Related papers: TADOC: Text Analytics Directly on Compression
Chain-of-Thought (CoT) reasoning improves performance on complex tasks but introduces significant inference latency due to verbosity. We propose Multiround Adaptive Chain-of-Thought Compression (MACC), a framework that leverages the token…
Recent advancements in generative artificial intelligence have introduced groundbreaking approaches to innovating next-generation semantic communication, which prioritizes conveying the meaning of a message rather than merely transmitting…
Internet of Things (IoT) devices and applications are generating and communicating vast quantities of data, and the rate of data collection is increasing rapidly. These high communication volumes are challenging for energy-constrained,…
Logs are essential for diagnosing failures and conducting retrospective studies, leading many software organizations to retain log messages for a long time. Nevertheless, the volume of generated log data grows rapidly as software systems…
Hierarchical reinforcement learning has focused on discovering temporally extended actions, such as options, that can provide benefits in problems requiring extensive exploration. One promising approach that learns these options end-to-end…
Lookup tables are a fundamental structure in many data processing and systems applications. Examples include tokenized text in NLP, quantized embedding collections in recommendation systems, integer sketches for streaming data, and…
Sophisticated traffic analytics, such as the encrypted traffic analytics and unknown malware detection, emphasizes the need for advanced methods to analyze the network traffic. Traditional methods of using fixed patterns, signature…
Since the advent of the web, the amount of data on wen has been increased several million folds. In recent years web data generated is more than data stored for years. One important data format is text. To answer user queries over the…
Effective token compression remains a critical challenge for scaling models to handle increasingly complex and diverse datasets. A novel mechanism based on contextual reinforcement is introduced, dynamically adjusting token importance…
Task-oriented communication is a new paradigm that aims at providing efficient connectivity for accomplishing intelligent tasks rather than the reception of every transmitted bit. In this paper, a deep learning-based task-oriented…
We develop the theory and practical implementation of p-adic sparse coding of data. Rather than the standard, sparsifying criterion that uses the $L_0$ pseudo-norm, we use the p-adic norm. We require that the hierarchy or tree be…
Documents are central to many business systems, and include forms, reports, contracts, invoices or purchase orders. The information in documents is typically in natural language, but can be organized in various layouts and formats. There…
AI coding agents can resolve real-world software issues, yet they frequently introduce regressions -- breaking tests that previously passed. Current benchmarks focus almost exclusively on resolution rate, leaving regression behavior…
Modern applied optimization problems become more and more complex every day. Due to this fact, distributed algorithms that can speed up the process of solving an optimization problem through parallelization are of great importance. The main…
High-energy, large-scale particle colliders in nuclear and high-energy physics generate data at extraordinary rates, reaching up to $1$ terabyte and several petabytes per second, respectively. The development of real-time, high-throughput…
In many learning situations, resources at inference time are significantly more constrained than resources at training time. This paper studies a general paradigm, called Differentiable ARchitecture Compression (DARC), that combines model…
Anonymizing textual documents is a highly context-sensitive problem: the appropriate balance between privacy protection and utility preservation varies with the data domain, privacy objectives, and downstream application. However, existing…
Dataset distillation compresses large datasets into compact synthetic ones to reduce storage and computational costs. Among various approaches, distribution matching (DM)-based methods have attracted attention for their high efficiency.…
Visual instruction tuning aims to enable large language models to comprehend the visual world, with a pivotal challenge lying in establishing an effective vision-to-language projection. However, existing methods often grapple with the…
The Data-to-Text task aims to generate human-readable text for describing some given structured data enabling more interpretability. However, the typical generation task is confined to a few particular domains since it requires well-aligned…