Health
1353 storiesPublic health and medicine worldwide — sourced from WHO News.
Skill Reuse as Compression in Agentic RL
arXiv:2605.31509v2 Announce Type: replace Abstract: Large language model agents trained with reinforcement learning (RL) often learn brittle, task-specific shortcuts. We hypothesize that agents generalize better when the…
ScaRF-SLAM: Scale-Consistent Reconstruction with Feed-Forward Models and Classical Visual SLAM
arXiv:2606.00307v3 Announce Type: replace Abstract: Recent works have explored unifying SLAM with geometric foundation models (GFMs). However, directly using GFM predictions for tracking is highly sensitive to model capa…
FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search
arXiv:2606.00660v2 Announce Type: replace Abstract: Agentic search requires language model agents to explore many sources and answer complex information-seeking questions. Scaling test-time compute is a promising way to …
PlanarBench: Evaluating LLM Spatial Reasoning via Planar Graph Drawing
arXiv:2606.02010v2 Announce Type: replace Abstract: Existing LLM graph benchmarks typically ask models to answer graph-theoretic questions or compute symbolic solutions rather than construct spatial layouts. Within-task …
Who Annotates in NLP? A Large-scale Assessment of Human Annotation Reporting between 2018 and 2025
arXiv:2606.02255v3 Announce Type: replace Abstract: Human annotation is the empirical foundation of much NLP research, from dataset construction to model evaluation, but papers often leave unclear who produced the annota…
What Do Students Learn? A Feature-Level Analysis of Dark Knowledge
arXiv:2606.03052v2 Announce Type: replace Abstract: Knowledge Distillation (KD) is a powerful tool for model compression, yet the precise mechanisms by which student models acquire feature representations remain underexp…
GeM-NR: Geometry-Aware Multi-View Editing for Nonrigid Scene Changes
arXiv:2606.05142v2 Announce Type: replace Abstract: Recent developments in multi-view image editing with generative models have brought us a step closer toward general 3D content generation and customization. Most existi…
A Comprehensive Survey on Semantic Communication in Non-Terrestrial Networks: Architectures, Methodologies, and Challenges
arXiv:2606.05216v2 Announce Type: replace Abstract: Sixth-generation networks are expected to extend connectivity beyond terrestrial infrastructure through non-terrestrial networks (NTNs) comprising satellites, high-alti…
Online Safety Regulation Increases Attention to VPNs: Privacy Implications of the UK Online Safety Act
arXiv:2606.05273v2 Announce Type: replace Abstract: Governments worldwide are increasingly regulating digital platforms to reduce online harms, but access restrictions can alter user behaviour and create new privacy risk…
Jacobi-Anger Method for Deterministic Initialization in Implicit Neural Representation
arXiv:2606.06671v2 Announce Type: replace Abstract: Existing implicit neural representation (INR) approaches suffer from stochastic initialization that does not guarantee consistent or high-quality performance across run…
RECAP: Regression Evaluation for Continual Adaptation of Prompts
arXiv:2606.06698v4 Announce Type: replace Abstract: Production agentic systems routinely face evolving constraints and must comply from the very next interaction. Scenarios like a tool-call notification changing a compli…
Enabling KV Caching of Shared Prefix for Diffusion Language Models
arXiv:2606.07571v4 Announce Type: replace Abstract: Key-value (KV) caching for shared prefixes is essential for high-throughput large language model (LLM) serving, but it faces critical challenges in emerging diffusion l…
DOG-DPO:Dynamic Optimization in Geometry for Safety Alignment
arXiv:2606.07678v4 Announce Type: replace Abstract: Safety alignment for large language models relies on preference data, but current pipelines often train on large, redundant datasets. Existing data selection methods ty…
Toward Interaction Dynamics: A Predictive Framework for Safe Physical Human Robot Interaction
arXiv:2606.08281v3 Announce Type: replace Abstract: Physical human-robot interaction requires yielding transiently to contact yet recovering the commanded reference under sustained load. Finite-stiffness impedance contro…
DECSELFMASK: Leveraging Unlabeled Text via Self-Relevance-Guided Masking for Decoder-Only Classification
arXiv:2606.09466v3 Announce Type: replace Abstract: Classification tasks require annotated data, which can often be expensive, time-consuming, or even unfeasible to collect. This is the case of the medical domain, where …
Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation
arXiv:2606.09536v2 Announce Type: replace Abstract: Conventional one-hot encodings often yield poorly calibrated models, being overconfident under attack, and letting entropy-based detection algorithms fail. Previous ima…
Self-EmoQ: Plutchik-Guided Value-based Planning to Drive Streaming Emotional TTS
arXiv:2606.09837v2 Announce Type: replace Abstract: Emotional interaction is increasingly crucial for conversational AI, yet current systems lack a self-emotion determination mechanism to drive the streaming text-to-spee…
Quantified propositional calculi and narrow implicit proofs
arXiv:2606.10535v2 Announce Type: replace Abstract: In the implicit version of a propositional proof system Q, we work with Q-proofs that are not written down directly, but are succinctly encoded by circuits. Thus implic…
From Prompt to Purchase: How AI Brand Recommendations Move Consumers on the Open Web
arXiv:2606.10907v2 Announce Type: replace Abstract: When a conversational assistant recommends a brand to a user with no recent observed engagement, that user's same-name Google search rises $+4.3$ percentage points (pp)…
Generativism: Toward a Learning Theory for the Age of Generative Artificial Intelligence
arXiv:2606.12441v2 Announce Type: replace Abstract: The four dominant learning theories of behaviorism, cognitivism, constructivism, and connectivism show significant conceptual limitations as generative artificial intel…