arXiv:2512.16221v1 Announce Type: cross Abstract: Predicting geohazard runout is critical for protecting lives, infrastructure and ecosystems. Rapid mass flows, including landslides and avalanches, cause several thousand deaths across a wide range of environments, often travelling many kilometres from their source. The wide range of source conditions and material properties governing these flows makes their runout […]
An Information-Theoretic Framework for Robust Large Language Model Editing
arXiv:2512.16227v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become indispensable tools in science, technology, and society, enabling transformative advances across diverse fields. However, errors or outdated information within these models can undermine their accuracy and restrict their safe deployment. Developing efficient strategies for updating model knowledge without the expense and disruption of full […]
Wrist Photoplethysmography Predicts Dietary Information
arXiv:2511.19260v2 Announce Type: replace-cross Abstract: Whether wearable photoplethysmography (PPG) contains dietary information remains unknown. We trained a language model on 1.1M meals to predict meal descriptions from PPG, aligning PPG to text. PPG nontrivially predicts meal content; predictability decreases for PPGs farther from meals. This transfers to dietary tasks: PPG increases AUC by 11% for […]
AI-Powered Dermatological Diagnosis: From Interpretable Models to Clinical Implementation A Comprehensive Framework for Accessible and Trustworthy Skin Disease Detection
arXiv:2512.16235v1 Announce Type: cross Abstract: Dermatological conditions affect 1.9 billion people globally, yet accurate diagnosis remains challenging due to limited specialist availability and complex clinical presentations. Family history significantly influences skin disease susceptibility and treatment responses, but is often underutilized in diagnostic processes. This research addresses the critical question: How can AI-powered systems integrate family […]
Efficient Zero-Order Federated Finetuning of Language Models for Resource-Constrained Devices
arXiv:2502.10239v2 Announce Type: replace-cross Abstract: Federated fine-tuning offers a promising approach for tuning Large Language Models (LLMs) on edge devices while preserving data privacy. However, fine-tuning these models on edge devices remains challenging due to high memory, communication, and computational demands. Zero-order optimization with task alignment provides a potential solution, enabling fine-tuning with inference-level memory […]
Open Ad-hoc Categorization with Contextualized Feature Learning
arXiv:2512.16202v1 Announce Type: cross Abstract: Adaptive categorization of visual scenes is essential for AI agents to handle changing tasks. Unlike fixed common categories for plants or animals, ad-hoc categories are created dynamically to serve specific goals. We study open ad-hoc categorization: Given a few labeled exemplars and abundant unlabeled data, the goal is to discover […]
Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods
arXiv:2502.01384v3 Announce Type: replace-cross Abstract: Discrete diffusion models have recently gained significant attention due to their ability to process complex discrete structures for language modeling. However, fine-tuning these models with policy gradient methods, as is commonly done in Reinforcement Learning from Human Feedback (RLHF), remains a challenging task. We propose an efficient, broadly applicable, and […]
LLM one-shot style transfer for Authorship Attribution and Verification
arXiv:2510.13302v3 Announce Type: replace-cross Abstract: Computational stylometry studies writing style through quantitative textual patterns, enabling applications such as authorship attribution, identity linking, and plagiarism detection. Existing supervised and contrastive approaches often rely on datasets with spurious correlations, conflating style with topic. Despite the relevance of language modeling to these tasks, the pre-training of modern large […]
EnviSAgE: A Survey of Environment Scaling for Qualitative Agentic Experience Collection
arXiv:2511.09586v2 Announce Type: replace-cross Abstract: LLM-based agents can autonomously accomplish complex tasks across various domains. However, to further cultivate capabilities such as adaptive behavior and long-term decision-making, training on static datasets built from human-level knowledge is insufficient. These datasets are costly to construct and lack both dynamism and realism. A growing consensus is that agents […]
Towards Closing the Domain Gap with Event Cameras
arXiv:2512.16178v1 Announce Type: cross Abstract: Although traditional cameras are the primary sensor for end-to-end driving, their performance suffers greatly when the conditions of the data they were trained on does not match the deployment environment, a problem known as the domain gap. In this work, we consider the day-night lighting difference domain gap. Instead of […]