arXiv:2605.23603v1 Announce Type: cross Abstract: We introduce the Preisach Attention Layer (PAL), a novel sequence modelling architecture grounded in the classical Preisach hysteresis operator from mathematical physics. PAL replaces the softmax attention mechanism with a binary relay operator parameterised by learned activation and deactivation thresholds, maintaining a stack of local extrema as its internal state. […]
Particle Image Velocimetry of 3D printed vascular fluidic phantom devices
arXiv:2605.23877v1 Announce Type: cross Abstract: Altered hemodynamics play a key role in cerebrovascular diseases such as aneurysms and stenosis. However, in vivo imaging lacks the spatial resolution required to resolve flow dynamics in small vessels. This study presents an experimental framework to investigate microscale hemodynamics using transparent 3D printed vascular models and particle image velocimetry […]
SciHorizon-GENE: Benchmarking LLM for Life Sciences Inference from Gene Knowledge to Functional Understanding
arXiv:2601.12805v3 Announce Type: replace Abstract: Large language models (LLMs) have shown growing promise in biomedical research, particularly for knowledge-driven interpretation tasks. However, their ability to reliably reason from gene-level knowledge to functional understanding, a core requirement for knowledge-enhanced cell atlas interpretation, remains largely underexplored. To address this gap, we introduce SciHorizon-GENE, a large-scale gene-centric benchmark […]
Model Spec Midtraining: Improving How Alignment Training Generalizes
arXiv:2605.02087v2 Announce Type: replace Abstract: Some frontier AI developers aim to align language models to a Model Spec or Constitution that describes the intended model behavior. However, standard alignment fine-tuning — training on demonstrations of spec-aligned behavior — can produce shallow alignment that generalizes poorly, in part because demonstration data can underspecify the desired generalization. […]
Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG
arXiv:2506.04390v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) systems are vulnerable to attacks that inject poisoned passages into the retrieved context, even at low corruption rates. We show that existing attacks are not designed to be stealthy, allowing reliable detection and mitigation. We formalize a distinguishability-based security game to quantify stealth for such attacks. If […]
Bridging AI and Clinical Reasoning: Abductive Explanations for Alignment on Critical Symptoms
arXiv:2602.13985v2 Announce Type: replace Abstract: Artificial intelligence (AI) has demonstrated strong potential in clinical diagnostics, often achieving accuracy comparable to or exceeding that of human experts. A key challenge, however, is that AI reasoning frequently diverges from structured clinical frameworks, limiting trust, interpretability, and adoption. Critical symptoms, pivotal for rapid and accurate decision-making, may be […]
Controlled Personalization in Legacy Media Online Services: A Case Study in News Recommendation
arXiv:2510.09136v2 Announce Type: replace-cross Abstract: Personalized news recommendations have become a standard feature of large news aggregation services, optimizing user engagement through automated content selection. In contrast, legacy news media often approach personalization cautiously, striving to balance technological innovation with core editorial values. As a result, online platforms of traditional news outlets typically combine editorially […]
CoFrGeNet: Continued Fraction Architectures for Language Generation
arXiv:2601.21766v4 Announce Type: replace-cross Abstract: Transformers are arguably the preferred architecture for language generation. In this paper, inspired by continued fractions, we introduce a new function class for generative modeling. The architecture family implementing this function class is named CoFrGeNets – Continued Fraction Generative Networks. We design novel architectural components based on this function class […]
MemReward: Graph-Based Experience Memory for LLM Reward Prediction with Limited Labels
arXiv:2603.19310v4 Announce Type: replace-cross Abstract: Reinforcement learning has emerged as a powerful paradigm for improving large language model (LLM) reasoning, where rollouts are sampled from the policy and reward signals computed on those rollouts are used to update the policy. However, in data-scarce scenarios, obtaining ground-truth labels to verify rollouts at scale often requires expensive […]
Content-Aware Attack Detection in LLM Agent Tool-Call Traffic: An Empirical Study of Features, Architectures, and Evaluation Protocols
arXiv:2605.11053v3 Announce Type: replace-cross Abstract: The Model Context Protocol (MCP) has become a widely adopted interface for LLM agents to invoke external tools, yet learned monitoring of MCP tool-call traffic remains underexplored. In this article, the proposed detector is presented as an attack detection framework for MCP tool-call traffic that encodes each agent session as […]
Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning
arXiv:2605.20201v2 Announce Type: replace-cross Abstract: Recent large language models support inputs of up to 10 million tokens, yet they perform poorly on long-context tasks that require complex reasoning. Such tasks can be solved using only a subset of the input — a proxy context — rather than the full sequence. Despite sharing the same underlying […]
ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning
arXiv:2605.23562v1 Announce Type: cross Abstract: Sparse rewards are a major bottleneck in multi-agent reinforcement learning (MARL), where simultaneous learning induces non-stationarity and makes reward design especially delicate. Reward shaping can accelerate learning, but in the multi-agent setting it must preserve the strategic structure of the problem rather than merely improve short-term optimization. We propose Automatic […]