Related papers: CoRoVA: Compressed Representations for Vector-Augm…

High-resolution Large Multimodal Models (LMMs) encounter the challenges of excessive visual tokens and quadratic visual complexity. Current high-resolution LMMs address the quadratic complexity while still generating excessive visual…

Retrieval-augmented generation (RAG) has become a key paradigm for knowledge-intensive question answering. However, existing multi-hop RAG systems remain inefficient, as they alternate between retrieval and reasoning at each step, resulting…

Multimodal large language models (MLLMs) have recently shown great progress in text-rich image understanding, yet they still struggle with complex, multi-page visually-rich documents. Traditional methods using document parsers for…

Generating Chain-of-Thought (CoT) before deriving the answer can effectively improve the reasoning capabilities of large language models (LLMs) and significantly improve the accuracy of the generated answer. However, in most cases, the…

Retrieval-augmented generation (RAG) techniques have emerged as a promising solution to enhance the reliability of large language models (LLMs) by addressing issues like hallucinations, outdated knowledge, and domain adaptation. In…

Text-to-speech (TTS) synthesis has seen renewed progress under the discrete modeling paradigm. Existing autoregressive approaches often rely on single-codebook representations, which suffer from significant information loss. Even with…

Recent advances in text-to-video generation, particularly with autoregressive models, have enabled the synthesis of high-quality videos depicting individual scenes. However, extending these models to generate long, cross-scene videos…

Retrieval-augmented generation (RAG) can supplement large language models (LLMs) by integrating external knowledge. However, as the number of retrieved documents increases, the input length to LLMs grows linearly, causing a dramatic…

We approach the important challenge of code autocompletion as an open-domain task, in which a sequence-to-sequence code generator model is enhanced with the ability to attend to reference code snippets supplied by a semantic code search…

Recently, large vision-language models (LVLMs) have rapidly gained popularity for their strong generation and reasoning capabilities given diverse multimodal inputs. However, these models incur significant computational and memory overhead…

High-resolution inputs enable Large Vision-Language Models (LVLMs) to discern finer visual details, enhancing their comprehension capabilities. To reduce the training and computation costs caused by high-resolution input, one promising…

Large Language Models (LLMs) excel at code generation but struggle with complex problems. Retrieval-Augmented Generation (RAG) mitigates this issue by integrating external knowledge, yet retrieval models often miss relevant context, and…

Large Language Models (LLMs) have been integrated into recommender systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further incorporated into these systems to retrieve more relevant items…

Multi-modal Retrieval-Augmented Generation (RAG) has become a critical method for empowering LLMs by leveraging candidate visual documents. However, current methods consider the entire document as the basic retrieval unit, introducing…

Large Language Models (LLMs) have shown remarkable performance in Open-Domain Question Answering (ODQA) by leveraging external documents through Retrieval-Augmented Generation (RAG). To reduce RAG overhead, from longer context, context…

Long text generation, such as novel writing and discourse-level translation with extremely long contexts, presents significant challenges to current language models. Existing methods mainly focus on extending the model's context window…

Large Language Models (LLMs) face limitations due to the high demand on GPU memory and computational resources when handling long contexts. While sparsify the Key-Value (KV) cache of transformer model is a typical strategy to alleviate…

Traditional Retrieval-Augmented Generation (RAG) approaches generally assume that retrieval and generation occur on powerful servers removed from the end user. While this reduces local hardware constraints, it introduces significant…

Large reasoning models (LRMs) often incur significant key-value (KV) cache overhead, due to their linear growth with the verbose chain-of-thought (CoT) reasoning. This incurs both memory overhead and throughput bottlenecks, limiting…

The scaling of large language models to encode all the world's knowledge in model parameters is unsustainable and has exacerbated resource barriers. Retrieval-Augmented Generation (RAG) presents a potential solution, yet its application to…