7189 papers
This paper bridges the gap between dynamic programming-based planning and reinforcement learning by developing a derandomized RL variant, mathematically analyzing the conditions under which their differing formulations (such as cost minimization versus reward maximization and goal termination versus infinite-horizon discounting) are equivalent, and advocating for the optimization of true cost over arbitrary parameters.
This paper proposes a unified, domain-agnostic framework for computing the bus-factor by modeling projects as bipartite graphs, proving the NP-hardness of both redundancy and criticality formulations, and introducing a novel robustness-based measure with efficient linear-time approximations that outperforms existing methods in capturing project risk and fragmentation.
This paper presents a systematic study demonstrating that LLM agents can be engineered to intentionally deceive other agents in multi-agent systems by inferring their motivations and employing strategic misdirection rather than fabrication, revealing that current fact-checking defenses are insufficient against such targeted attacks.
This paper offers a comprehensive practitioner-oriented guide to the UK's 2025 Cyber Security and Resilience Bill, detailing its expanded regulatory scope, stringent enforcement penalties, and incident reporting requirements while providing actionable compliance frameworks, sector-specific roadmaps, and self-assessment tools to help organizations align with the new legislation and related international standards.
SoundWeaver is a training-free, model-agnostic serving system that accelerates text-to-audio diffusion by warm-starting generation from semantically similar cached audio, achieving a 1.8–3.0× latency reduction while preserving perceptual quality.
This paper proposes a task-aware observation interface that canonicalizes raw RGB inputs into unified semantic-geometric representations using segmentation and depth injection, thereby significantly enhancing the robustness of visuomotor policies to out-of-distribution appearance shifts without requiring policy retraining.
This supplementary document provides a detailed correctness proof for the CoPPar architecture, which was introduced in the main CoPPar Tree paper.
This paper introduces a method using transfer entropy to identify influential robot actions during human-robot conversations, demonstrating its effectiveness in analyzing nonlinear interactions to improve robotic system design and adaptability.
This paper proposes Structure and Progress Aware Diffusion (SPAD), a novel framework for medical image segmentation that employs a progress-aware scheduler to guide a coarse-to-fine learning paradigm, utilizing semantic-concentrated and boundary-centralized diffusion modules to effectively balance stable anatomical structure understanding with the refinement of ambiguous target boundaries.
This paper proposes using image segmentation as a visual diagnostic framework for hedonic games, demonstrating how granularization parameters influence coalition equilibrium structures and their ability to recover foreground ground-truth on the Weizmann benchmark.
This paper proposes a new approach that leverages LaCAM*'s ability to construct a dynamic, lightweight traffic map during search, overcoming the computational overhead and static limitations of existing Frank-Wolfe-based guidance path methods to achieve higher solution quality in Multi-Agent Path Finding.
RoboRouter is a training-free framework that enhances robotic manipulation performance by intelligently routing diverse, off-the-shelf policies to the most suitable one for each task based on semantic representations and historical execution data, achieving significant success rate improvements in both simulation and real-world settings without requiring additional model training.
The paper introduces MINT, a fine-tuning framework that enhances pathology foundation models by integrating spatial transcriptomics supervision to bridge the gap between tissue morphology and molecular states, achieving superior performance in both gene expression prediction and general pathology tasks.
EveryQuery is a novel electronic health record foundation model that achieves efficient, zero-shot clinical prediction by directly estimating outcome likelihoods through task-conditioned pre-training, thereby outperforming computationally expensive autoregressive baselines—particularly for rare events—while currently facing limitations in complex disjunctive reasoning tasks.
This paper presents IOTEL, a tool designed to systematically generate IoT-enriched Object-Centric Event Logs (OCEL) by integrating heterogeneous IoT data with business process logs, thereby enabling effective analysis of IoT-enhanced processes without requiring specialized schemas or extensive preprocessing.
This paper proposes a robust control synthesis method for uncertain linear systems with input saturation by reformulating the problem within an integral quadratic constraints (IQC) framework, which yields improved -gain performance and numerically tractable LMI-based conditions compared to conventional static sector approaches.
This paper presents a vision-only autonomous bronchoscopy framework utilizing hierarchical long-short agents and a world-model critic to achieve accurate, sensor-free intraoperative navigation in preclinical models, demonstrating performance comparable to expert human operators.
This paper proposes a Concept-Guided Bayesian Framework for zero-shot image recognition that enhances Vision-Language Models by treating class-specific concepts as latent variables, utilizing an LLM-driven synthesis pipeline with diversity enforcement and a training-free adaptive soft-trim likelihood to achieve superior performance over heuristic prompting methods.
This paper proposes a streamlined learned video compression framework that replaces traditional motion estimation with a direct transform strategy, utilizing a cascaded Mamba module with embedded geometric transformations and a locality refinement network to achieve superior perceptual quality and temporal consistency at low bitrates.
The paper introduces Ares, a framework that dynamically selects the optimal reasoning effort level for each step of an LLM agent's task using a lightweight router, achieving up to 52.7% reduction in token usage with minimal impact on success rates compared to static high-effort strategies.