arXiv AI June 10, 2026 By Patrik Czak\'o, G\'abor Kert\'esz, S\'andor Sz\'en\'asi

Trainable Smooth-Rotation Transforms with Learned Channel Scales for LLM Quantization

arXiv:2606. 09927v1 Announce Type: cross Abstract: Post-training quantization (PTQ) is one of the most practical ways to reduce the serving cost of Large Language Models (LLMs), but activation quantization remains difficult because outlier-dominated channels lead to large quantization errors.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 10

Optimal Post-Training Quantization Scales and Where to Find Them

arXiv:2606. 10890v1 Announce Type: cross Abstract: Post-training quantization (PTQ) compresses large language models by mapping weights to low-bit representations.

By Juan Amboage, Pablo Monteagudo-Lago, Ian Colbert, Giuseppe Franco, Nicholas Fraser

llms efficiency

arXiv AI

Jun 15

Quantized Evolution Strategies: High-precision Fine-tuning of Quantized LLMs at Low-precision Cost

arXiv:2602. 03120v2 Announce Type: replace-cross Abstract: Post-Training Quantization (PTQ) is essential for deploying Large Language Models (LLMs) on memory-constrained devices, yet it renders models static and difficult to fine-tune.

By Yinggan Xu, Kajetan Schweighofer, Risto Miikkulainen, Xin Qiu

llms reinforcement-learning fine-tuning efficiency benchmarks

arXiv AI

Jun 9

ScaleSweep: Accurate NVFP4 Post-Training Quantization of LLMs via Block Scale Initialization

arXiv:2606. 07618v1 Announce Type: cross Abstract: NVFP4 is a recently introduced hardware-supported FP4 format that improves the fidelity of 4-bit quantization through fine-grained block scales.

By Li Lin, Xiaojun Wan

llms efficiency

Hugging Face Trending Papers

Jun 11

TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization

Large language models (LLMs) exhibit exceptional general language processing capabilities, but their memory and compute costs hinder deployment. Ternarization has emerged as a promising compression technique, offering significant reductions in model size and inference complexity.

llms efficiency

arXiv Machine Learning

Aug 10

{\Omega}-QVLA: Robust Quantization for Vision-Language-Action Models via Composite Rotation and Per-step Scaling

arXiv:2605. 28803v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models unify perception, reasoning, and control within a single policy, yet their multi-billion-parameter backbones and diffusion-based action heads make on-device deployment prohibitively expensive.

By Xinyu Wang, Mingze Li, Sicheng Lyu, Dongxiu Liu, Kaicheng Yang, Ziyu Zhao, Yufei Cui, Xiao-Wen Chang, Peng Lu

llms diffusion robotics efficiency multimodal

arXiv Machine Learning

Jul 24

KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers

arXiv:2607. 21446v1 Announce Type: new Abstract: Post-training quantization (PTQ) of diffusion transformers (DiTs) to W4A4 severely degrades output quality, because activations entering each linear layer contain outliers that 4-bit formats cannot represent.

By Yann Bouquet, Alireza Khodamoradi, Kristof Denolf, Mathieu Salzmann

llms diffusion efficiency

Related stories

Optimal Post-Training Quantization Scales and Where to Find Them

Quantized Evolution Strategies: High-precision Fine-tuning of Quantized LLMs at Low-precision Cost

ScaleSweep: Accurate NVFP4 Post-Training Quantization of LLMs via Block Scale Initialization

TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization

{\Omega}-QVLA: Robust Quantization for Vision-Language-Action Models via Composite Rotation and Per-step Scaling

KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers