arXiv:2603.24750v2 Announce Type: replace-cross Abstract: Online Health Communities connect patients for peer support, but users face a discovery challenge when they have minimal prior interactions to guide personalization. We study recommendation under extreme interaction sparsity in a survey driven setting where each user provides a 16 dimensional intake vector and each support group has a […]
Growth-rate distributions at stationarity
arXiv:2603.29916v1 Announce Type: cross Abstract: We propose new analytical tools for describing growth-rate distributions generated by stationary time-series. Our analysis shows how deviations from normality are not pathological behaviour, as suggested by some traditional views, but instead can be accounted for by clean and general statistical considerations. In contrast, strict normality is the effect of […]
Turbo4DGen: Ultra-Fast Acceleration for 4D Generation
arXiv:2603.29572v1 Announce Type: cross Abstract: 4D generation, or dynamic 3D content generation, integrates spatial, temporal, and view dimensions to model realistic dynamic scenes, playing a foundational role in advancing world models and physical AI. However, maintaining long-chain consistency across both frames and viewpoints through the unique spatio-camera-motion (SCM) attention mechanism introduces substantial computational and memory […]
Improving Plan Execution Flexibility using Block-Substitution
arXiv:2406.03091v2 Announce Type: replace Abstract: Partial-order plans in AI planning facilitate execution flexibility due to their less-constrained nature. Maximizing plan flexibility has been studied through the notions of plan deordering, and plan reordering. Plan deordering removes unnecessary action orderings within a plan, while plan reordering modifies them arbitrarily to minimize action orderings. This study, in […]
Cost-Sensitive Neighborhood Aggregation for Heterophilous Graphs: When Does Per-Edge Routing Help?
arXiv:2603.24291v2 Announce Type: replace-cross Abstract: Recent work distinguishes two heterophily regimes: adversarial, where cross-class edges dilute class signal and harm classification, and informative, where the heterophilous structure itself carries useful signal. We ask: when does per-edge message routing help, and when is a uniform spectral channel sufficient? To operationalize this question we introduce Cost-Sensitive Neighborhood […]
Characterizing Open-Ended Evolution Through Undecidability Mechanisms in Random Boolean Networks
arXiv:2512.15534v2 Announce Type: replace Abstract: Discrete dynamical models underpin systems biology, but we still lack substrate-agnostic diagnostics for when such models can sustain genuinely open-ended evolution (OEE): the continual production of novel phenotypes rather than eventual settling. We introduce a simple, model-independent metric, Omega, that quantifies OEE as the residence-time-weighted average of attractor cycle lengths […]
Generating Key Postures of Bharatanatyam Adavus with Pose Estimation
arXiv:2603.29570v1 Announce Type: cross Abstract: Preserving intangible cultural dances rooted in centuries of tradition and governed by strict structural and symbolic rules presents unique challenges in the digital era. Among these, Bharatanatyam, a classical Indian dance form, stands out for its emphasis on codified adavus and precise key postures. Accurately generating these postures is crucial […]
Early Exiting Predictive Coding Neural Networks for Edge AI
arXiv:2309.02022v2 Announce Type: replace-cross Abstract: The Internet of Things is transforming various fields, with sensors increasingly embedded in wearables, smart buildings, and connected equipment. While deep learning enables valuable insights from IoT data, conventional models are too computationally demanding for resource-limited edge devices. Moreover, privacy concerns and real-time processing needs make local computation a necessity […]
Robust Safety Monitoring of Language Models via Activation Watermarking
arXiv:2603.23171v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can be misused to reveal sensitive information, such as weapon-making instructions or writing malware. LLM providers rely on $emphmonitoring$ to detect and flag unsafe behavior during inference. An open security challenge is $emphadaptive$ adversaries who craft attacks that simultaneously (i) evade detection while (ii) eliciting unsafe […]
Streaming 4D Visual Geometry Transformer
arXiv:2507.11539v2 Announce Type: replace-cross Abstract: Perceiving and reconstructing 3D geometry from videos is a fundamental yet challenging computer vision task. To facilitate interactive and low-latency applications, we propose a streaming visual geometry transformer that shares a similar philosophy with autoregressive large language models. We explore a simple and efficient design and employ a causal transformer […]
Bringing Up a Bilingual BabyLM: Investigating Multilingual Language Acquisition Using Small-Scale Models
arXiv:2603.29552v1 Announce Type: cross Abstract: Multilingualism is incredibly common around the world, leading to many important theoretical and practical questions about how children learn multiple languages at once. For example, does multilingual acquisition lead to delays in learning? Are there better and worse ways to structure multilingual input? Many correlational studies address these questions, but […]
Past, Present, and Future of Bug Tracking in the Generative AI Era
arXiv:2510.08005v3 Announce Type: replace-cross Abstract: Traditional bug-tracking systems rely heavily on manual reporting, reproduction, classification, and resolution, involving multiple stakeholders such as end users, customer support, developers, and testers. This division of responsibilities requires substantial coordination and human effort, widens the communication gap between non-technical users and developers, and significantly slows the process from bug […]