3836 papers
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.
This paper introduces ColonSplat, a dynamic Gaussian Splatting framework that achieves superior 3D reconstruction of peristaltic colon motion by preserving global geometric consistency, supported by a new synthetic benchmark dataset called DynamicColon and a critical analysis of existing methods' limitations.
This paper proposes a hardware-efficient trajectory prediction framework that integrates environmental priors with a Dual-Transformer-Cascaded (DTC) architecture to accurately predict the landing points of flying objects, such as tennis balls, by outperforming existing methods in complex real-world scenarios.
The paper introduces Robodimm, a physics-grounded software framework that automates actuator sizing for scalable modular robots by leveraging Pinocchio and Pink to solve constrained inverse dynamics via a Karush-Kuhn-Tucker formulation, thereby addressing the complexities of coupled joint torques and self-weight effects in closed kinematic chains.
The paper proposes CAR, a novel framework that leverages a Transformer encoder with Adaptive Layer Normalization to map diverse vehicle configurations into a shared latent space, enabling rapid and data-efficient kinodynamic adaptation for new autonomous off-road platforms with minimal training data.
The paper introduces Lookahead-Enhanced Atomic Decomposition (LEAD), a method that mitigates the "no-recovery bottleneck" caused by extreme decomposition in long-horizon reasoning by integrating short-horizon future validation and overlapping rollouts, thereby enabling models like o4-mini to solve complex algorithmic puzzles beyond the limits of previous approaches.
The paper introduces PICS, a self-supervised framework that improves pairwise image compositing by employing an Interaction Transformer with mask-guided Mixture-of-Experts and adaptive blending to explicitly model spatial interactions and preserve physical consistency between objects and backgrounds.
This study reveals that while the correctness of LLM-generated reasoning is the primary driver of user accuracy in critical thinking tasks, medium-length explanations uniquely enhance users' ability to detect errors when the AI's reasoning is incorrect, suggesting that response length plays a nuanced role in shaping human critical evaluation.
This paper proposes a framework for Material Driven HRI Design that leverages color, texture, and material choices as interaction signals to enhance robot explainability, clarify roles, and align user expectations with actual capabilities.
This paper introduces "notational animating," an interactive animation authoring paradigm that enables users to sketch high-level notations over static drawings, which are then interpreted by AI into formalized animation keyframes through a structured representation and a closed feedback loop for resolving ambiguity.