collaborators

7 papers

cs.LG2026

Stochastic Sparse Attention for Memory-Bound Inference

Kyle Lee, Corentin Delacour, Kevin Callahan-Coray +5

Autoregressive decoding becomes bandwidth-limited at long contexts, as generating each token requires reading all key and value vectors from KV cache. We present Stochastic A…

cs.ET2026

Probabilistic Computers for MIMO Detection: From Sparsification to 2D Parallel Tempering

M Mahmudul Hasan Sajeeb, Kevin Callahan-Coray, Corentin Delacour +3

Probabilistic computers built from p-bits offer a promising path for combinatorial optimization, but the dense connectivity required by real-world problems scales poorly in hardwar…

cs.ET2025

Lagrange Oscillatory Neural Networks for Constraint Satisfaction and Optimization

Corentin Delacour, Bram Haverkort, Filip Sabo +2

Physics-inspired computing paradigms are receiving renewed attention to enhance efficiency in compute-intensive tasks such as artificial intelligence and optimization. Similar to H…

cs.LG2025

IsingFormer: Augmenting Parallel Tempering With Learned Proposals

Saleh Bunaiyan, Corentin Delacour, Shuvro Chowdhury +2

Markov Chain Monte Carlo (MCMC) underlies both statistical physics and combinatorial optimization, but mixes slowly near critical points and in rough landscapes. Parallel Tempering…

cs.LG2025

Two-dimensional Parallel Tempering for Constrained Optimization

Corentin Delacour, M Mahmudul Hasan Sajeeb, Joao P. Hespanha +1

Sampling Boltzmann probability distributions plays a key role in machine learning and optimization, motivating the design of hardware accelerators such as Ising machines. While the…

cs.ET2025

Scalable Connectivity for Ising Machines: Dense to Sparse

M Mahmudul Hasan Sajeeb, Navid Anjum Aadit, Shuvro Chowdhury +7

In recent years, hardware implementations of Ising machines have emerged as a viable alternative to quantum computing for solving hard optimization problems among other application…