Quantizer

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 167% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 39

All topics

XOR-Trellis: Ultra-Low-Complexity Dequantization and Curvature-Aware Hadamard-Free LLM Quantization
Sep 30, 2026Xiaofan Que, Nir Elkayam, Spandan Pyakurel +2Large Language Model Quantization Quantizer
Arm, Inc. · Rochester Institute of Technology
Exact Factorisation and Fast Computation of Invertible Constant-Q Transforms
Sep 24, 2026Facundo Franchino, Eloi Moliner, Vesa VälimäkiFourier Quantizer
Massachusetts Institute of Technology, Cambridge, MA, USA · Acoustics Lab, Dept. of Information and Communications Eng., Aalto University, Espoo, Finland
Disaggregated Quantization: Specializing LLM Prefill and Decode
Sep 22, 2026Andrei Panferov, Maximilian Kleinegger, Sweta Priyadarshi +2Large Language Model Quantization Quantizer
NVIDIA · ISTA
RGSQ: Riemannian Geometry-Sensitive Quantization for Large Vision-Language Models
Sep 21, 2026Zhiping Wu, Dongdong Ren, Yangchengyu Zhou +4Large Language Model Quantization Post-Training Quantization
State Key Laboratory for Novel Software Technology and the School of Intelligence Science and Technology, Nanjing University, Suzhou Campus, Suzhou 215163, China
What Makes a Good Medical Image Tokenizer? Rethinking Reconstruction and Generation in Medical Image Tokenization
Sep 21, 2026Niklas Bubeck, Yundi Zhang, Vasiliki Sideri-Lampretsa +4Medical Image Generation Visual Tokenizers
School of Computation, Information and Technology, Technical University of Munich, Germany · Munich Center for Machine Learning, Technical University of Munich, Germany · School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Germany +3
D-Quant: Driftable Entropy Coding for KV Cache Quantization
Sep 17, 2026Yi Su, Hong Liu, Guanghua Yu +1Key-Value Cache Quantization Key-Value Cache
Tencent
A Calibrated Instrument for Measuring How Inference Optimizations Affect Output Quality
Sep 16, 2026Jerry KaplanLLM Inference Optimization Quantizer
Adjunct Lecturer, Computer Science and Masters in International Policy, Stanford University
KBBQ: A Predictive Noise Law and the Limits of Spectrum Flattening in FP4 Quantization
Sep 8, 2026Lexington Whalen, Yuki Ito, Ryo SakamotoQuantized Quantizer
1SB Intuitions, Tokyo, Japan.
From Ordered Bernoulli Levels to Critical-Line Geometry: Integer Quantization, Bernoulli Residual Phase, and Prime-Power Spectra
Sep 3, 2026Y. Kenan YılmazQuantizer Symmetry
PACodec: A Low-bitrate Neural Speech Codec with Parallel Additive Vector Quantization
Sep 3, 2026Fei Liu, Yang Ai, Xiao-Hang Jiang +1Neural Speech Codecs Residual Vector Quantization
National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China
Language-Conditional Dequantization: Recovering What Quantization Steals from Non-English Languages
Aug 12, 2026Nirmal ThomasLarge Language Model Quantization Quantized
Prathama International
Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving
Aug 9, 2026Matteo GrellaQuantizer
Crisis24
VibeVoice-ASR-BitNet Technical Report
Jul 23, 2026Songchen Xu, Ting Song, Shaohan Huang +10Quantizer
Shanghai Jiao Tong University · Microsoft Research · University of Chinese Academy of Sciences +1
QuantiBias: Benchmarking Quantization-Induced Bias in LLMs
Jul 23, 2026Emilio FerraraLarge Language Model Bias Large Language Model Quantization
Thomas Lord Department of Computer Science University of Southern California
Reliability Scaling Laws for Quantized Large Language Models
Jul 12, 2026Sirine Ayadi, Sándor Daróczi, Stephan Günnemann +1Large Language Model Quantization Large Language Model Reliability
School of Computation, Information and Technology, Technical University of Munich Munich Data Science Institute · Pruna AI
Fractal KV-Cache Archives: Lossless Symbolic Storage with In-Place Retrieval for Long-Context LLM Inference
Jul 8, 2026Vladimir GusevKey-Value Cache LLM Inference Optimization
Independent Researcher
OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
Jul 2, 2026Donghyun Lee, Jitesh Chavan, Duy Nguyen +5Diffusion Transformers Quantizer
Cantina Labs · University of Southern California · *Work done during an internship at Cantina Labs. +1
GEAR: Guided End-to-End AutoRegression for Image Synthesis
Jun 30, 2026Bin Lin, Zheyuan Liu, Chenguo Lin +8Autoregressive Image Generation Generative Models
Peking University · Tencent Hunyuan
Techniques for Peak Memory Reduction for LoRA Fine-tuning of LLMs on Edge Devices
Jun 17, 2026Hassan Dbouk, Matthias Reisser, Prathamesh Mandke +2Large Language Model Fine-Tuning Model Fine-Tuning
Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc. · work done while at Qualcomm
Signed Symmetric Quantization for Few-Bit Integers
Jun 12, 2026Ian Colbert, Eashan Dash, Pablo Monteagudo-Lago +5Quantizer Information Asymmetry
AMD
Realizing Native INT8 Compute for Diffusion Transformers on Consumer GPUs: A Fused INT8 GEMM Kernel for Ideogram 4.0
Jun 12, 2026Ali Asaria, Tony Salomone, Deep GandhiDiffusion Transformers Matched Fp16 Intermediate
Transformer Lab
TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization
Jun 11, 2026Zhixiong Zhao, Zukang Xu, Zhixuan Chen +3Large Language Model Quantization Post-Training Quantization
Houmo AI, China · 2Southeast University, Nanjing, China
Optimal Post-Training Quantization Scales and Where to Find Them
Jun 9, 2026Juan Amboage, Pablo Monteagudo-Lago, Ian Colbert +2Post-Training Quantization Quantizer
AMD
Minimum Distortion Quantization with Specified Output Distribution
Jun 9, 2026Aolin XuRate-Distortion Theory Quantizer
Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin
Jun 8, 2026Hanyang Li, Jianhao Ma, Ying CuiQuantization-Aware Training Post-Training Quantization
Department of IEOR, University of California, Berkeley · Department of Statistics and Data Science, University of Pennsylvania
LiftQuant: Continuous Bit-Width LLM via Dimensional Lifting and Projection
Jun 2, 2026Liulu He, XuanAng Liu, Juntao Liu +8Large Language Model Quantization Quantizer
Nanjing University, China · China Mobile Research Institute, China · Xiaomi Corporation, China +2
Perplexity Can Miss SAE Feature Damage Under Quantization
Jun 2, 2026Evan DuanQuantizer Model Activations
University of Michigan
Enhancing Human-Likeness in Reinforcement Learning Agents via Hierarchical Macro Action Quantization
May 29, 2026M. Shaheer Luqman, Usman Nizamani, Fawad Javed Fateh +4Hierarchical Reinforcement Learning Offline Reinforcement Learning
Retrocausal, Inc., Redmond, WA 98052, USA
ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention
May 21, 2026Joe SharrattBlock Sparse Flash Attention Efficient Long-Context Inference
Q-ARVD: Quantizing Autoregressive Video Diffusion Models
May 20, 2026Siao Tang, Xinyin Ma, Gongfan Fang +2Autoregressive Video Diffusion Models Quantizer
National University of Singapore · The Hong Kong Polytechnic University
Q-LocalAdam: Memory-Efficient Client-Side Adaptive Optimization for Edge Federated Learning
May 17, 2026Vedant Waykole, Haroon R. LoneFederated Learning Resource-Constrained Edge Devices
IISER Bhopal · India
Covariance Structure and Coordinate Heterogeneity Govern Binary Quantization of Contrastive Embeddings
May 17, 2026Wenxuan XiaoQuantizer Covariance
Changsha University
Asymmetric Generative Recommendation via Multi-Expert Projection and Multi-Faceted Hierarchical Quantization
May 14, 2026Bin Huang, Xin Wang, Junwei Pan +6Recommendation Text Embeddings
DCST, Tsinghua University Beijing, China · DCST, BNRist, Tsinghua University Beijing, China · Tencent Shenzhen, China
Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference
May 13, 2026Lingchao Zheng, Yuwei Fan, Jun Li +5Quantizer Matched Fp16 Intermediate
Huawei
WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference Optimization
May 4, 2026Wei Tao, Xiaoyang Qu, Peiqiang Wang +4Key-Value Cache Quantization Quantizer
Huazhong University of Science and Technology, Wuhan, Hubei, China · Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, Guangdong, China · Tsinghua University, Shenzhen International Graduate School, Shenzhen, Guangdong, China
Quantamination: Dynamic Quantization Leaks Your Data Across the Batch
Apr 29, 2026Hanna Foerster, Ilia Shumailov, Cheng Zhang +3Quantizer Data Leakage
University of Cambridge · 2AI Sequrity Company · 3Google DeepMind
When Flat Minima Fail: Characterizing INT4 Quantization Collapse After FP32 Convergence
Apr 16, 2026Marcus ArmstrongPost-Training Quantization Quantizer
Department of Computer Science University of Houston Houston, TX 77004
Attack-Dependent Robustness of Neural Audio Codecs for Adversarial ASR
Mar 10, 2026Jordan Prescott, Thanathai Lertpetchpun, Shrikanth NarayananNeural Audio Codecs Automatic Speech Recognition
Signal Analysis and Interpretation Laboratory, University of Southern California, USA
Pushing Toward the Simplex Vertices: A Simple Remedy for Code Collapse in Smoothed Vector Quantization
Sep 26, 2025Takashi MoritaResidual Vector Quantization Quantizer
Academy of Emerging Sciences, Chubu University · Institute for Advanced Research, Nagoya University

Sep 30, 2026, cs.LGJ/K move · Enter open · S save

XOR-Trellis: Ultra-Low-Complexity Dequantization and Curvature-Aware Hadamard-Free LLM Quantization

Xiaofan Que, Nir Elkayam, Spandan Pyakurel, Shuokai Pan+1

Arm, Inc. · Rochester Institute of Technology

Large Language Model Quantization Quantizer Deterministic Reconstruction

Open paper AskPDF arXiv

Trellis-coded quantization enables high-dimensional compression of large language model (LLM) weights at ultra-low bit widths without the exponentially large codebooks required by conventional vector quantization. Practical deployment, however, presents two challenges: reconstructing compressed weights at sufficient parallel throughput to avoid making dequantization an inference bottleneck, and maintaining quantization accuracy without costly incoherence transformations. We address these challenges with two complementary techniques. First, we introduce an ultra-low-complexity trellis dequantizer that uses a structured, hardware-efficient state-to-value mapping while preserving diverse reconstruction choices for trellis search. Second, we reformulate discrete trellis path optimization with a curvature-aware objective that reflects model sensitivity directly in the original coordinate space. Together, these techniques enable high-quality ultra-low-bit trellis quantization with inexpensive, highly parallel runtime reconstruction and without relying on Hadamard-based incoherence processing.

Momentum

Related topics

Latest papers 39