and computational costs that hinder efficient deployment. Singular value decomposition (SVD) has emerged as an effective post-training compression…

Learned Sparse Retrieval (LSR) is an effective IR approach that exploits pre-trained language models for encoding text into a learned bag of words. Several efforts in the literature have shown that sparsity is key to enabling a good…

Speculative decoding accelerates autoregressive language model inference by verifying multiple draft tokens in parallel. However, the verification stage often becomes the dominant computational bottleneck, especially for long-context inputs…

Speculative decoding (SD) has been demonstrated as an effective technique for lossless LLM inference acceleration. Retrieval-based SD methods, one kind of model-free method, have yielded promising speedup, but they often rely on incomplete…

Generative retrieval stands out as a promising new paradigm in text retrieval that aims to generate identifier strings of relevant passages as the retrieval target. This generative paradigm taps into powerful generative language models,…

Retrieval-Augmented Generation (RAG) systems have become a dominant approach to augment large language models (LLMs) with external knowledge. However, existing vector database (VecDB) retrieval pipelines rely on flat or single-resolution…

A key paradigm to improve the reasoning capabilities of large language models (LLMs) is to allocate more inference-time compute to search against a verifier or reward model. This process can then be utilized to refine the pretrained model…

Sparse tensor networks are commonly used to represent contractions over sparse tensors. Tensor contractions are higher-order analogs of matrix multiplication. Tensor networks arise commonly in many domains of scientific computing and data…

Retrieval-Augmented Generation (RAG) is a crucial method for mitigating hallucinations in Large Language Models (LLMs) and integrating external knowledge into their responses. Existing RAG methods typically employ query rewriting to clarify…

Generative Recommendation has emerged as a promising paradigm, reformulating recommendation as a sequence-to-sequence generation task over hierarchical Semantic IDs. However, existing methods suffer from a critical issue we term Semantic…

Retrieval-augmented generation (RAG) is critical for reducing hallucinations and incorporating external knowledge into Large Language Models (LLMs). However, advanced RAG systems face a trade-off between performance and efficiency.…

The rapid advancement of Multimodal Large Language Models (MLLMs) has led to remarkable performances across various domains. However, this progress is accompanied by a substantial surge in the resource consumption of these models. We…

Neural document rerankers are extremely effective in terms of accuracy. However, the best models require dedicated hardware for serving, which is costly and often not feasible. To avoid this serving-time requirement, we present a method of…

Retrieval augmented generation (RAG) combines the generative abilities of large language models (LLMs) with external knowledge sources to provide more accurate and up-to-date responses. Recent RAG advancements focus on improving retrieval…

Performing Retrieval-Augmented Generation (RAG) directly on mobile devices is promising for data privacy and responsiveness but is hindered by the architectural constraints of mobile NPUs. Specifically, current hardware struggles with the…