4 citations · 6 across the 16 of their papers we have counts for
17 papers
Scaled Companion Linearizations for Coefficientwise Backward Stability
Javier Pérez
A central goal in solving a polynomial eigenvalue problem is to compute eigenpairs that are exact for a nearby polynomial, with each coefficient perturbation bounded by a modest mu…
EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?
Zixuan Ke, Vaidehi Patil, Haizhou Shi +9
Modern LLM-based agents operate through a harness of tools, reusable skills, and specialist agents that shapes what they observe and what they can do. In practice, this harness con…
Counterparty Modeling is Not Strategy: The Limits of LLM Negotiators
Romain Cosentino, Sarath Shekkizhar, Adam Earle +1
Negotiation requires more than inferring what the other side wants: it requires using that information to make advantageous offers and counteroffers over multiple turns. We study w…
Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models
Sarath Shekkizhar, Romain Cosentino, Adam Earle
Standard LLM benchmarks evaluate the assistant turn: the model generates a response to an input, a verifier scores correctness, and the analysis ends. This paradigm leaves unmeasur…
Interaction Theater: A case of LLM Agents Interacting at Scale
Sarath Shekkizhar, Adam Earle
As multi-agent architectures and agent-to-agent protocols proliferate, a fundamental question arises: what actually happens when autonomous LLM agents interact at scale? We study t…
Echoing: Identity Failures when LLM Agents Talk to Each Other
Sarath Shekkizhar, Romain Cosentino, Adam Earle +1
As large language model (LLM) based agents interact autonomously with one another, a new class of failures emerges that cannot be predicted from single agent performance: behaviora…
Convergence dynamics of Agent-to-Agent Interactions with Misaligned objectives
Romain Cosentino, Sarath Shekkizhar, Adam Earle
We develop and analyze a theoretical framework for agent-to-agent interactions in a simplified in-context linear regression setting. In our model, each agent is instantiated as a s…
AGI Is Coming... Right After AI Learns to Play Wordle
Sarath Shekkizhar, Romain Cosentino
This paper investigates multimodal agents, in particular, OpenAI's Computer-User Agent (CUA), trained to control and complete tasks through a standard computer interface, similar t…
Out-of-Distribution Detection through Soft Clustering with Non-Negative Kernel Regression
Aryan Gulati, Xingjian Dong, Carlos Hurtado +3
As language models become more general purpose, increased attention needs to be paid to detecting out-of-distribution (OOD) instances, i.e., those not belonging to any of the distr…
Reasoning in Large Language Models: A Geometric Perspective
Romain Cosentino, Sarath Shekkizhar
The advancement of large language models (LLMs) for real-world applications hinges critically on enhancing their reasoning capabilities. In this work, we explore the reasoning abil…
Towards a geometric understanding of Spatio Temporal Graph Convolution Networks
Pratyusha Das, Sarath Shekkizhar, Antonio Ortega
Spatiotemporal graph convolutional networks (STGCNs) have emerged as a desirable model for skeleton-based human action recognition. Despite achieving state-of-the-art performance,…
Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation
Randall Balestriero, Romain Cosentino, Sarath Shekkizhar
Large Language Models (LLMs) drive current AI breakthroughs despite very little being known about their internal representations. In this work, we propose to shed the light on LLMs…
Study of Manifold Geometry using Multiscale Non-Negative Kernel Graphs
Carlos Hurtado, Sarath Shekkizhar, Javier Ruiz-Hidalgo +1
Modern machine learning systems are increasingly trained on large amounts of data embedded in high-dimensional spaces. Often this is done without analyzing the structure of the dat…
The Geometry of Self-supervised Learning Models and its Impact on Transfer Learning
Romain Cosentino, Sarath Shekkizhar, Mahdi Soltanolkotabi +2
Self-supervised learning (SSL) has emerged as a desirable paradigm in computer vision due to the inability of supervised models to learn representations that can generalize in doma…
Channel redundancy and overlap in convolutional neural networks with channel-wise NNK graphs
David Bonet, Antonio Ortega, Javier Ruiz-Hidalgo +1
Feature spaces in the deep layers of convolutional neural networks (CNNs) are often very high-dimensional and difficult to interpret. However, convolutional layers consist of multi…
NNK-Means: Data summarization using dictionary learning with non-negative kernel regression
Sarath Shekkizhar, Antonio Ortega
An increasing number of systems are being designed by gathering significant amounts of data and then optimizing the system parameters directly using the obtained data. Often this i…
Neighborhood and Graph Constructions using Non-Negative Kernel Regression
Sarath Shekkizhar, Antonio Ortega
Data-driven neighborhood definitions and graph constructions are often used in machine learning and signal processing applications. k-nearest neighbor~(kNN) and -neighborhood me…