Health
988 storiesPublic health and medicine worldwide — sourced from WHO News.
VOiLA: Vectorized Online Planning with Learned Diffusion Models for POMDP Agents
arXiv:2606.19729v2 Announce Type: replace Abstract: Planning under uncertainty is an essential capability for autonomous robots. The Partially Observable Markov Decision Process (POMDP) provides a powerful framework for …
Training-Free Metrics for Synthetic Object Detection Data: A Proxy for Detector Performance
arXiv:2606.19817v2 Announce Type: replace Abstract: Synthetic images are increasingly used to augment scarce real data for object detection. However, not all synthetic sets help equally, and the only way to know a set's …
Building Agent Harnesses for Scientific Curation from Multimodal Sources
arXiv:2606.21005v2 Announce Type: replace Abstract: Scientific discovery workflows often depend on structured curation from the literature. This is difficult for current agents because the key evidence is scattered acros…
Warning labels shift perceptions of sycophantic AI, but not its influence
arXiv:2606.21317v2 Announce Type: replace Abstract: Recent work has raised concerns about the influence of sycophantic AI on user judgment and relationships. One proposed mitigation, which has received regulatory attenti…
When Does Belief-Based Agent Memory Help? Reliability-Conditional Updating and Provenance-Capped Poisoning Defense
arXiv:2606.22030v2 Announce Type: replace Abstract: We investigate when belief-based memory actually improves large language model (LLM) agents. Our vehicle is Nous, a long-term memory architecture that represents each e…
Schemata, Cyclic Proofs and Herbrand Systems
arXiv:2606.23040v2 Announce Type: replace Abstract: Inductive proofs can be represented by proof schemata, a formalism that represents infinite sequences of proofs by recursive definitions. Since proof schemata avoid the…
Structuring International Governance through the Space of Concerns
arXiv:2606.25286v3 Announce Type: replace Abstract: When institutions decide by consensus, the official record shows agreement but hides who shaped what was decided. We introduce a way to recover that hidden structure fr…
Toward Robust In-Context Segmentation via Concept Guidance
arXiv:2606.28149v2 Announce Type: replace Abstract: In-context segmentation (ICS) requires a model to segment target regions in a query image using only a few reference images and their corresponding masks, without updat…
Flow Matching in Feature Space for Stochastic World Modeling
arXiv:2606.29059v2 Announce Type: replace Abstract: World modeling requires forecasting uncertain futures while preserving information useful for downstream perception. Existing visual world models often struggle to sati…
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
arXiv:2606.29538v3 Announce Type: replace Abstract: Skills are a useful abstraction for software agents, turning human and agent experience into reusable procedural knowledge. Yet existing skill libraries are mostly hand…
Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis
arXiv:2606.29814v2 Announce Type: replace Abstract: We propose Nemotron-Labs-Diffusion-Image, a state-of-the-art masked discrete diffusion model (MDM) for high-resolution text-to-image synthesis. Compared with prior work…
SAGA: Scene-Aware, Goal-Evolving Agents for Long-Horizon Strategy Game Planning
arXiv:2606.29932v3 Announce Type: replace Abstract: Long-horizon strategic planning in complex strategy games requires coordinating tightly coupled decision domains, including technology, economy, diplomacy, and military…
LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via State Proprioception
arXiv:2606.30005v3 Announce Type: replace Abstract: Long-horizon tool agents are bottlenecked by how their context grows toward the limits of the context window. Recent systems make context management agent- or system-co…
EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures
arXiv:2606.30219v2 Announce Type: replace Abstract: LLM evaluation and AI safety face a shared measurement problem: benchmark scores, reward-model signals, and reported safety metrics can improve while the latent propert…
Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors
arXiv:2606.30252v2 Announce Type: replace Abstract: Inoculation prompting is a selective-generalization technique used against Emergent Misalignment. We introduce inoculation adapters (IA), a family of methods that simil…
Zero-Shot Quantization for Object Detectors using Off-the-Shelf Generative Models
arXiv:2606.31456v2 Announce Type: replace Abstract: With an increasing number of Object Detection (OD) models being deployed on edge devices, Zero-Shot Quantization for OD (ZSQ-OD) aims to quantize these models when acce…
ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping
arXiv:2606.31693v2 Announce Type: replace Abstract: The wave of AI-native applications is moving shopping beyond page- and feed-based browsing toward intent-driven experiences orchestrated by LLM agents. A common design …
MSQA: A Natively Sourced Multilingual and Multicultural SimpleQA Benchmark
arXiv:2607.00724v3 Announce Type: replace Abstract: Multilingual fluency often invites a stronger assumption: a model that can speak a user's language must also understand the culture encoded by that language. We call th…
Technical Report: Asynchronous Distributed Trajectory Estimation of Multi-Robot Systems
arXiv:2607.01106v2 Announce Type: replace Abstract: Distributed trajectory estimation arises in many applications across robotics, but existing implementations typically do not consider asynchrony in agents' communicatio…
Adversarial Pragmatics for AI Safety Evaluation: A Benchmark for Instruction Conflict, Embedded Commands, and Policy Ambiguity
arXiv:2607.01153v2 Announce Type: replace Abstract: Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model has followed an instruction, refused…