93 citations · 122 across the 6 of their papers we have counts for
7 papers
Salesforce Koa: An Enterprise Language Model for Agentic Tool Use
Zixiang Chen, Sufeng Niu, Yingchi Liu +23
We present Salesforce Koa, an enterprise language model built by post-training the open-weight Nemotron-3-Super-120B foundation model with reinforcement learning using Group Relati…
seqBench: A Tunable Benchmark to Quantify Sequential Reasoning Limits of LLMs
Mohammad Ramezanali, Mo Vazifeh, Paolo Santi
We introduce seqBench, a parametrized benchmark for probing sequential reasoning limits in Large Language Models (LLMs) through precise, multi-dimensional control over several key…
FNetAR: Mixing Tokens with Autoregressive Fourier Transforms
Tim Lou, Michael Park, Mohammad Ramezanali +1
In this note we examine the autoregressive generalization of the FNet algorithm, in which self-attention layers from the standard Transformer architecture are substituted with a tr…
Critical Behavior and Universality Classes for an Algorithmic Phase Transition in Sparse Reconstruction
Mohammad Ramezanali, Partha P. Mitra, Anirvan M. Sengupta
Recovery of an -dimensional, -sparse solution from an -dimensional vector of measurements for multivariate linear regression can be accomplished…
The cavity method for analysis of large-scale penalized regression
Mohammad Ramezanali, Partha P. Mitra, Anirvan M. Sengupta
Penalized regression methods aim to retrieve reliable predictors among a large set of putative ones from a limited amount of measurements. In particular, penalized regression with…
Finite-temperature Screening and the Specific Heat of Doped Graphene Sheets
M. R. Ramezanali, M. M. Vazifeh, Reza Asgari +2
At low energies, electrons in doped graphene sheets are described by a massless Dirac fermion Hamiltonian. In this work we present a semi-analytical expression for the dynamical de…