Related papers: The Lossy Horizon: Error-Bounded Predictive Coding…

Large language models (LLMs) demonstrate strong performance as text embedding models when finetuned with supervised contrastive training. However, their large size balloons inference time and memory requirements. In this paper, we show that…

Traditional lossless text compression preserves every byte, but its gains on natural language are often modest in realistic operating regimes. We study \emph{lossy semantic text compression}, where the encoder strategically deletes parts of…

Current large language models (LLMs) generally lack an effective runtime memory mechanism,making it difficult to adapt to dynamic and personalized interaction requirements. To address this issue, this paper proposes a novel neural memory…

In this report, we investigate the potential use of large language models (LLM's) in the task of data compression. Previous works have demonstrated promising results in applying LLM's towards compressing not only text, but also a wide range…

Error resilient tools like Packet Loss Concealment (PLC) and Forward Error Correction (FEC) are essential to maintain a reliable speech communication for applications like Voice over Internet Protocol (VoIP), where packets are frequently…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision-language understanding, reasoning, and generation. However, they struggle with tasks requiring fine-grained localization and reasoning in…

Most current long-context language models still rely on attention to handle both local interaction and long-range state, which leaves relatively little room to test alternative decompositions of sequence modeling. We propose LPC-SM, a…

In spite of the great potential of large language models (LLMs) across various tasks, their deployment on resource-constrained devices remains challenging due to their excessive computational and memory demands. Quantization has emerged as…

Large language models (LLMs) have shown remarkable success in language modelling due to scaling laws found in model size and the hidden dimension of the model's text representation. Yet, we demonstrate that compressed representations of…

Learning, prediction, and compression are intimately connected: a model that accurately predicts the next symbol in a sequence can be coupled with a source coder to compress that sequence near its information-theoretic limit. When tokenized…

Despite the recent success of Large Language Models (LLMs), it remains challenging to feed LLMs with long prompts due to the fixed size of LLM inputs. As a remedy, prompt compression becomes a promising solution by removing redundant tokens…

This paper considers the performance of $(j,k)$-regular low-density parity-check (LDPC) codes with message-passing (MP) decoding algorithms in the high-rate regime. In particular, we derive the high-rate scaling law for MP decoding of LDPC…

The performance of maximum-likelihood (ML) decoding on the binary erasure channel for finite-length low-density parity-check (LDPC) codes from two random ensembles is studied. The theoretical average spectrum of the Gallager ensemble is…

Click-through rate (CTR) prediction plays an important role in online advertising systems. On the one hand, traditional CTR prediction models capture the collaborative signals in tabular data via feature interaction modeling, but they lose…

Multi-token prediction (MTP) is a prominent strategy to significantly speed up generation in large language models (LLMs), including byte-level LLMs, which are tokeniser-free but prohibitively slow. However, existing MTP methods often…

Augmenting Large Language Models (LLMs) with retrieved external knowledge has proven effective for improving the factual accuracy of generated responses. Despite their success, retrieval-augmented LLMs still face the distractibility issue,…

Large Language Models (LLMs) have become a cornerstone in Natural Language Processing (NLP), achieving impressive performance in text generation. Their token-level representations capture rich, human-aligned semantics. However, pooling…

Predictive coding (PC) is a biologically plausible alternative to standard backpropagation (BP) that minimises an energy function with respect to network activities before updating weights. Recent work has improved the training stability of…

Large Language Models (LLMs) are often asked to generate structured outputs that obey precise syntactic rules, such as code snippets or formatted data. Grammar-constrained decoding (GCD) can guarantee that LLM outputs matches such rules by…

Phase change memory (PCM) has recently emerged as a promising technology to meet the fast growing demand for large capacity memory in computer systems, replacing DRAM that is impeded by physical limitations. Multi-level cell (MLC) PCM…