arXiv:2209.15111v3 Announce Type: replace Abstract: In earlier work we defined a qualitative notion of harm: either harm is caused, or it is not. For practical applications, we often need to quantify harm; for example, we may want to choose the least harmful of a set of possible interventions. In this work, which is an expanded […]
Neuro-Symbolic Agents for Hallucination-Free Requirements Reuse
arXiv:2605.01562v2 Announce Type: replace-cross Abstract: The Object-Oriented Method for Requirements Authoring and Management (OOMRAM) is a requirements reuse framework that relies on exact identifier matching and rigid templates, limiting its ability to adapt specifications across diverse contexts. While Large Language Models (LLMs) offer the flexibility to overcome this bottleneck, they introduce the risk of generating […]
BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulation
arXiv:2602.13280v2 Announce Type: replace Abstract: Simulating student learning behaviors in open-ended problem-solving environments holds potential for education research, from training adaptive tutoring systems to stress-testing pedagogical interventions. However, collecting authentic data is challenging due to privacy concerns and the high cost of longitudinal studies. While Large Language Models (LLMs) offer a promising path to student […]
On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference
arXiv:2605.04901v1 Announce Type: cross Abstract: For Transformer models, cryptographically secure inference ensures that the client learns only the final output, while the server learns nothing about the client’s input. However, securely computing nonlinear layers remains a major efficiency bottleneck due to the substantial communication rounds and data transmission required. To address this issue, prior works […]
OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models
arXiv:2605.00877v2 Announce Type: replace-cross Abstract: The vast and underexplored ocean plays a critical role in regulating global climate and supporting marine biodiversity, yet artificial intelligence has so far delivered limited impact in this domain due to a fundamental data bottleneck. Specifically, ocean data are highly fragmented across disparate sources and inherently exhibit multi-modal, high-noise, and […]
Optimal Control with Natural Images: Efficient Reinforcement Learning using Overcomplete Sparse Codes
arXiv:2412.08893v3 Announce Type: replace-cross Abstract: Optimal control and sequential decision making are widely used in many complex tasks. Optimal control over a sequence of natural images is a first step towards understanding the role of vision in control. Here, we formalize this problem as a reinforcement learning task, and derive general conditions under which an […]
Storage Is Not Memory: A Retrieval-Centered Architecture for Agent Recall
arXiv:2605.04897v1 Announce Type: cross Abstract: Extraction at ingestion is the wrong primitive for agent memory: content discarded before the query is known cannot be recovered at retrieval time. We propose True Memory, a six-layer architecture that shifts the center of the system from a storage schema to a multi-stage retrieval pipeline operating over events preserved […]
Deep Learning in Astrophysics
arXiv:2510.10713v2 Announce Type: replace-cross Abstract: Deep learning has generated diverse perspectives in astronomy, with ongoing discussions between proponents and skeptics motivating this review. We examine how neural networks complement classical statistics, extending our data analytical toolkit for modern surveys. Astronomy offers unique opportunities through encoding physical symmetries, conservation laws, and differential equations directly into architectures, […]
Atomic-Probe Governance for Skill Updates in Compositional Robot Policies
arXiv:2604.26689v3 Announce Type: replace-cross Abstract: Skill libraries in deployed robotic systems are continually updated through fine-tuning, fresh demonstrations, or domain adaptation, yet existing typed-composition methods (BLADE, SymSkill, Generative Skill Chaining) treat the library as frozen at test time and do not analyze how composition outcomes change when a skill is replaced. We introduce a paired-sampling […]
LLMs learn scientific taste from institutional traces across the social sciences
arXiv:2603.16659v2 Announce Type: replace Abstract: Reinforcement-learned reasoning has powered recent AI leaps on verifiable tasks, including mathematics, code, and structure prediction. The harder bottleneck is evaluative judgment in low-verifiability domains, where no oracle anchors reward and the core question is which untested ideas deserve attention. We test whether institutional traces, the record of what fields […]
FairEnc: A Fair Vision-Language Model with Fair Vision and Text Encoders for Glaucoma Detection
arXiv:2605.04882v1 Announce Type: cross Abstract: Automated glaucoma detection is critical for preventing irreversible vision loss and reducing the burden on healthcare systems. However, ensuring fairness across diverse patient populations remains a significant challenge. In this paper, we propose FairEnc, a fair pretraining method for vision-language models (VLMs) that enables simultaneous debiasing across multiple sensitive attributes. […]
ANO: A Principled Approach to Robust Policy Optimization
arXiv:2605.02320v2 Announce Type: replace Abstract: Proximal Policy Optimization (PPO) dominates reinforcement learning and LLM alignment but relies on a “hard clipping” mechanism that discards valuable gradients. Conversely, unconstrained methods like SPO expose the optimization to unbounded updates, causing severe instability and policy collapse during extreme outlier encounters. To resolve this dilemma, we introduce a principled […]