25 citations · 68 across the 11 of their papers we have counts for
13 papers
BEM: Learning Bregman Divergences for Concept Erasure in Flow Matching Models
Mohamed-Hicham Leghettas, Markus Püschel
Concept erasure removes harmful, private, or copyrighted concepts from text-to-image models while preserving their other abilities. Leading models such as FLUX and Stable Diffusion…
Fast Entropy Decoding for Sparse MVM on GPUs
Emil Schätzle, Tommaso Pegolotti, Markus Püschel
We present a novel, practical approach to speed up sparse matrix-vector multiplication (SpMVM) on GPUs. The novel key idea is to apply lossless entropy coding to further compress t…
QIGen: Generating Efficient Kernels for Quantized Inference on Large Language Models
Tommaso Pegolotti, Elias Frantar, Dan Alistarh +1
We present ongoing work on a new automatic code generation approach for supporting quantized generative inference on LLMs such as LLaMA or OPT on off-the-shelf CPUs. Our approach i…
Fast Möbius and Zeta Transforms
Tommaso Pegolotti, Bastian Seifert, Markus Püschel
Möbius inversion of functions on partially ordered sets (posets) is a classical tool in combinatorics. For finite posets it consists of two, mutually inverse, linear…
Finite-Time In-Network Computation of Linear Transforms
Soummya Kar, Markus Püschel, José M. F. Moura
This paper focuses on finite-time in-network computation of linear transforms of distributed graph data. Finite-time transform computation problems are of interest in graph-based c…
Scaling Polyhedral Neural Network Verification on GPUs
Christoph Müller, François Serre, Gagandeep Singh +2
Certifying the robustness of neural networks against adversarial attacks is essential to their reliable adoption in safety-critical systems such as autonomous driving and medical d…
Digraph Signal Processing with Generalized Boundary Conditions
Bastian Seifert, Markus Püschel
Signal processing on directed graphs (digraphs) is problematic, since the graph shift, and thus associated filters, are in general not diagonalizable. Furthermore, the Fourier tran…
Discrete Signal Processing with Set Functions
Markus Püschel, Chris Wendler
Set functions are functions (or signals) indexed by the powerset (set of all subsets) of a finite set N. They are fundamental and ubiquitous in many application domains and have be…
Powerset Convolutional Neural Networks
Chris Wendler, Dan Alistarh, Markus Püschel
We present a novel class of convolutional neural networks (CNNs) for set functions, i.e., data indexed with the powerset of a finite set. The convolutions are derived as linear, sh…
Program Generation for Linear Algebra Using Multiple Layers of DSLs
Daniele G. Spampinato, Diego Fabregat-Traver, Markus Püschel +1
Numerical software in computational science and engineering often relies on highly-optimized building blocks from libraries such as BLAS and LAPACK, and while such libraries provid…
On Linear Learning with Manycore Processors
Eliza Wszola, Celestine Mendler-Dünner, Martin Jaggi +1
A new generation of manycore processors is on the rise that offers dozens and more cores on a chip and, in a sense, fuses host processor and accelerator. In this paper we target th…
Program Generation for Small-Scale Linear Algebra Applications
Daniele G. Spampinato, Diego Fabregat-Traver, Paolo Bientinesi +1
We present SLinGen, a program generation system for linear algebra. The input to SLinGen is an application expressed mathematically in a linear-algebra-inspired language (LA) that…
A Lower-Upper-Lower Block Triangular Decomposition with Minimal Off-Diagonal Ranks
François Serre, Markus Püschel
We propose a novel factorization of a non-singular matrix , viewed as a -blocked matrix. The factorization decomposes into a product of three matrices that are lo…