arXiv Computation and Language October 9, 2026 By Vinko Sabol\v{c}ec, Angelos Katharopoulos, David Grangier

Lossy Compressive Text Autoencoders

Read the original on arXiv Computation and Language →

The paper introduces a lossy compressive text autoencoder that learns a compressed latent representation of text by applying residual downscaling and upscaling along the time axis, culminating in a low‑dimensional discrete bottleneck. The authors evaluate various quantization methods, training objectives, and datasets, measuring reconstruction quality with BLEU and LLM‑based semantic judgments, and also test downstream performance on question‑answering and semantic similarity tasks. Their results show that the compressed representations achieve compression rates comparable to lossless algorithms (2.24 bits per byte on web text) while maintaining strong reconstruction and downstream task performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Sep 15

Dynamic Semantic Compression for Efficient Latent-Space Inference in Large Language Models

arXiv:2609.15338v1 Announce Type: cross Abstract: Large Language Models (LLMs) primarily perform inference at the token level, resulting in substantial memory overhead and compromised computational e...

By Peipei Li, Dongsen Zhang, Yuchen Liu, Wenjun Xu

llms diffusion efficiency

arXiv Computation and Language

3d ago

When Is 0.1% Enough? Analyzing the Combined Effects of Dimensionality Reduction and Quantization on Text Embedding Compression

The paper investigates how dimensionality reduction and quantization together affect text embedding compression across four task families in the Massive Text Embedding Benchmark using five pretrained models. It finds that combining these techniques can preserve near-original performance while drastically reducing storage, with some classification models retaining at least 99% of their score using less than 0.1% of the original storage. The optimal trade‑off between dimensionality and bit‑width varies by task, with retrieval tasks being more sensitive to compression.

By Riku Kisako, Hayato Tsukagoshi, Ryohei Sasano

rag efficiency benchmarks

Hugging Face Trending Papers

Jun 24

BitNet Text Embeddings

LLM-based text embedders have substantially improved retrieval and semantic representation quality, but their deployment remains costly: large backbone models slow down embedding inference, while high-dimensional full-precision embeddings impose substantial storage and bandwidth overhead on large-scale indexes. In this paper, we present BITEMBED, an extreme low-bit framework for LLM-based text embedding that jointly targets encoding efficiency and vector storage.

llms rag fine-tuning efficiency

arXiv Machine Learning

Jul 24

Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs

arXiv:2607. 21291v1 Announce Type: cross Abstract: Large language models (LLMs) achieve strong generation and reasoning performance, but the Transformer architecture incurs high inference cost.

By Yidu Wu, Xiang Wang, Kejie Zhao, Zhangchi Wang, Qinghai Guo, Xiaoying Tang

llms fine-tuning efficiency safety

arXiv Computation and Language

Sep 24

EnComp: Lightweight Encoder-Only Context Compression for Retrieval-Augmented Question Answering

arXiv:2603.09222v2 Announce Type: replace Abstract: Efficient context compression is critical for retrieval-augmented question answering in resource-constrained settings, where long retrieved context...

By Thao Do, Dinh Phu Tran, An Vo, Seon Kwon Kim, Daeyoung Kim

llms rag nlp efficiency

arXiv AI

Jul 16

DIVE: Embedding Compression via Self-Limiting Gradient Updates

arXiv:2605. 20689v2 Announce Type: replace-cross Abstract: High-dimensional language-model embeddings increase storage and search costs, while supervised compressors can overfit when relevance labels are scarce.

By Dongfang Zhao