Papers
Research papers from arXiv and related sources
El Agente Gráfico: Structured Execution Graphs for Scientific Agents
Large language models (LLMs) are increasingly used to automate scientific workflows, yet their integration with heterogeneous computational tools remains ad hoc and fragile. Current agentic approac...
Jiaru Bai, Abdulrahman Aldossary, Thomas Swanick, Marcel Müller, Yeonghun Kang, Zijian Zhang, Jin...
The Strategic Gap: How AI-Driven Timing and Complexity Shape Investor Trust in the Age of Digital Agents
Traditional models of market efficiency assume that equity prices incorporate information based on content alone, often neglecting the structural influence of reporting timing and cadence. This stu...
Krishna Neupane
HookLens: Visual Analytics for Understanding React Hooks Structures
Maintaining and refactoring React web applications is challenging, as React code often becomes complex due to its core API called Hooks. For example, Hooks often lead developers to create complex d...
Suyeon Hwang, Minkyu Kweon, Jeongmin Rhee, Soohyun Lee, Seokhyeon Park, Seokweon Jung, Hyeon Jeon...
Machine Learning Based Prediction of Surgical Outcomes in Chronic Rhinosinusitis from Clinical Data
Artificial intelligence (AI) has increasingly transformed medical prognostics by enabling rapid and accurate analysis across imaging and pathology. However, the investigation of machine learning pr...
Sayeed Shafayet Chowdhury, Karen D'Souza, V. Siva Kakumani, Snehasis Mukhopadhyay, Shiaofen Fang,...
Automated LLM-Based Accessibility Remediation: From Conventional Websites to Angular Single-Page Applications
Web accessibility remains an unresolved issue for a large part of the web content. There are many tools to detect errors automatically, but fixing those issues is still mostly a manual, slow, and c...
Carla Fernández-Navarro, Francisco Chicano
El Agente Sólido: A New Age(nt) for Solid State Simulations
Quantum chemistry calculations are a key component of the materials discovery process. The results from first-principles explorations enable the prediction of material properties prior to experimen...
Sai Govind Hari Kumar, Yunheng Zou, Andrew Wang, Jesús Valdés-Hernández, Tsz Wai Ko, Nathan Yue, ...
Understanding the Fine-Grained Knowledge Capabilities of Vision-Language Models
Vision-language models (VLMs) have made substantial progress across a wide range of visual question answering benchmarks, spanning visual reasoning, document understanding, and multimodal dialogue....
Dhruba Ghosh, Yuhui Zhang, Ludwig Schmidt
Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models
With recent advancements in video backbone architectures, combined with the remarkable achievements of large language models (LLMs), the analysis of long-form videos spanning tens of minutes has be...
Yuxiao Chen, Jue Wang, Zhikang Zhang, Jingru Yi, Xu Zhang, Yang Zou, Zhaowei Cai, Jianbo Yuan, Xi...
ADAPT: Hybrid Prompt Optimization for LLM Feature Visualization
Understanding what features are encoded by learned directions in LLM activation space requires identifying inputs that strongly activate them. Feature visualization, which optimizes inputs to maxim...
João N. Cardoso, Arlindo L. Oliveira, Bruno Martins
Exploring The Impact Of Proactive Generative AI Agent Roles In Time-Sensitive Collaborative Problem-Solving Tasks
Collaborative problem-solving under time pressure is common but difficult, as teams must generate ideas quickly, coordinate actions, and track progress. Generative AI offers new opportunities to as...
Anirban Mukhopadhyay, Kevin Salubre, Hifza Javed, Shashank Mehrotra, Kumar Akash
Dual Length Codes for Lossless Compression of BFloat16
Training and serving Large Language Models (LLMs) relies heavily on parallelization and collective operations, which are frequently bottlenecked by network bandwidth. Lossless compression using e.g...
Aditya Agrawal, Albert Magyar, Hiteshwar Eswaraiah, Patrick Sheridan, Pradeep Janedula, Ravi Kris...
Strange Undercurrents: A Critical Outlook on AI's Cultural Influence
While generative artificial intelligence (generative AI) is being examined extensively, some issues it epitomizes call for more refined scrutiny and deeper contextualization. Besides the lack of nu...
Dejan Grba
Examining LLMs Ability to Summarize Code Through Mutation-Analysis
As developers increasingly rely on LLM-generated code summaries for documentation, testing, and review, it is important to study whether these summaries accurately reflect what the program actually...
Lara Khatib, Micheal Pu, Bogdan Vasilescu, Meiyappan Nagappan
TFL: Targeted Bit-Flip Attack on Large Language Model
Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection attacks. Recent studi...
Jingkai Guo, Chaitali Chakrabarti, Deliang Fan
Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning
Supervised fine-tuning (SFT) relies critically on selecting training data that most benefits a model's downstream performance. Gradient-based data selection methods such as TracIn and Influence Fun...
Sirui Chen, Yunzhe Qi, Mengting Ai, Yifan Sun, Ruizhong Qiu, Jiaru Zou, Jingrui He
Causality by Abstraction: Symbolic Rule Learning in Multivariate Timeseries with Large Language Models
Inferring causal relations in timeseries data with delayed effects is a fundamental challenge, especially when the underlying system exhibits complex dynamics that cannot be captured by simple func...
Preetom Biswas, Giulia Pedrielli, K. Selçuk Candan
Neural Synchrony Between Socially Interacting Language Models
Neuroscience has uncovered a fundamental mechanism of our social nature: human brain activity becomes synchronized with others in many social contexts involving interaction. Traditionally, social m...
Zhining Zhang, Wentao Zhu, Chi Han, Yizhou Wang, Heng Ji
VQPP: Video Query Performance Prediction Benchmark
Query performance prediction (QPP) is an important and actively studied information retrieval task, having various applications, such as query reformulation, query expansion, and retrieval system s...
Adrian Catalin Lutu, Eduard Poesina, Radu Tudor Ionescu
Collaborative Processing for Multi-Tenant Inference on Memory-Constrained Edge TPUs
IoT applications are increasingly relying on on-device AI accelerators to ensure high performance, especially in limited connectivity and safety-critical scenarios. However, the limited on-chip mem...
Nathan Ng, Walid A. Hanafy, Prashanthi Kadambi, Balachandra Sunil, Ayush Gupta, David Irwin, Yoge...
The Digital Divide in Generative AI: Evidence from Large Language Model Use in College Admissions Essays
Large language models (LLMs) have become popular writing tools among students and may expand access to high-quality feedback for students with less access to traditional writing support. At the sam...
Jinsook Lee, Conrad Borchers, AJ Alvero, Thorsten Joachims, Rene F. Kizilcec