Carlos E. Jimenez-Gomez

Vision Foundation Models in Agriculture: Toward Domain-Specific Adaptation for Weed Herbicide Trials Assessment

Leire Benito-Del-Valle, Artzai Picón, Daniel Múgica, Javier Romero et autres

Herbicide field trials require accurate identification of plant species and assessment of herbicide-induced damage across diverse environments. While general-purpose vision foundation models have shown promising results in complex visual domains, their performance can be limited in agriculture, where fine-grained distinctions between species …

CodeClash: Benchmarking Goal-Oriented Software Engineering

John Jeongseok Yang, K. Lieret, Joyce Yang, Carlos E. Jimenez-Gomez et autres

Current benchmarks for coding evaluate language models (LMs) on concrete, well-specified tasks such as fixing specific bugs or writing targeted tests. However, human programmers do not spend all day incessantly addressing isolated tasks. Instead, real-world software development is grounded in the pursuit …

ACM TechBrief: Government Digital Transformation

Carlos E. Jimenez-Gomez, A.B Shrinivass, Simson Garfinkel

IMPersona: Evaluating Individual Level LM Impersonation

Quan Shi, Carlos E. Jimenez-Gomez, Stephen Dong, Brian Seo et autres

As language models achieve increasingly human-like capabilities in conversational text generation, a critical question emerges: to what extent can these systems simulate the characteristics of specific individuals? To evaluate this, we introduce IMPersona, a framework for evaluating LMs at impersonating specific individuals' …

Revisiting open justice in the digital age

Carlos E. Jimenez-Gomez, Sandra Elena, Peter Sharp Vargas

Taxonomic hierarchical loss function for enhanced crop and weed phenotyping in multi-task semantic segmentation

Artzai Picón, Daniel Múgica, Itziar Eguskiza, Arantza Bereciartua et autres

Herbicide research and development necessitate specific trials to monitor the effects of various herbicide formulations, quantities, and protocols on different plant species and growth stages. These trials are necessary to ensure the safety and efficacy of the developed products. Currently, these tests …

Vision Foundation Models in Agriculture: Toward Domain-Specific Adaptation for Weed Herbicide Trials Assessment

Leire Benito-Del-Valle, Artzai Picón, Daniel Múgica, Javier Romero et autres

es, us, de (code pays fourni par la source)

When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration

Quan Shi, Carlos E. Jimenez-Gomez, Shunyu Yao, Nick Haber et autres

Recent advancements in AI reasoning have driven substantial improvements across diverse tasks. A critical open question is whether these improvements also yields better knowledge transfer: the ability of models to communicate reasoning in ways humans can understand, apply, and learn from. To …

cn, us (code pays fourni par la source)

SWE-smith: Scaling Data for Software Engineering Agents

John Jeongseok Yang, K. Lieret, Carlos E. Jimenez-Gomez, Alexander Wettig et autres

Despite recent progress in Language Models (LMs) for software engineering, collecting training data remains a significant pain point. Existing datasets are small, with at most 1,000s of training instances from 11 or fewer GitHub repositories. The procedures to curate such datasets are …

us (code pays fourni par la source)

First Detection of Oropouche Virus in Culicoides insignis in the Ucayali Region, Peru: Evidence of a Possible New Vector

Edwin Requena-Zúñiga, Miriam Palomino-Salcedo, María García-Mendoza, Maribel Dana Figueroa-Romero et autres

Abstract This report details the first detection of the Oropouche virus (OROV) in Culicoides insignis in the Ucayali region (Peruvian Amazon) during an outbreak study in 2024. Captures conducted in peri-urban and rural areas showed that C. insignis accounted for 96.7% of …

pe (code pays fourni par la source)

SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?

John Jeongseok Yang, Carlos E. Jimenez-Gomez, Alex Zhang, K. Lieret et autres

Autonomous systems for software engineering are now capable of fixing bugs and developing features. These systems are commonly evaluated on SWE-bench (Jimenez et al., 2024a), which assesses their ability to solve software issues from GitHub repositories. However, SWE-bench uses only Python repositories, …

EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities

Talor Abramovich, Meet Udeshi, Minghao Shao, K. Lieret et autres

Although language model (LM) agents have demonstrated increased performance in multiple domains, including coding and web-browsing, their success in cybersecurity has been limited. We present EnIGMA, an LM agent for autonomously solving Capture The Flag (CTF) challenges. We introduce new tools and …