Health
988 storiesPublic health and medicine worldwide — sourced from WHO News.
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
arXiv:2607.14935v1 Announce Type: new Abstract: Recent advances in video understanding have spanned motion, long video, and streaming interaction, driving this field toward real-world applications. Despite this progress,…
Confidence-based Ranking with Adaptive Sampling for Noisy Black-Box Optimisation
arXiv:2607.14936v1 Announce Type: new Abstract: Real-world optimization problems often involve black-box functions and uncertainties in their evaluation, widely referred to as noisy optimization problems (NOPs). Evolutio…
A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems
arXiv:2607.14937v1 Announce Type: new Abstract: Recent foundation models (FMs) for zero-shot reconstruction of dynamical systems (DS) achieve strong out-of-domain generalization but provide little insight into the mechan…
Causal Inference for Sequential Settings under Interference and Latent Confounding
arXiv:2607.14940v1 Announce Type: new Abstract: We study causal inference under outcome interference for sequential, observational settings. Specifically, we consider settings where the binary outcomes over N units are M…
Frequency-Structured Field Learning for Light-Field Disparity Estimation
arXiv:2607.14941v1 Announce Type: new Abstract: Light-field disparity estimation requires global consistency in smooth or textureless regions and local precision near occlusion boundaries, thin structures, and abrupt dep…
Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control
arXiv:2607.14943v1 Announce Type: new Abstract: World Action Models (WAMs) enable semantically- and physically-informed control but are brittle under distribution shift. In this work, we use mechanistic interpretability …
Introspective Attention Modulation for Safe Text-to-Image Generation
arXiv:2607.14945v1 Announce Type: new Abstract: State-of-the-art flow based text-to-image (T2I) models exhibit remarkable generative abilities but remain vulnerable to producing unsafe content. Prior safety efforts range…
DINE: Distance Is Not Enough -- Learning Global Deformation Priors for Robust Soft-Tissue Point Cloud Registration
arXiv:2607.14946v1 Announce Type: new Abstract: Non-rigid point cloud registration is central to soft-tissue shape analysis, but large deformations, noise, and outliers make correspondence estimation challenging. Most le…
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget
arXiv:2607.14952v1 Announce Type: new Abstract: A growing gap separates inference context lengths from RL post-training: inference systems are approaching million-token contexts, while post-training workloads often remai…
A Queueing-Stability Criterion for Causal IPD-QIM Network Flow Watermarking
arXiv:2607.14954v1 Announce Type: new Abstract: On multi-hop encrypted links such as Tor and cascaded VPNs, tunneling flattens packet lengths and protocol fields, leaving inter-packet delay (IPD) as the main carrier for …
A Comprehensive History of $\mu$CRL and mCRL2
arXiv:2607.14956v1 Announce Type: new Abstract: This article gives a historical overview of the background, motivation and development of {\mu}CRL and its successor mCRL2, from the inception to the present. Both mCRL2 an…
Contextualized Early Detection of Online Firestorms: A Sequential LLM-Based Approach
arXiv:2607.14957v1 Announce Type: new Abstract: Online firestorms are rapid collective escalations of highly negative user-generated content and may cause substantial reputational and economic damage. Existing detectors …
Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation
arXiv:2607.14962v1 Announce Type: new Abstract: Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset of visually distinct m…
U-shaped Multi-granularity Learning for Vision-Language Models
arXiv:2607.14966v1 Announce Type: new Abstract: The prompt learning paradigm for vision-language models is effective yet faces a granularity dilemma: global prompts lack fine-grained semantic awareness, while local promp…
Latent Trajectory Discrimination for AI-Generated Text Detection
arXiv:2607.14967v1 Announce Type: new Abstract: Most existing approaches to AI-Generated Text Detection (AIGTD) treat documents as static objects and base their decisions on aggregate statistics or globally compressed em…
Stitch-Inferencer: Enhance Endoscopic Video Segmentation and Tracking via Panoramic Reconstruction
arXiv:2607.14968v1 Announce Type: new Abstract: Surgical video understanding is fundamental to navigation systems. Endoscopic perception is often hindered by a limited field-of-view and frequent instrument occlusions, ma…
Explaining Process Control Optimisation Recommendations via GradientSHAP and Implicit Differentiation
arXiv:2607.14970v1 Announce Type: new Abstract: Automated optimisation is increasingly adopted in industrial processes, yet a trust gap persists between engineers who design these algorithms and operators who must act on…
On Success and Simplicity: A Second Look at Transferable Vision-Language Attack Pipeline
arXiv:2607.14974v1 Announce Type: new Abstract: Vision-Language Pre-training Models (VLPMs) are known to be vulnerable to adversarial attacks. Recent transferable attacks on VLPMs have followed a common pipeline with com…
CFM-Bench: A Unified Multi-Domain, Multi-Task Benchmark for Channel Foundation Models
arXiv:2607.14975v1 Announce Type: new Abstract: Channel foundation models (CFMs) are developing rapidly, with recent studies reporting benefits from pretraining across downstream wireless tasks. Yet CFMs are commonly eva…
From Draft to Draft-Free: One-Step Video Object Removal via Privileged Distillation and Fast Planting
arXiv:2607.14976v1 Announce Type: new Abstract: Video object removal is a fundamental yet challenging task in video editing. Despite recent progress, existing methods typically fall into two categories. Traditional appro…