works on

From the 1 of 11 linked papers with an AI index.

collaborators

11 papers

cs.LG2026

Nonlinear Laplacians Improve Signed-Directed Graph Learning

Ali Parviz, Yuichi Yoshida

While signed-directed graphs have been studied using linear Laplacians in the design of graph neural networks, relatively little research has focused on developing non-linear Lapla…

cs.LG2026

Reassessing Muon for Matrix Factorization

Ali Parviz, Gal Mishne, Alex Cloninger

The paper investigates the Muon optimizer on a simple low‑rank matrix factorization task, comparing it to carefully tuned AdamW baselines, and finds that Muon does not consistently…

cs.AI2026

Probabilistic Tiny Recursive Model

Amin Sghaier, Ali Parviz, Alexia Jolicoeur-Martineau

Tiny Recursive Models (TRM) solve complex reasoning tasks with a fraction of the parameters of modern large language models (LLMs) by iteratively refining a latent state and final…

cs.LG2026

GraphBench: Next-generation graph learning benchmarking

Timo Stoll, Chendi Qian, Ben Finkelshtein +16

Machine learning on graphs has made substantial progress across domains such as molecular property prediction and chip design. Yet benchmarking practices remain fragmented, often r…

cs.AI2026

Local Inconsistency Resolution: The Interplay between Attention and Control in Probabilistic Models

Oliver E. Richardson, Mandana Samiei, Mehran Shakerinava +4

We present a generic algorithm for learning and approximate inference with an intuitive epistemic interpretation: iteratively focus on a subset of the model and resolve inconsisten…

cs.AI2026

REAM: Merging Improves Pruning of Experts in LLMs

Saurav Jha, Maryam Hashemzadeh, Ali Saheb Pasand +3

Mixture-of-Experts (MoE) large language models (LLMs) are among the top-performing architectures. The largest models, often with hundreds of billions of parameters, pose significan…