We investigate whether temporal embedding models trained on longitudinal electronic health records can learn clinically meaningful representations without compromising predictive performance, and how architectural choices affect embedding quality. Model-guided medicine requires representations that capture disease dynamics while remaining transparent and task agnostic, whereas most clinical prediction models are optimised for a single task. Representation learning facilitates learning embeddings that generalise across downstream tasks, and recurrent architectures are well-suited for modelling temporal structure in observational clinical data. Using the […]

Ver mais

State space models (SSMs) have recently emerged for modeling long-range dependency in sequence data, with much simplified computational costs than modern alternatives, such as transformers. Advancing SMMs to graph structured data, especially for large graphs, is a significant challenge because SSMs are sequence models and the shear graph volumes make it very expensive to convert graphs as sequences for effective learning. In this paper, we propose COMBA to tackle large graph learning using state space models, with two […]

Ver mais

Clinejection — Compromising Cline’s Production Releases just by Prompting an Issue Triager Adnan Khan describes a devious attack chain against the Cline GitHub repository, which started with a prompt injection attack in the title of an issue opened against the repo. Cline were running AI-powered issue triage using the anthropics/claude-code-action@v1 action, configured to run Claude Code with –allowedTools “Bash,Read,Write,…” any time any user opened an issue in their repo. The configured prompt included the issue title, which meant […]

Ver mais

arXiv:2504.11279v2 Announce Type: replace-cross Abstract: The analysis of data from multiple experiments, such as observations of several individuals, is commonly approached using mixed-effects models, which account for variation between individuals through hierarchical representations. This makes mixed-effects models widely applied in fields such as biology, pharmacokinetics, and sociology. In this work, we propose a novel methodology for scalable Bayesian inference in hierarchical mixed-effects models. Our framework first constructs amortized approximations of the likelihood and the posterior distribution, which are […]

Ver mais

We relate function class complexity to structure in the function domain. This facilitates risk analysis relative to cluster structure in the input space which is particularly effective in semi-supervised learning. In particular we quantify the complexity of function classes defined over a graph in terms of the graph structure.

Ver mais

We give new differentially private algorithms for the classic problems of learning decision lists and large-margin halfspaces in the PAC and online models. In the PAC model, we give a computationally efficient algorithm for learning decision lists with minimal sample overhead over the best non-private algorithms. In the online model, we give a private analog of the influential Winnow algorithm for learning halfspaces with mistake bound polylogarithmic in the dimension and inverse polynomial in the margin. As an […]

Ver mais

Accurate, large-scale building-use information at very high spatial resolution is critical for urban, economic, and risk-related applications. We present a nationwide framework for building-use mapping at 50~cm resolution in China by fusing very-high-resolution RGB imagery with points-of-interest (POI) data. A multi-task U-Net with a ResNet-34 backbone jointly predicts building footprints and three building-use classes (residential, commercial, industrial), using POI-based probability maps as additional input channels. We construct a labeled dataset of approximately 100{,}000 buildings from 90 cities and […]

Ver mais

arXiv:2601.03416v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have become widely deployed, yet their safety alignment remains fragile under adversarial inputs. Previous work has shown that increasing inference steps can disrupt safety mechanisms and lead MLLMs to generate attacker-desired harmful content. However, most existing attacks focus on increasing the complexity of the modified visual task itself and do not explicitly leverage the model’s own reasoning incentives. This leads to them underperforming on reasoning models (Models with […]

Ver mais

In the world of Generative AI, latency is the ultimate killer of immersion. Until recently, building a voice-enabled AI agent felt like assembling a Rube Goldberg machine: you’d pipe audio to a Speech-to-Text (STT) model, send the transcript to a Large Language Model (LLM), and finally shuttle text to a Text-to-Speech (TTS) engine. Each hop added hundreds of milliseconds of lag. OpenAI has collapsed this stack with the Realtime API. By offering a dedicated WebSocket mode, the platform […]

Ver mais