8091 papers
This paper presents a multi-layer Sim-to-Real framework that utilizes VR-collected eye-head data to train and evaluate gaze-driven controllers for a powered neck exoskeleton, ultimately demonstrating the necessity of personalized control strategies to effectively assist individuals with dropped head syndrome.
This paper introduces AceMAD, a multi-agent debate framework that overcomes the "Martingale Curse" of standard methods by leveraging asymmetric cognitive potential energy—where truth-holders anticipate collective misconceptions—to transform agent convergence from a random walk into a directed drift toward the correct answer.
This paper presents a hybrid machine learning model that combines VGG19, EfficientNet, and ResNet50 for feature extraction with a Bi-LSTM classifier to achieve a 98.83% accuracy in the early detection of Cerebral Palsy from MRI images, outperforming several individual pre-trained models.
This paper introduces "context specification" as a process to transform diffuse stakeholder perspectives into clear, measurable constructs, thereby bridging the gap between abstract AI evaluation methods and the operational realities necessary for successful, value-driven AI deployment.
This paper argues that in decentralized multi-agent reinforcement learning, the instability of the agent-world boundary caused by peer-policy updates leads to the erosion of invariant decision cores, thereby framing the challenge as a continual learning problem driven by boundary drift rather than exogenous task switches.
This study utilizes AI-assisted curation to compile and analyze a comprehensive database of 23,793 presentations from the Society for Social Work and Research Annual Conference (2005–2026), revealing significant growth in participation, collaboration, and international engagement alongside a continued predominance of quantitative research methods.
This paper introduces NetFI, a novel fault injection tool, to comprehensively analyze how packet loss, delay, and communication loss impact telesurgical task performance and motion primitives across different proficiency levels, providing quantitative insights and open-source resources to define operational boundaries and guide the development of robust network-aware control strategies.
This paper establishes that the quality of a model's step-level visual grounding, quantified by the Step Grounding Rate (SGR), serves as a robust and independent predictor of out-of-distribution generalization in long-horizon vision-language models, outperforming traditional final-answer accuracy metrics.
This paper proposes a receding-horizon, actuation-aware control allocation strategy for fully actuated omnidirectional UAVs that utilizes nullspace optimization and Constrained iterative LQR to anticipate and suppress asymmetric motor-induced oscillations, thereby significantly improving trajectory tracking performance compared to conventional methods.
This paper presents a case study demonstrating how a Master of Social Work program utilized a locally deployed AI model to analyze over 40,000 job postings, generating actionable workforce intelligence on practice specializations and required competencies to inform strategic curriculum planning.
RoboCritics is a novel framework that enhances the safety and reliability of end-to-end LLM-based robot programming by integrating expert-informed critics to detect motion-level violations, provide transparent feedback, and enable iterative refinement through a human-in-the-loop interface.
This paper introduces MotionBits, a novel concept and learning-free segmentation method that identifies the smallest manipulable rigid bodies through kinematic spatial twist equivalence, outperforming state-of-the-art embodied perception models on the new MoRiBo benchmark and enabling more effective downstream robotic manipulation and reasoning tasks.
This paper presents a comprehensive taxonomy of faults in agentic AI systems, derived from a large-scale empirical study of 13,602 issues and validated by 145 practitioners, which categorizes 37 distinct fault types, their symptoms, and root causes to reveal critical propagation patterns and mismatches between probabilistic LLM outputs and deterministic system constraints.
This paper introduces Twitch, a tool that automatically discovers reusable term abstractions from failed or successful proofs to enhance the performance of the Twee equational theorem prover, resulting in the solution of new problems and significant speed-ups on existing benchmarks.
This paper introduces the Latency-Aware Vision Teleoperation (LAVT) testbed to systematically demonstrate that vision-based teleoperation for autonomous vehicles suffers a sharp, nonlinear collapse in closed-loop stability when one-way perception latency exceeds 150–225 ms, a degradation significantly compounded by additional control-channel delays.
This paper introduces Perturbed Gaussian Ensemble, an active view selection framework for sparse-view CT that leverages stochastic density scaling of uncertain Gaussian primitives to identify high-variance projections, thereby significantly improving reconstruction fidelity and reducing geometric artifacts compared to existing methods.
This paper introduces a mechanistic interpretability approach to identify "audio-specialist" attention heads in large audio-language models, enabling a parameter-free inference-time steering technique that significantly boosts audio grounding and accuracy by amplifying the model's reliance on audio evidence.
A randomized experiment involving 400 participants reveals that while AI assistance can enhance both performance and pleasure in close reading poems, the benefits are optimized with a single interpretation rather than multiple, as heavy reliance on AI improves task performance but diminishes the enjoyment of the experience.
This study evaluates four multi-agent LLM topologies for rare disease diagnosis, revealing that while hierarchical structures marginally outperform single-agent baselines, increased complexity does not guarantee better reasoning and can significantly degrade performance through artificial doubt, thus supporting a shift toward dynamic topology selection.
This paper introduces PVBench, a benchmark demonstrating that over 40% of patches generated by automated vulnerability repair systems are falsely validated as correct because they fail to pass critical "PoC+" tests that encode developer intentions, root cause locations, and specific coding conventions.