Health
1301 storiesPublic health and medicine worldwide — sourced from WHO News.
Integrating Flow Matching and Model Predictive Control for Safe Robot Navigation
arXiv:2610.29377v1 Announce Type: new Abstract: Learning-based path planners based on diffusion and flow matching can generate diverse trajectories from demonstrations but typically lack mechanisms for constraint satisfa…
Right On Q: Recovering Reasoning under Quantization via Self-Generated Trajectories
arXiv:2610.29378v1 Announce Type: new Abstract: Quantization-aware training (QAT) aims to recover reasoning capabilities in low-bit large language models (LLMs). Existing recipes typically supervise the quantized student…
Where AI Vulnerability Discovery Harnesses Go Quiet: Structural False Negatives and Hidden Vulnerabilities
arXiv:2610.29379v1 Announce Type: new Abstract: LLM-based vulnerability discovery harnesses can miss real, reachable vulnerabilities because of how the harness around the model is built. Steps that select code, filter it…
AdvFidelity: Unifying Preference Alignment and Few-Step Image Generation within Reinforcement Learning
arXiv:2610.29380v1 Announce Type: new Abstract: Practical image generation requires both human preference alignment and few-step efficiency, yet combining reinforcement learning (RL) with distillation is often multi-stag…
Cascading Bandits with Noisy Observations: Algorithms and Regret Bounds
arXiv:2610.29381v1 Announce Type: new Abstract: We propose a novel stochastic cascading bandit setup where probing an ordered shortlist of $K$ out of $L$ arms incurs position-dependent costs, and the learner observes onl…
RadioDreamer: A World Model for Radio Map Forecasting and Imagination-Based Optimization
arXiv:2610.29382v1 Announce Type: new Abstract: Radio maps characterize the spatial distribution of wireless conditions and are fundamental to network planning and optimization. However, existing learning-based methods r…
Parallelizable Probabilistic Latent Reasoning for Diverse Reasoning Trajectories
arXiv:2610.29385v1 Announce Type: new Abstract: Language models relying on verbalized Chain-of-Thought (CoT) are constrained to token-by-token generation in the language space, where many tokens serve textual coherence r…
FM-Occ: Feature-Diverse Upsampling and Memory-Aware Decoding for 3D Occupancy Prediction
arXiv:2610.29388v1 Announce Type: new Abstract: 3D semantic occupancy prediction estimates voxel-wise occupancy and semantic labels throughout a scene. Our experiments reveal that conventional sparse transposed-convoluti…
Nominate-then-Adjudicate: LLM-Assisted One-Pass and Per-Instance MIP Solver Tuning
arXiv:2610.29391v1 Announce Type: new Abstract: Mixed-integer programming solvers expose hundreds or even thousands of parameters whose best setting varies per instance, yet per-instance search is prohibitively expensive…
CertMoE: Robustness Certification for Mixture-of-Experts LLMs via Routing-Aware Smoothing
arXiv:2610.29395v1 Announce Type: new Abstract: Provable robustness is a cornerstone of trustworthy machine learning, aiming to guarantee model predictions under adversarial perturbations. Existing certification framewor…
Progressive Permutation Alignment with Temperature-Controlled Spectral Sharpening
arXiv:2610.29396v1 Announce Type: new Abstract: In implicit neural representations (INRs), 3D signals are encoded directly in network weights, making stable weight-space operations essential. However, permutation symmetr…
Region-Aware Multi-View Inspection Using Deep Learning and Domain-Informed Decision Fusion
arXiv:2610.29398v1 Announce Type: new Abstract: Automated optical inspection of precision components with tiny surface defects remains challenging when different regions of the same component exhibit different defect cha…
VideoGen Model 1: Prompt Expansion Versus Formatting in Audiovisual Generation
arXiv:2610.29407v1 Announce Type: new Abstract: Creative prompt expansion improved overall audiovisual quality scores over raw prompts in a controlled pilot of VideoGen Model 1, our post-trained version of MiniMax H3. We…
LiveAct: Towards Real-Time Multi-Agent World Models with Heterogeneous Action Interfaces
arXiv:2610.29408v1 Announce Type: new Abstract: Interactive video world models predict how an environment evolves under user actions, but most existing systems assume one controlled agent and one task-specific action int…
LLMSeg: Training-Free Text-Prompted Image Segmentation with B-Splines
arXiv:2610.29409v1 Announce Type: new Abstract: Promptable segmentation models such as SAM 3 achieve remarkable open-vocabulary performance but require dedicated architectures, large-scale annotation engines, and task-sp…
ECHO: Emergent Common-Mode Hidden Offsets Drive Vocabulary Collapse in Preference Optimization
arXiv:2610.29410v1 Announce Type: new Abstract: Preference optimization can improve every ranking metric while building a hidden, shared representation shift that the relative loss barely sees, one that can eventually de…
The Predictive--Optimization Gap in GuanDan Self-Play
arXiv:2610.29411v1 Announce Type: new Abstract: Outcome-predictive signals are often treated as promising optimization targets in reinforcement learning, but predictive validity and optimization utility are different cla…
Beyond Small Talk: Modeling Disclosure Trajectories in Human-AI Conversation
arXiv:2610.29413v1 Announce Type: new Abstract: Recently, we see a rise in conversational agents as a form of social and emotional support, where disclosure will unfold over time. Yet, current evaluations of these agents…
Solving Go under Positional Superko: Sound Proof Transfer and New Board Values
arXiv:2610.29414v1 Announce Type: new Abstract: Positional superko (PSK) forbids recreating any earlier whole-board position. It is part of the Chinese rules as written and of the rules used in computer Go. Yet almost al…
CCG Diffusion: Combinatory Categorial Grammar-Driven Compositional and Syntactically Disambiguated Text-to-Image Generation
arXiv:2610.29415v1 Announce Type: new Abstract: Text-to-image generation models do not explicitly receive the syntactic structure of the prompt, i.e., which word modifies which and where each phrase attaches. Consequentl…