Walsh-Hadamard Transform

Follow this topic Ask about this topic

Latest papers

11 papers0 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

H-DDCM: Hadamard Codebooks for Fast Generative Image and Video Compression
Oct 13, 2026Or Ronai, Vladimir Kulikov, Tomer MichaeliWalsh-Hadamard Transform Generative Image Compression
Technion – Israel Institute of Technology
Influence-Inspired Spectral Rotations for Extreme Low-Bit LLM Quantization
May 24, 2026Gorgi PavlovLLM Quantization Rotation-Based Quantization
Lehigh University
Provable Quantization with Randomized Hadamard Transform
May 13, 2026Ying Feng, Piotr Indyk, Michael Kapralov +2Vector Quantization Randomized Sketching
Pretraining large language models with MXFP4 on Native FP4 Hardware
May 11, 2026Musa Cim, Poovaiah Palangappa, Miro Hodak +3Language Model Pretraining LLM Quantization
1The Pennsylvania State University · 2Advanced Micro Devices, Inc.
Same Brain, Different Prediction: How Preprocessing Choices Undermine EEG Decoding Reliability
May 8, 2026Dengzhe Hou, Zihao Wu, Lingyu Jiang +3Uncertainty Quantification EEG Decoding
Tohoku University · University of Georgia · Texas A&M University +1
Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven
May 7, 2026Ran Ben-Basat, William Kuszmaul, Michael Mitzenmacher +2Quantization Rotation-Based Quantization
UCL and Broadcom · Carnegie Mellon University · Harvard University +2
The Banach-Butterfly Invariant: Influence-Adaptive Walsh Geometry for Ternary Polynomial Threshold Functions
May 2, 2026Gorgi PavlovBoolean Function Learning Walsh-Hadamard Transform
Lehigh University · Johnson and Johnson
Approximating Uniform Random Rotations by Two-Stage Structured Hadamard Rotations in High Dimensions
Apr 25, 2026Tomer Zilca, Gal MendelsonWalsh-Hadamard Transform
Faculty of Data and Decision Sciences, Technion – Israel Institute of Technology, Haifa, Israel · Edward P. Fitts Department of Industrial and Systems Engineering, North Carolina State University, Raleigh, NC, USA
AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation
Apr 2, 2026Seonggon Kim, Alireza Khodamoradi, Pranathi Vasireddy +2Walsh-Hadamard Transform Low-Precision Training
Advanced Micro Devices, Inc. · POSTECH
Rethinking Attention Output Projection: Structured Hadamard Transforms for Efficient Transformers
Mar 9, 2026Shubham Aggarwal, Lokendra KumarWalsh-Hadamard Transform Multi-Head Attention
Toward Generalizable Deep Learning Based Peatland Fire Detection via Walsh Hadamard Transform and Domain Adaptation
Mar 2, 2026Emadeldeen Hamdan, Ahmad Faiz Tharima, Mohd Zahirasri Mohd Tohir +4Efficient Neural Network Inference Walsh-Hadamard Transform
Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, IL, USA · Fire and Rescue Department of Malaysia, Malaysia · Dept. of Chemical and Environmental Engineering, Faculty of Engineering, Universiti Putra Malaysia, Malaysia. +2

Oct 13, 2026J/K move · Enter open · S save

H-DDCM: Hadamard Codebooks for Fast Generative Image and Video Compression

Or Ronai, Vladimir Kulikov, Tomer Michaeli

Technion – Israel Institute of Technology

Walsh-Hadamard Transform Generative Image Compression Generative Video Compression

Open paper AskPDF arXiv

Training-free diffusion-based compression methods repurpose the generative priors of a diffusion or a flow model to compress data without retraining them as task-specific codecs. Recent codebook-based approaches such as Turbo-DDCM achieve strong perceptual quality at ultra-low bitrates, but their reliance on dense Gaussian codebooks remains costly in both memory and computation, and scales poorly with the large latent dimensions of modern image and video generators. Their combinatorial bitstream encoding further becomes computationally heavy at this scale. We introduce H-DDCM, a scalable generative compression framework that replaces Gaussian codebooks with implicit randomized Hadamard dictionaries. The fast Walsh-Hadamard transform allows for implicitly synthesizing full-dimensional dictionaries with

O(d \log d)

compute for projection and reconstruction and

O(d)

memory, without materializing the full-dimensional dictionary. We further introduce an efficient table-free lexicographic coding scheme that makes combinatorial encoding practical at larger dimensions. Beyond images, we adapt the framework to an autoregressive video flow model and develop a streaming compression scheme that periodically re-encodes recently reconstructed frames into a fresh KV-cache prefix, preserving temporal context across segments at no additional transmitted bits. This enables long-form, close to real-time generative video compression on a single GPU. Across image and video benchmarks, H-DDCM achieves competitive rate-distortion-perception performance while substantially reducing the memory and computational overhead of codebook-based training-free generative compression.