activity
20242026
collaborators

6 papers

cs.LG2026

CMT-Benchmark: A Benchmark for Condensed Matter Theory Built by Expert Researchers

Haining Pan, James V. Roggeveen, Erez Berg +16

Large language models (LLMs) have shown remarkable progress in coding and math problem-solving, but evaluation on advanced research-level problems in hard sciences remains scarce.…

q-bio.NC2026

Short-term plasticity recalls forgotten memories through a trampoline mechanism

Martina Del Gaudio, Federico Ghimenti, Surya Ganguli

We analyze continuous Hopfield associative memories augmented by additional, rapid short-term associative synaptic plasticity. Through the cavity method, we determine the boundary…

cs.LG2026

Contrastive Concept-Tree Search for LLM-Assisted Algorithm Discovery

Timothee Leleu, Sudeera Gunathilaka, Federico Ghimenti +1

Large language Model (LLM)-assisted algorithm discovery is an iterative, black-box optimization process over programs to approximatively solve a target task, where an LLM proposes…

cond-mat.dis-nn2026

Reshaping Global Loop Structure to Accelerate Local Optimization by Smoothing Rugged Landscapes

Timothee Leleu, Sam Reifenstein, Atsushi Yamamura +1

Probabilistic graphical models with frustration exhibit rugged energy landscapes that trap iterative optimization dynamics. These landscapes are shaped not only by local interactio…

cond-mat.dis-nn2025

The geometry and dynamics of annealed optimization in the coherent Ising machine with hidden and planted solutions

Federico Ghimenti, Adithya Sriram, Atsushi Yamamura +2

The coherent Ising machine (CIM) is a nonconventional hardware architecture for finding approximate solutions to large-scale combinatorial optimization problems. It operates by ann…

cs.CR2024

Fooling LLM graders into giving better grades through neural activity guided adversarial prompting

Atsushi Yamamura, Surya Ganguli

The deployment of artificial intelligence (AI) in critical decision-making and evaluation processes raises concerns about inherent biases that malicious actors could exploit to dis…