arXiv:2511.04143v1 Announce Type: new Abstract: The turn of the millennium has seen a growing interest in the study of live cells by infrared (IR) spectroscopy, driven by the versatility, wealth of molecular information, and potential for high-throughput screening of the technique. Measurements on individual cells, either isolated or within a multi-cellular structure, provide information that […]
PETRA: Pretrained Evolutionary Transformer for SARS-CoV-2 Mutation Prediction
arXiv:2511.03976v1 Announce Type: cross Abstract: Since its emergence, SARS-CoV-2 has demonstrated a rapid and unpredictable evolutionary trajectory, characterized by the continual emergence of immune-evasive variants. This poses persistent challenges to public health and vaccine development. While large-scale generative pre-trained transformers (GPTs) have revolutionized the modeling of sequential data, their direct applications to noisy viral genomic […]
Understanding Adam Requires Better Rotation Dependent Assumptions
arXiv:2410.19964v3 Announce Type: replace-cross Abstract: Despite its widespread adoption, Adam’s advantage over Stochastic Gradient Descent (SGD) lacks a comprehensive theoretical explanation. This paper investigates Adam’s sensitivity to rotations of the parameter space. We observe that Adam’s performance in training transformers degrades under random rotations of the parameter space, indicating a crucial sensitivity to the choice […]
Simple 3D Pose Features Support Human and Machine Social Scene Understanding
arXiv:2511.03988v1 Announce Type: cross Abstract: Humans can quickly and effortlessly extract a variety of information about others’ social interactions from visual input, ranging from visuospatial cues like whether two people are facing each other to higher-level information. Yet, the computations supporting these abilities remain poorly understood, and social interaction recognition continues to challenge even the […]
Protein aggregation in Huntington’s disease
arXiv:2511.04174v1 Announce Type: new Abstract: The presence of an expanded polyglutamine produces a toxic gain of function in huntingtin. Protein aggregation resulting from this gain of function is likely to be the cause of neuronal death. Two main mechanisms of aggregation have been proposed: hydrogen bonding by polar-zipper formation and covalent bonding by transglutaminase-catalyzed cross-linking. […]
Hybrid Fuzzing with LLM-Guided Input Mutation and Semantic Feedback
arXiv:2511.03995v1 Announce Type: cross Abstract: Software fuzzing has become a cornerstone in automated vulnerability discovery, yet existing mutation strategies often lack semantic awareness, leading to redundant test cases and slow exploration of deep program states. In this work, I present a hybrid fuzzing framework that integrates static and dynamic analysis with Large Language Model (LLM)-guided […]
SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
arXiv:2503.03480v3 Announce Type: replace-cross Abstract: Vision-language-action models (VLAs) show potential as generalist robot policies. However, these models pose extreme safety challenges during real-world deployment, including the risk of harm to the environment, the robot itself, and humans. How can safety constraints be explicitly integrated into VLAs? We address this by exploring an integrated safety approach […]
Accelerating scientific discovery with the common task framework
arXiv:2511.04001v1 Announce Type: cross Abstract: Machine learning (ML) and artificial intelligence (AI) algorithms are transforming and empowering the characterization and control of dynamic systems in the engineering, physical, and biological sciences. These emerging modeling paradigms require comparative metrics to evaluate a diverse set of scientific objectives, including forecasting, state reconstruction, generalization, and control, while also […]
When Empowerment Disempowers
arXiv:2511.04177v1 Announce Type: new Abstract: Empowerment, a measure of an agent’s ability to control its environment, has been proposed as a universal goal-agnostic objective for motivating assistive behavior in AI agents. While multi-human settings like homes and hospitals are promising for AI assistance, prior work on empowerment-based assistance assumes that the agent assists one human […]
Abductive Inference in Retrieval-Augmented Language Models: Generating and Validating Missing Premises
arXiv:2511.04020v1 Announce Type: cross Abstract: Large Language Models (LLMs) enhanced with retrieval — commonly referred to as Retrieval-Augmented Generation (RAG) — have demonstrated strong performance in knowledge-intensive tasks. However, RAG pipelines often fail when retrieved evidence is incomplete, leaving gaps in the reasoning process. In such cases, emphabductive inference — the process of generating plausible […]