Natural language processing

Language is one of the key forms of communication. We study methods of language representation and understanding to simplify human-computer interactions.

Area 10. Natural language processing.svg

Posts

Publications

  • Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models

    Large-scale machine learningNatural language processing
    Alina Shutova
    Vladimir Malinovskii
    Vage Egiazarian
    Denis Kuznedelev
    Denis Mazur
    Nikita Surkov
    Ivan Ermakov
    Dan Alistarh
    ICML, 2025

    Efficient real-world deployments of large language models (LLMs) rely on Key-Value (KV) caching for processing and generating long outputs, reducing the need for repetitive computation. For large contexts, Key-Value caches can take up tens of gigabytes of device memory, as they store vector representations for each token and layer. Recent work has shown that the cached vectors can be compressed through quantization, pruning or merging, but these techniques often compromise quality towards higher compression rates. In this work, we aim to improve Key & Value compression by exploiting two observations: 1) the inherent dependencies between keys and values across different layers, and 2) the existence of high-compression methods for internal network states (e.g. attention Keys & Values). We propose AQUA-KV, an adaptive quantization for Key-Value caches that relies on compact adapters to exploit existing dependencies between Keys and Values, and aims to “optimally” compress the information that cannot be predicted. AQUA-KV significantly improves compression rates, while maintaining high accuracy on state-of-the-art LLM families. On Llama 3.2 LLMs, we achieve near-lossless inference at 2-2.5 bits per value with under 1 relative error in perplexity and LongBench scores. AQUA-KV is one-shot, simple, and efficient: it can be calibrated on a single GPU within 1-6 hours, even for 70B models.

  • EvoPress: Accurate Dynamic Model Compression via Evolutionary Search

    Model compressionLarge-scale machine learningNatural language processing
    Oliver Sieberling
    Denis Kuznedelev
    Eldar Kurtic
    Dan Alistarh
    ICML, 2025

    The high computational costs of large language models (LLMs) have led to a flurry of research on LLM compression, via methods such as quantization, sparsification, or structured pruning. A new frontier in this area is given by dynamic, non-uniform compression methods, which adjust the compression levels (e.g., sparsity) per-block or even per-layer in order to minimize accuracy loss, while guaranteeing a global compression threshold. Yet, current methods rely on estimating the “importance” of a given layer, implicitly assuming that layers contribute independently to the overall compression error. We begin from the motivating observation that this independence assumption does not generally hold for LLM compression: pruning a model further may even significantly recover performance. To address this, we propose EvoPress, a novel evolutionary framework for dynamic LLM compression. By formulating dynamic compression as a general optimization problem, EvoPress identifies optimal compression profiles in a highly efficient manner, and generalizes across diverse models and compression techniques. Via EvoPress, we achieve state-of-the-art performance for dynamic compression of Llama, Mistral, and Phi models, setting new benchmarks for structural pruning (block/layer dropping), unstructured sparsity, and quantization with dynamic bitwidths.

  • FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training

    OptimizationMachine learning theoryNatural language processing
    Philip Zmushko
    Aleksandr Beznosikov
    Martin Takáč
    Samuel Horváth
    ICML, 2025

    With the increase in the number of parameters in large language models, the training process increasingly demands larger volumes of GPU memory. A significant portion of this memory is typically consumed by the optimizer state. To overcome this challenge, recent approaches such as low-rank adaptation (LoRA), low-rank gradient projection (GaLore), and blockwise optimization (BAdam) have been proposed. However, in all these algorithms, the effective rank of the weight updates remains low-rank, which can lead to a substantial loss of information from the gradient. This loss can be critically important, especially during the pre-training stage. In this paper, we introduce FRUGAL (Full-Rank Updates with GrAdient spLitting), a new memory-efficient optimization framework. FRUGAL leverages gradient splitting to perform low-dimensional updates using advanced algorithms (such as Adam), while updates along the remaining directions are executed via state-free methods like SGD or signSGD. Our framework can be integrated with various low-rank update selection techniques, including GaLore and BAdam. We provide theoretical convergence guarantees for our framework when using SGDM for low-dimensional updates and SGD for state-free updates. Additionally, our method consistently outperforms concurrent approaches, achieving state-of-the-art results in pre-training and fine-tuning tasks while balancing memory efficiency and performance metrics.

Datasets

  • Shifts Dataset

    Distributional shiftUncertainty estimation Tabular dataMachine translationNatural language processing
    Andrey Malinin
    Neil Band
    Yarin Gal
    Mark J. F. Gales
    Alexander Ganshin
    German Chesnokov
    Alexey Noskov
    Andrey Ploskonosov
    Liudmila Prokhorenkova
    Ivan Provilkov
    Vatsal Raina
    Vyas Raina
    Denis Roginskiy
    Mariya Shmatova
    Panos Tigas
    Boris Yangel

    The Shifts Dataset contains curated and labeled examples of real, 'in-the-wild' distributional shifts across three large-scale tasks. Specifically, it contains tabular weather prediction, machine translation, and vehicle motion prediction tasks' data used in Shifts Challenge 2021. Dataset shift is ubiquitous in all of these tasks and modalities.

  • Text-to-Image dataset for billion-scale similarity search

    Nearest neighbor searchNatural language processing Computer vision
    Dmitry Baranchuk
    Artem Babenko

    Yandex Text-to-Image (T2I) dataset is collected to foster the research in billion-scale nearest neighbor search (NNS) when query distribution differs from the indexing one. In particular, this dataset addresses the cross-domain setting: a user specifies a textual query and requests the search engine to retrieve the most relevant images to the query. Notably, current large-scale indexing methods perform poorly in this setting. Therefore, novel highly-performant indexing solutions robust to out-of-domain queries are in high demand.

    The dataset represents a snapshot of the Yandex visual search engine and contains 1 billion 200-dimensional image embeddings for indexing. The image embeddings are produced by the Se-ResNext-101 model. The embeddings for textual queries are extracted by a variant of the DSSM model.

    Read more about the data format and how to download the dataset in the related post.