Health
1301 storiesPublic health and medicine worldwide — sourced from WHO News.
Beyond the Vote: When Do LLMs Add Value to Retrieval-Based Tabular Classification?
arXiv:2610.29520v1 Announce Type: new Abstract: Retrieval-based in-context learning (ICL) enables large language models (LLMs) to predict tabular labels from similar examples, but it remains unclear whether LLM inference…
X-Embedding: Two-Stage Training for Multilingual Patent Prior-Art Retrieval
arXiv:2610.29521v1 Announce Type: new Abstract: Multilingual patent prior-art retrieval requires identifying X-category references that are particularly relevant to the novelty or inventive step of a claimed invention, b…
pplx-embed-v2-late Technical Report
arXiv:2610.29523v1 Announce Type: new Abstract: In this report, we introduce pplx-embed-v2-late, a pair of 0.6B and 9B multilingual and multimodal late-interaction models. Both models achieve state-of-the-art results wit…
Geometric knowledge spaces, Attention pairing and Architectures
arXiv:2610.29526v1 Announce Type: new Abstract: In this paper, we propose a geometric approach to deriving attention mechanisms and exploring potential new transformer architectures. We begin by formalizing the notions o…
RCSD: Reinforcement and Continual Learning for Domain-Specific Speculative Decoding
arXiv:2610.29527v1 Announce Type: new Abstract: Speculative decoding accelerates large language model inference by employing a compact draft model to propose candidate tokens that are verified in parallel by a target mod…
Are Joint-Embedding Predictive Objectives Effective for Longitudinal EHRs?
arXiv:2610.29528v1 Announce Type: new Abstract: Masked language modelling (MLM) is the dominant pretraining objective for transformer encoders applied to longitudinal electronic health records (EHRs). However, reconstruc…
Phase Transitions in Learning Driven by Extremal Data
arXiv:2610.29531v1 Announce Type: new Abstract: We study an extremal regression problem, an example of multiple instance learning (MIL), where the predictors are given as multisets, called bags. The bag elements (called …
Block Diffusion for Longitudinal EHR: Accuracy, Efficiency, and Representation Trade-offs
arXiv:2610.29533v1 Announce Type: new Abstract: Autoregressive (AR) models have proved effective for zero-shot prediction from longitudinal electronic health records, but impose strictly sequential generation on trajecto…
Safe World Model for Joint Trajectory and Beamforming Design of Mobile Base Stations
arXiv:2610.29534v1 Announce Type: new Abstract: Mobile base stations (MBSs), including aerial and ground-based platforms, provide flexible wireless coverage through adaptive positioning. However, jointly optimizing their…
A recovery based linear finite element method for the Monge--Amp\`{e}re equation
arXiv:2610.29536v1 Announce Type: new Abstract: In this paper, we study finite element approximations of a fourth-order perturbed semilinear partial differential equation that arises naturally in the computation of visco…
Melange: A Synthetic Visual Bias Benchmark for Multi-modal Large Language Models
arXiv:2610.29537v1 Announce Type: new Abstract: Multi-modal Large Language Models (MLLMs) have seen broad adoption, but their biases are still far less examined than those of standard LLMs, creating possible social harms…
Stochastic Pruning of the DPO Computation Graph: 1.4x Faster Training and Lower Peak Memory
arXiv:2610.29538v1 Announce Type: new Abstract: Direct preference optimization (DPO) incurs training costs in output scoring, sequence execution, and backpropagation, so reducing supervision alone does not necessarily sa…
Broadcasting in Centimeter-Wave Gigantic MIMO Systems: Beam Shaping is All You Need
arXiv:2610.29542v1 Announce Type: new Abstract: Beamforming is a key enabling technology for centimeter-wave Gigantic MIMO (G-MIMO) systems, using antenna arrays to generate wide beams for cell-wide broadcasting or narro…
RISK-KV: Quality-Aware Selective KV Cache Reconstruction for Distributed LLM Inference
arXiv:2610.29544v1 Announce Type: new Abstract: Request migration and interruption recovery in distributed large language model (LLM) inference rely on historical key-value (KV) caches. Retaining or transferring a comple…
PACE: Periodic and Channel-Aligned Encoding of Four-Bit Recurrent States
arXiv:2610.29545v1 Announce Type: new Abstract: Linear-attention language models keep their context in a recurrent state of fixed size, where an inference system stores one copy of this state for every sequence it decode…
Sequential Entropic Optimal Transport for Bayesian Inverse Problems via Multilevel Monte Carlo
arXiv:2610.29546v1 Announce Type: new Abstract: We consider the problem of Bayesian estimation associated to inverse problems governed by partial differential equations (PDEs). In most cases of practical interest, one mu…
On the Effectiveness of Snapshot Testing: An Empirical Study
arXiv:2610.29549v1 Announce Type: new Abstract: Software testing is essential for ensuring quality, yet testing complex front-end user interfaces is often time-consuming and difficult. Snapshot testing has emerged as a l…
Hyperspherical Simplex Representations for Backward-Compatible Retrieval
arXiv:2610.29550v1 Announce Type: new Abstract: Training modern AI models has become increasingly expensive, and updating deployed models can alter their internal feature representations, affecting applications built upo…
Generalized CycleGRPO for Fine-Grained Multimodal Understanding and Grounding
arXiv:2610.29552v1 Announce Type: new Abstract: Fine-grained multimodal intelligence requires models to both understand a designated region and localize it from language. Existing methods learn these directions with sepa…
Dynamical low-rank approximations for the optimal control of matrix ODEs
arXiv:2610.29554v1 Announce Type: new Abstract: We consider the open-loop optimal control of a dynamical system whose state is described by a time-dependent matrix $X(t)\in\mathbb{R}^{m\times n}$. Gradient-based optimiza…