Stay updated with the latest research and technology news
arXiv:2602.15756v1 Announce Type: new Abstract: A natural and informal approach to verifiable (or zero-knowledge) ML inference over floating-point data is: ``prove that each layer was...
arXiv:2602.15757v1 Announce Type: new Abstract: Online sexism appears in various forms, which makes its detection challenging. Although automated tools can enhance the identification of sexist...
arXiv:2602.15758v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) perform strongly on single-turn chart generation, their ability to support real-world exploratory data analysis...
arXiv:2602.15761v1 Announce Type: new Abstract: With the rapid adoption of large language models (LLMs) in automated code refactoring, assessing and ensuring functional equivalence between LLM-generated...
arXiv:2602.15766v1 Announce Type: new Abstract: Large Audio Language Models struggle to disentangle overlapping events in complex acoustic scenes, yielding temporally inconsistent captions and frequent hallucinations....
arXiv:2602.15767v1 Announce Type: new Abstract: Robot-assisted feeding enables people with disabilities who require assistance eating to enjoy a meal independently and with dignity. However, existing...
arXiv:2602.15769v1 Announce Type: new Abstract: Multimodal Large Language Models (mLLMs) are often used to answer questions in structured data such as tables in Markdown, JSON,...
arXiv:2602.15772v1 Announce Type: new Abstract: Current research in multimodal models faces a key challenge where enhancing generative capabilities often comes at the expense of understanding,...
arXiv:2602.15773v1 Announce Type: new Abstract: Transaction flow networks are crucial in detecting illicit activities such as wash trading, credit card fraud, cashback arbitrage fraud, and...
arXiv:2602.15775v1 Announce Type: new Abstract: Endoscopy is essential in medical imaging, used for diagnosis, prognosis and treatment. Developing a robust dynamic 3D reconstruction pipeline for...
arXiv:2602.15776v1 Announce Type: new Abstract: In the realm of multi-agent systems, the challenge of \emph{partial observability} is a critical barrier to effective coordination and decision-making....
arXiv:2602.15778v1 Announce Type: new Abstract: Evaluating the quality of automatically generated text often relies on LLM-as-a-judge (LLM-judge) methods. While effective, these approaches are computationally expensive...
arXiv:2602.15782v1 Announce Type: new Abstract: Due to the rise in the use of renewable energies as an alternative to traditional ones, and especially solar energy,...
arXiv:2602.15783v1 Announce Type: new Abstract: Whole-slide images (WSIs) from cancer patients contain rich information that can be used for medical diagnosis or to follow treatment...
arXiv:2602.15784v1 Announce Type: new Abstract: We introduce a new class of network allocation games called graphical distance preservation games. Here, we are given a graph,...
arXiv:2602.15785v1 Announce Type: new Abstract: A growing literature uses large language models (LLMs) as synthetic participants to generate cost-effective and nearly instantaneous responses in social...
arXiv:2602.15791v1 Announce Type: new Abstract: Accurate representation of building semantics, encompassing both generic object types and specific subtypes, is essential for effective AI model training...
arXiv:2602.15794v1 Announce Type: new Abstract: The Computing Continuum (CC) integrates different layers of processing infrastructure, from Edge to Cloud, to optimize service quality through ubiquitous...
arXiv:2602.15799v1 Announce Type: new Abstract: Fine-tuning aligned language models on benign tasks unpredictably degrades safety guardrails, even when training data contains no harmful content and...
arXiv:2602.15802v1 Announce Type: new Abstract: We initiate an investigation of node differential privacy for graphs in the local model of private data analysis. In our...
arXiv:2602.15811v1 Announce Type: new Abstract: Clinical deployment of chest radiograph classifiers requires models that can be updated as new datasets become available without retraining on...
arXiv:2602.15813v1 Announce Type: new Abstract: Embodied Question Answering (EQA) combines visual scene understanding, goal-directed exploration, spatial and temporal reasoning under partial observability. A central challenge...
arXiv:2602.15814v1 Announce Type: new Abstract: Compact pretrained bidirectional encoders remain the backbone of industrial NLP under tight compute and memory budgets. Their effectiveness stems from...
arXiv:2602.15815v1 Announce Type: new Abstract: We study natural privacy filters, which enable the exact composition of differentially private (DP) mechanisms with adaptively chosen privacy characteristics....