4743 papers
The paper presents "Guardian," an interpretable, three-layer decision-support system that combines Markov chains, reinforcement learning, and LLM-based validation to generate dynamic, probabilistic search plans for missing-child investigations within the critical first 72 hours.
PathoScribe is a unified retrieval-augmented large language model framework that transforms static pathology archives into an active, reasoning-enabled clinical intelligence platform, enabling natural language case retrieval, automated cohort construction, and real-time diagnostic support with high accuracy and efficiency.
The paper introduces VoxEmo, a comprehensive benchmark and toolkit for evaluating Speech Large Language Models on speech emotion recognition across 35 corpora and 15 languages, featuring a distribution-aware soft-label protocol that reveals how these models uniquely align with human subjective emotion distributions despite trailing supervised baselines in hard-label accuracy.
This paper proposes "AgentOS," a new paradigm that replaces traditional GUI-based operating systems with a natural language-driven ecosystem centered on an Agent Kernel, framing the realization of such a system as a Knowledge Discovery and Data Mining (KDD) challenge involving intent mining, workflow automation, and dynamic personal knowledge graphs.
The paper introduces BiCLIP, a simple and parameter-efficient framework that achieves state-of-the-art few-shot domain adaptation for vision-language models by applying a structured geometric transformation to align multimodal features across disparate domains using a small set of anchor samples.
This paper introduces Guardian, a consensus-driven, multi-LLM pipeline enhanced by QLoRA fine-tuning that coordinates specialized models and a consensus engine to perform auditable, structured information extraction for critical missing-person investigations while avoiding unconstrained decision-making.
This paper introduces \texttt{EinSum}, a tensor-relational extension of Einstein Summation Notation that automatically rewrites computations to leverage efficient numerical kernels for dense operations while utilizing relational systems to manage large-scale sparsity.
This paper introduces the FaBRIC strategy, which integrates new scalable backward reachability algorithms with existing forward analysis techniques to significantly improve the verification of reach-avoid specifications in nonlinear neural feedback systems.
This paper introduces Semantic Level of Detail (SLoD), a framework that utilizes heat kernel diffusion on hyperbolic manifolds to enable continuous, principled control over knowledge abstraction levels in AI memory systems, automatically detecting emergent semantic boundaries in both synthetic and real-world knowledge graphs without manual supervision.
This paper introduces Arbiter, a framework that combines formal rules with multi-model LLM analysis to detect interference patterns in coding agent system prompts, revealing that prompt architecture influences failure types and that multi-model evaluation uncovers distinct vulnerabilities missed by single-model approaches.
This study systematically characterizes the unique threat landscape of multi-agent AI systems and empirically evaluates 16 security frameworks, revealing that none achieve majority coverage of the identified risks, with Non-Determinism and Data Leakage being the most under-addressed domains.
This paper analyzes gender bias in audio deepfake detection using the ASVspoof 5 dataset and a ResNet-18 classifier, demonstrating that while aggregate metrics like Equal Error Rate may suggest low disparity, fairness-aware evaluation reveals significant gender-specific error distributions that necessitate more equitable and robust detection systems.
This paper introduces CMA-ES-IG, an algorithm that enhances robot preference learning by generating perceptually distinct and informative queries, thereby improving scalability, robustness, and user experience compared to existing state-of-the-art methods.
Meissa is a lightweight, 4B-parameter offline medical multi-modal agent that achieves state-of-the-art performance across diverse clinical benchmarks by employing novel trajectory modeling and stratified supervision to distill frontier model capabilities, thereby offering a cost-effective, low-latency, and privacy-preserving alternative to API-dependent systems.
This paper proposes "AI phenomenology" as a research framework that prioritizes users' first-person lived experiences over traditional performance metrics to better understand and guide the bidirectional alignment between humans and AI systems, offering a set of methodological tools, design concepts, and a research agenda derived from three empirical studies.
The paper introduces MEMO, a memory-augmented self-play framework that optimizes inference-time context through structured memory retention and uncertainty-aware prompt exploration, significantly improving the win rates and run-to-run stability of multi-agent LLMs in long-horizon, imperfect-information games.
This paper introduces Pichay, a demand paging system that treats LLM context windows as a memory hierarchy rather than a static cache, successfully reducing context consumption by up to 93% in production by evicting stale content and dynamically reloading it only when needed.
This paper presents an automated pipeline leveraging Large Language Models to detect and diagnose flaky tests in quantum software, successfully expanding an existing dataset by 54% and demonstrating that models like Google Gemini can achieve high accuracy (F1-scores up to 0.9643) in classifying flakiness and identifying root causes.
PlayWorld introduces a fully autonomous pipeline that trains high-fidelity, physically consistent video world models from unsupervised robot self-play, outperforming human-collected data in predicting complex interactions and significantly boosting real-world reinforcement learning success rates.
This paper introduces WS-Net, a deep unmixing framework that combines state-space modeling, wavelet-fused encoding, and a specialized weak signal attention mechanism to effectively recover weak spectral signals and significantly improve abundance estimation accuracy in hyperspectral images under low signal-to-noise conditions.