activity
20182025
most citedSpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression

26 citations · 27 across the 7 of their papers we have counts for

collaborators

14 papers

cs.LG2025

WUSH: Near-Optimal Adaptive Transforms for LLM Quantization

Jiale Chen, Vage Egiazarian, Roberto L. Castro +2

Quantizing LLM weights and activations is a standard approach for efficient deployment, but a few extreme outliers can stretch the dynamic range and amplify low-bit quantization er…

cs.LG2025

Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization

Vage Egiazarian, Roberto L. Castro, Denis Kuznedelev +8

The recent hardware-accelerated microscaling 4-bit floating-point formats such as MXFP4 and NVFP4, supported on NVIDIA and AMD GPUs, promise to revolutionize large language model (…

cs.LG2025

Unified Scaling Laws for Compressed Representations

Andrei Panferov, Alexandra Volkova, Ionut-Vlad Modoranu +3

Scaling laws have shaped recent advances in machine learning by enabling predictable scaling of model performance based on model size, computation, and data volume. Concurrently, t…

cs.CL2025

AutoJudge: Judge Decoding Without Manual Annotation

Roman Garipov, Fedor Velikonivtsev, Ivan Ermakov +3

We introduce AutoJudge, a method that accelerates large language model (LLM) inference with task-specific lossy speculative decoding. Instead of matching the original model output…

cs.LG2025

Hogwild! Inference: Parallel LLM Generation via Concurrent Attention

Gleb Rodionov, Roman Garipov, Alina Shutova +6

Large Language Models (LLMs) have demonstrated the ability to tackle increasingly complex tasks through advanced reasoning, long-form content generation, and tool use. Solving thes…

cs.LG2025

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

Alina Shutova, Vladimir Malinovskii, Vage Egiazarian +5

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 computa…