Related papers: CARAMEL: A Succinct Read-Only Lookup Table via Com…

Dense retrieval methods typically target unstructured text data represented as flat strings. However, e-commerce catalogs often include structured information across multiple fields, such as brand, title, and description, which contain…

Compressed prompts aid instruction-tuned language models (LMs) in overcoming context window limitations and reducing computational costs. Existing methods, which primarily based on training embeddings, face various challenges associated…

According to Algorithmic Information Theory (AIT) -- Intelligent representations compress data into the shortest possible program that can reconstruct its content, exhibiting low Kolmogorov Complexity (KC). In contrast, most visual…

Large vision-language models (LVLMs) achieve strong multimodal understanding, but their inference cost grows rapidly with the number of visual tokens, especially for high-resolution images and long videos. Existing attention-based methods…

Current unified multimodal models typically rely on discrete visual tokenizers to bridge the modality gap. However, discretization inevitably discards fine-grained semantic information, leading to suboptimal performance in visual…

We propose a strategy to compress and store large volumes of scientific data represented on unstructured grids. Approaches utilizing tensor decompositions for data compression have already been proposed. Here, data on a structured grid is…

Large language models suffer from knowledge staleness and lack of interpretability due to implicit knowledge storage across entangled network parameters, preventing targeted updates and reasoning transparency. We propose ExplicitLM, a novel…

Kernel methods provide a theoretically grounded framework for non-linear and non-parametric learning, with strong analytic foundations and statistical guarantees. Yet, their scalability has long been limited by prohibitive time and memory…

Table images present unique challenges for effective and efficient understanding due to the need for question-specific focus and the presence of redundant background regions. Existing Multimodal Large Language Model (MLLM) approaches often…

Large Language Models (LLMs) present significant deployment challenges due to their immense size and computational requirements. Model compression techniques are essential for making these models practical for resource-constrained…

This paper presents new alternatives to the well-known Bloom filter data structure. The Bloom filter, a compact data structure supporting set insertion and membership queries, has found wide application in databases, storage systems, and…

Cropping high-resolution document images into multiple sub-images is the most widely used approach for current Multimodal Large Language Models (MLLMs) to do document understanding. Most of current document understanding methods preserve…

Voxel-based segmentation volumes often store a large number of labels and voxels, and the resulting amount of data can make storage, transfer, and interactive visualization difficult. We present a lossless compression technique which…

To alleviate the problem of information explosion, recommender systems are widely deployed to provide personalized information filtering services. Usually, embedding tables are employed in recommender systems to transform high-dimensional…

Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex tasks. However, manually designing optimal communication topologies is labor-intensive, while automated expansion methods often result…

Efficient context compression is crucial for improving the accuracy and scalability of question answering. For the efficiency of Retrieval Augmented Generation, context should be delivered fast, compact, and precise to ensure clue…

Large language models (LLMs) exhibit a wide range of capabilities, including mathematical reasoning, code generation, and linguistic behaviors. We show that many capabilities are highly localized to small subsets of attention heads within…

Learning effective visual representations that generalize well without human supervision is a fundamental problem in order to apply Machine Learning to a wide variety of tasks. Recently, two families of self-supervised methods, contrastive…

Motivation: Second generation sequencing technology makes it feasible for many researches to obtain enough sequence reads to attempt the de novo assembly of higher eukaryotes (including mammals). De novo assembly not only provides a tool…

The stateless architecture of Large Language Models inherently lacks the mechanism to preserve dynamic context, compelling agents to redundantly reprocess history to maintain long-horizon autonomy. While latent memory offers a solution,…