Health
1353 storiesPublic health and medicine worldwide — sourced from WHO News.
Beyond Magnitude: Contrastive Routing for Modular Mixture-of-Experts
arXiv:2609.01100v1 Announce Type: new Abstract: In current Mixture-of-Experts architectures, routing is performed based on representations dominated by structure shared across all tokens, limiting expert specialization. …
Neural Symbollic Regression Using Deep Learning and Sparse Modelling
arXiv:2609.01102v1 Announce Type: new Abstract: Symbolic Regression (SR) seeks to find succinct mathematical expressions that represent the fundamental relationships within data, providing interpretability and scientific…
When Modality Gap Reduction Fails: Prediction-Level Hubness in CLIP
arXiv:2609.01103v1 Announce Type: new Abstract: Reducing the modality gap between image and text representations in CLIP is widely expected to improve cross-modal alignment and downstream performance. However, a smaller …
Hints Help But Do They Teach? Evaluating Skills Transfer in Code Generation
arXiv:2609.01106v1 Announce Type: new Abstract: When a hint turns a failing generated program into a passing one, does it provide missing information or merely steer the model toward a solution it could already produce? …
Symmetry Inheritance and Symmetry-Reduced Finite Element Analysis for Second-Order Linear Elliptic Problems with Robin Boundary Conditions
arXiv:2609.01107v1 Announce Type: new Abstract: A symmetry framework is developed for second-order linear elliptic equations subject to Robin boundary conditions on bounded domains. Orthogonal transformations of the doma…
Replicating TRACE: A Practitioner's Guide to Its Threshold and Particle Budget
arXiv:2609.01108v1 Announce Type: new Abstract: TRACE (Math & Lienhart, arXiv:2602.01135) reads causal graphs over event types out of a pretrained autoregressive sequence model by thresholding a per-position conditional-…
Griotte: Verified Compartmentalisation via Capabilities
arXiv:2609.01110v1 Announce Type: new Abstract: CHERIoT is a novel hardware-software co-design that leverages hardware capabilities to define a notion of compartment, in a minimalistic capability-based OS, CHERIoT RTOS. …
ClinTraceBench: Source-Verifiable Longitudinal Clinical Reasoning over EHR-Derived Dialogues
arXiv:2609.01111v1 Announce Type: new Abstract: Clinical LLM assistants must reason over multi-visit patient trajectories, yet whether the compact history representations used to scale them---retrieval, structured timeli…
Generalized Tan-Arlery-Rabaste-Lehmann-Ovarlez Lower Bound on Ambiguity Function of a Set of Sequences With Mismatched Filters
arXiv:2609.01112v1 Announce Type: new Abstract: In this paper, a lower bound on the maximum ambiguity function (AF) sidelobes of a set of unimodular sequences is formulated for the desired low-ambiguity-zone (LAZ). Our m…
EDRAC: Benchmarking Arabic Dialect Reading Comprehension
arXiv:2609.01113v1 Announce Type: new Abstract: Dialectal Arabic (DA) remains under-resourced compared to Modern Standard Arabic (MSA), particularly for machine reading comprehension (MRC) and question answering (QA). Ex…
Latent Recurrent Thoughts: Recurrent Refinement of Proposed Latents for Reasoning with Frozen LLMs
arXiv:2609.01117v1 Announce Type: new Abstract: Chain-of-thought reasoning unfolds in discrete token space: each step is committed as text, errors propagate, and eliciting good traces presupposes traces to imitate. Reaso…
DNC-IMM: Early Lane-Change Intention Recognition via Neural Calibration Based on Driving Context Information
arXiv:2609.01120v1 Announce Type: new Abstract: Early recognition of lane-change intention is essential for proactive decision-making in autonomous driving and advanced driver assistance systems. This paper proposes a Du…
Sentinel-Based Failover for QKD-Augmented IPsec Tunnels
arXiv:2609.01121v1 Announce Type: new Abstract: Quantum-safe IPsec through hybrid key establishment is practical, but creates a critical operational challenge: how to maintain tunnel availability when the QKD infrastruct…
P-PatchDiff: Progressive Patch Diffusion Models for Low-light Image Enhancement
arXiv:2609.01123v1 Announce Type: new Abstract: Recent advancements in low-light image enhancement have leveraged diffusion models for their strong ability to generate perceptually realistic, detailed images. Patch diffu…
When Does Online Adaptation Pay on the Edge? A Leakage-Free Evaluation of Warmup, Learning-Rate Selection, and Resource Trade-offs for Time-Series Forecasting
arXiv:2609.01126v1 Announce Type: new Abstract: Online adaptation can help edge time-series forecasting under distribution drift, but its measured benefit is sensitive to evaluation choices. We study six public multivari…
Scaled Idempotence in Transformer Attention: Paired OV Geometry and Shared-Value Algebras
arXiv:2609.01129v1 Announce Type: new Abstract: We identify a recurrent algebraic regularity in Transformer attention: a sparse subset of effective OV operators $T=OV^\top$ nearly closes under composition, $T^2\approx\al…
From Source Reconstruction to Predictive State Preservation: An Information-Theoretic Framework for AI-Native Communication
arXiv:2609.01131v1 Announce Type: new Abstract: AI-native communication increasingly aims to support prediction rather than reproduce every detail of the source. This shift raises a basic question left implicit by conven…
Overfitting Mitigation via Singular Value Decomposition in Minimum Bayes Risk Decoding
arXiv:2609.01135v1 Announce Type: new Abstract: Minimum Bayes Risk (MBR) decoding enables high-quality text generation by selecting the hypothesis that maximizes a utility metric over sampled pseudo-references. However, …
Different Changes Require Different Reasoning: Change-Type-Specialized Experts for Robust Change Captioning
arXiv:2609.01136v1 Announce Type: new Abstract: Change captioning is the task of generating natural language descriptions that explain the changes between a pair of images. Although different change types (e.g., color sh…
Does task decomposition improve automatic NLG evaluation?
arXiv:2609.01139v1 Announce Type: new Abstract: The LLM-as-a-judge (LLMaJ) framework has emerged as a promising solution for cheap, reproducible, reference-free Natural Language Generation (NLG) evaluation. Prior work se…