arXiv:2510.15949v4 Announce Type: replace-cross Abstract: Large language models show promise for financial decision-making, yet deploying them as autonomous trading agents raises fundamental challenges: how to adapt instructions when rewards arrive late and obscured by market noise, how to synthesize heterogeneous information streams into coherent decisions, and how to bridge the gap between model outputs and […]
Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Prompts
arXiv:2510.22628v2 Announce Type: replace-cross Abstract: This paper presents a real-time modular defense system named Sentra-Guard. The system detects and mitigates jailbreak and prompt injection attacks targeting large language models (LLMs). The framework uses a hybrid architecture with FAISS-indexed SBERT embedding representations that capture the semantic meaning of prompts, combined with fine-tuned transformer classifiers, which are […]
AI-Driven Expansion and Application of the Alexandria Database
arXiv:2512.09169v2 Announce Type: replace-cross Abstract: We present a novel multi-stage workflow for computational materials discovery that achieves a 99% success rate in identifying compounds within 100 meV/atom of thermodynamic stability, with a threefold improvement over previous approaches. By combining the Matra-Genoa generative model, Orb-v2 universal machine learning interatomic potential, and ALIGNN graph neural network for […]
Adoption and Use of LLMs at an Academic Medical Center
arXiv:2602.00074v2 Announce Type: replace-cross Abstract: While large language models (LLMs) can support clinical documentation needs, standalone tools struggle with “workflow friction” from manual data entry. We developed ChatEHR, a system that enables the use of LLMs with the entire patient timeline spanning several years. ChatEHR enables automations – which are static combinations of prompts and […]
BadSNN: Backdoor Attacks on Spiking Neural Networks via Adversarial Spiking Neuron
arXiv:2602.07200v2 Announce Type: replace-cross Abstract: Spiking Neural Networks (SNNs) are energy-efficient counterparts of Deep Neural Networks (DNNs) with high biological plausibility, as information is transmitted through temporal spiking patterns. The core element of an SNN is the spiking neuron, which converts input data into spikes following the Leaky Integrate-and-Fire (LIF) neuron model. This model includes […]
Fair Dataset Distillation via Cross-Group Barycenter Alignment
arXiv:2605.00185v1 Announce Type: cross Abstract: Dataset Distillation aims to compress a large dataset into a small synthetic one while maintaining predictive performance. We show that as different demographic groups exhibit distinct predictive patterns, the distillation process struggles to simultaneously preserve informative signals for all subgroups, regardless of whether group sizes are mildly or severely imbalanced. […]
Towards Disentangled Preference Optimization Dynamics: Suppress the Loser, Preserve the Winner
arXiv:2604.18239v3 Announce Type: replace-cross Abstract: Preference optimization is widely used to align large language models (LLMs) with human preferences. However, many margin-based methods also suppress the chosen response when they try to suppress the rejected one, and there is no general way to prevent this across different objectives. We address this issue with a unified […]
How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models
arXiv:2604.04385v4 Announce Type: replace-cross Abstract: We localize the policy routing mechanism in alignment-trained language models. An intermediate-layer attention gate reads detected content and triggers deeper amplifier heads that boost the signal toward refusal. In smaller models the gate and amplifier are single heads; at larger scale they become bands of heads across adjacent layers. The […]
Self-organized criticality enables conscious integration through brain-body resonance
arXiv:2605.00024v1 Announce Type: new Abstract: The “binding problem” of how distributed neural activity unifies into conscious experience has remained an open challenge since its articulation in 1890. We present evidence that conscious integration relies on self-organized criticality maintained by brain-body resonance, placing human cognition within the universality class of critical systems. Using 64-channel EEG data, […]
Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions
arXiv:2605.00226v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly tasked with strategic decision-making under incomplete information, such as in negotiation and policymaking. While LLMs can excel at many such tasks, they also fail in ways that are poorly understood. We shed light on these failures by uncovering two fundamental gaps in the internal […]
Can Coding Agents Reproduce Findings in Computational Materials Science?
arXiv:2605.00803v1 Announce Type: cross Abstract: Large language models are increasingly deployed as autonomous coding agents and have achieved remarkably strong performance on software engineering benchmarks. However, it is unclear whether such success transfers to computational scientific workflows, where tasks require not only strong coding ability, but also the ability to navigate complex, domain-specific procedures and […]
Reinforcement Learning with Markov Risk Measures and Multipattern Risk Approximation
arXiv:2605.00654v1 Announce Type: cross Abstract: For a risk-averse finite-horizon Markov Decision Problem, we introduce a special class of Markov coherent risk measures, called mini-batch measures. We also define the class of multipattern risk-averse problems that generalizes the class of linear systems. We use both concepts in a feature-based $Q$-learning method with multipattern $Q$-factor approximation and […]