Related papers: Stingy Context: 18:1 Hierarchical Code Compression…

Arithmetic coding is an essential class of coding techniques. One key issue of arithmetic encoding method is to predict the probability of the current coding symbol from its context, i.e., the preceding encoded symbols, which usually can be…

We propose novel compression algorithms for time-varying channel state information (CSI) in wireless communications. The proposed scheme combines (lossy) vector quantisation and (lossless) compression. First, the new vector quantisation…

Prompt compression condenses contexts while maintaining their informativeness for different usage scenarios. It not only shortens the inference time and reduces computational costs during the usage of large language models, but also lowers…

We introduce Lossless Context Management (LCM), a deterministic architecture for LLM memory that outperforms Claude Code on long-context tasks. When benchmarked using Opus 4.6, our LCM-augmented coding agent, Volt, achieves higher scores…

The existing Retrieval-Augmented Generation (RAG) systems face significant challenges in terms of cost and effectiveness. On one hand, they need to encode the lengthy retrieved contexts before responding to the input tasks, which imposes…

With context windows of millions of tokens, Long-Context Language Models (LCLMs) can encode entire document collections, offering a strong alternative to conventional retrieval-augmented generation (RAG). However, it remains unclear whether…

Recent successes in natural language processing have led to the proliferation of large language models (LLMs) by multiple providers. Each LLM offering has different inference accuracy, monetary cost, and latency, and their accuracy further…

Large Language Models (LLMs) achieve strong performance across tasks, but face storage and compute challenges on edge devices. We propose EntroLLM, a compression framework combining mixed quantization and entropy coding to reduce storage…

Large Language Models (LLMs) struggle with long-horizon tasks due to the "context bottleneck" and the "lost-in-the-middle" phenomenon, where accumulated noise from verbose environments degrades reasoning over multi-turn interactions. To…

Large language models (LLMs) have shown promising performance across diverse domains. Many practical applications of LLMs, such as code completion and structured data extraction, require adherence to syntactic constraints specified by a…

Although large language models (LLM) have achieved remarkable performance, their enormous parameter counts hinder deployment on resource-constrained hardware. Low-rank compression can reduce both memory usage and computational demand, but…

The impressive capabilities of large foundation models come at a cost of substantial computing resources to serve them. Compressing these pre-trained models is of practical interest as it can democratize deploying them to the machine…

Question-answering (QA) is a significant application of Large Language Models (LLMs), shaping chatbot capabilities across healthcare, education, and customer service. However, widespread LLM integration presents a challenge for small…

Agentic RAG systems that equip language models with dozens to hundreds of tool definitions face a critical resource conflict: tool schemas consume the same context window needed for retrieval-augmented generation. We present the first…

Deploying LLMs raises two coupled challenges: (1) monitoring--estimating where a model underperforms as traffic and domains drift--and (2) improvement--prioritizing data acquisition to close the largest performance gaps. We test whether an…

We present a series of long-context LLMs that support effective context windows of up to 32,768 tokens. Our model series are built through continual pretraining from Llama 2 with longer training sequences and on a dataset where long texts…

Embedding-based code retrieval often suffers when encoders overfit to surface syntax. Prior work mitigates this by using LLMs to rephrase queries and corpora into a normalized style, but leaves two questions open: how much representational…

The prevailing approach to improving large language model (LLM) reasoning has centered on expanding context windows, implicitly assuming that more tokens yield better performance. However, empirical evidence - including the "lost in the…

We propose a context-adaptive entropy model for use in end-to-end optimized image compression. Our model exploits two types of contexts, bit-consuming contexts and bit-free contexts, distinguished based upon whether additional bit…

Recent techniques such as retrieval-augmented generation or chain-of-thought reasoning have led to longer contexts and increased inference costs. Context compression techniques can reduce these costs, but the most effective approaches…