Related papers: Visual Late Chunking: An Empirical Study of Contex…

Vision-Language Models (VLMs) face severe memory and latency bottlenecks due to high-resolution visual tokens. While current token reduction methods theoretically save FLOPs, post-hoc pruning introduces structural overhead, failing to yield…

Current document chunking methods for Retrieval-Augmented Generation (RAG) typically linearize text. This forced linearization strips away intrinsic topological hierarchies, creating ``semantic fragmentation'' that degrades downstream…

Modern embedding models capture both semantic and syntactic structures of queries, often mapping different queries to similar regions in vector space. This results in non-uniform cluster access patterns in disk-based vector search systems,…

Code completion can help developers improve efficiency and ease the development lifecycle. Although code completion is available in modern integrated development environments (IDEs), research lacks in determining what makes a good context…

Multimodal document retrieval systems have shown strong progress in aligning visual and textual content for semantic search. However, most existing approaches remain heavily English-centric, limiting their effectiveness in multilingual…

Although Multimodal Large Language Models (MLLMs) have shown remarkable potential in Visual Document Retrieval (VDR) through generating high-quality multi-vector embeddings, the substantial storage overhead caused by representing a page…

Streamlining content discovery within media archives requires integrating advanced data representations and effective visualization techniques for clear communication of video topics to users. The proposed system addresses the challenge of…

Despite advances in feature representation, leveraging geometric relations is crucial for establishing reliable visual correspondences under large variations of images. In this work we introduce a Hough transform perspective on…

Recent progress in vision-language models (VLMs) has led to impressive results in document understanding tasks, but their high computational demands remain a challenge. To mitigate the compute burdens, we propose a lightweight token pruning…

Vector quantization is a technique in machine learning that discretizes continuous representations into a set of discrete vectors. It is widely employed in tokenizing data representations for large language models, diffusion models, and…

Vision-and-Language Navigation (VLN) increasingly relies on large vision-language models, but their inference cost conflicts with real-time deployment. Token caching is a promising training-free strategy that avoids redundant computation by…

The rapid growth of video content demands efficient and precise retrieval systems. While vision-language models (VLMs) excel in representation learning, they often struggle with adaptive, time-sensitive video retrieval. This paper…

In a retrieval system, simultaneously achieving search accuracy and efficiency is inherently challenging. This challenge is particularly pronounced in partially relevant video retrieval (PRVR), where incorporating more diverse context…

Content-defined Chunking (CDC) algorithms dictate the overall space savings that deduplication systems achieve. However, due to their need to scan each file in its entirety, they are slow and often the main performance bottleneck within…

Streaming video understanding with large vision-language models (VLMs) requires a compact memory that can support future reasoning over an ever-growing visual history. A common solution is to compress the key-value (KV) cache, but existing…

This paper tackles an emerging and challenging problem of long video temporal grounding~(VTG) that localizes video moments related to a natural language (NL) query. Compared with short videos, long videos are also highly demanded but less…

Multi-vector representations generated by late interaction models, such as ColBERT, enable superior retrieval quality compared to single-vector representations in information retrieval applications. In multi-vector retrieval systems, both…

Visual document retrieval has become essential for accessing information in visually rich documents. Existing approaches fall into two camps. Late-interaction retrievers achieve strong quality through fine-grained token-level matching but…

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…

Retrieval-Augmented Generation (RAG) has emerged as a framework to address the constraints of Large Language Models (LLMs). Yet, its effectiveness fundamentally hinges on document chunking - an often-overlooked determinant of its quality.…