6510 papers
This paper presents ZipLex, a formally verified framework in Scala that achieves linear-time invertible lexical analysis with longest-match semantics by combining a novel token sequence abstraction with verified data structures like zippers and memoization, demonstrating performance comparable to unverified tools while providing rigorous proofs of correctness and invertibility.
This paper presents a sample-based hybrid mode control framework that formulates mode selection, switching timing, and duration as an integer optimization problem to achieve asymptotically optimal, reactive switching between non-differentiable and algorithmic control strategies for complex robotic tasks.
This paper proposes a multi-UAV flood monitoring strategy using Centroidal Voronoi Tessellation with a Gaussian Mixture of Density Functions to model inundation areas, demonstrating through ROS/Gazebo simulations that this approach achieves superior coverage rates and spatial distribution compared to conventional axis-aligned Gaussian models across various fleet sizes.
This paper introduces Consensus Complementarity Control Plus (C3+), an enhanced contact-implicit model predictive control algorithm that enables a complete robotic pipeline to robustly and efficiently push diverse single and multi-object configurations to target poses in real-time, achieving a 98% success rate on hardware.
This paper introduces AURASeg, an attention-guided segmentation framework featuring a Residual Boundary Refinement Module and an Attention Progressive Upsampling Decoder to enhance drivable-area boundary precision and multi-scale feature representation for onboard robot navigation, demonstrating superior performance on multiple datasets and successful deployment on a Jetson Nano.
This paper proposes and evaluates four augmented reality indicators designed to visualize a robot's field of view, finding that allocentric indicators placed in the task space and egocentric indicators modifying the robot's eyes effectively improve human accuracy in collaborative tasks while maintaining high confidence and low cognitive load.
This paper resolves a key open question from Gorantla et al. by deriving explicit upper bounds on the number of item copies required to guarantee envy-free allocations for arbitrary numbers of agent groups and item types, using a novel constructive technique that extends to both chores and continuous fair division settings.
This paper introduces CULTIVate, a comprehensive benchmark and evaluation framework designed to assess the cultural faithfulness of text-to-image models in depicting social activities across 16 countries, revealing significant performance disparities between Global North and South regions and demonstrating that its proposed metrics align more closely with human judgment than existing standards.
ExpReS-VLA is a specialized Vision-Language-Action model that enables rapid, memory-efficient on-device adaptation to specific robotic tasks by combining compressed experience replay, retrieval-augmented generation, and a novel contrastive loss to prevent catastrophic forgetting while significantly improving performance on both spatial and long-horizon benchmarks.
The paper introduces CAVER, a novel robot equipped with a specialized audio-exciting end-effector, a combined audiovisual representation, and a curiosity-driven exploration algorithm that efficiently learns object correlations to improve material classification and audio-only imitation tasks.
This paper proposes a dual-mechanism collaborative optimization framework that synergistically integrates structural fairness decoupling and global distribution alignment to enhance both inter-group and intra-group fairness in deepfake detection without compromising overall accuracy.
This habilitation thesis investigates polynomial algorithmics under space constraints, presenting time- and space-efficient algorithms for fundamental operations and introducing the first quasi-linear algorithm for sparse polynomial interpolation while addressing hard problems in sparse factorization and divisibility.
LaxMotion is a novel framework for 3D human motion generation that replaces precise 3D coordinate supervision with a relaxed paradigm based on global trajectories and monocular 2D cues, thereby enhancing model generalization and diversity while achieving performance comparable to fully supervised methods.
This paper presents a Coq-based formalization that extends Tarski's mereogeometry into a full topological space by proving the correspondence between mereological classes and regular open sets, thereby reducing Tarski's axiomatic system and enhancing its expressiveness for Euclidean geometric reasoning.
This paper introduces SPARK, a jailbreak framework that exploits cross-modal associations in text-to-video models by combining neutral scene anchors, latent auditory triggers, and stylistic modulators to generate semantically unsafe videos that bypass safety guardrails while maintaining a benign appearance.
The paper introduces MRIQT, a physics-aware 3D conditional diffusion model that significantly enhances the image quality and diagnostic fidelity of portable ultra-low-field neonatal MRI by translating noisy scans into high-fidelity images comparable to high-field MRI.
This paper proposes a contact-safe reinforcement learning framework that combines Proximal Policy Optimization with movement primitives and an energy-aware Cartesian impedance controller to generate robust, safe, and energy-efficient task-space trajectories for complex contact-rich manipulation in 3D environments.
This paper introduces WNumMPC, a hierarchical multi-agent navigation framework that combines a reinforcement learning-based planner and a model-based controller to resolve symmetry-induced deadlocks in dense environments by leveraging topological winding numbers for robust, communication-free coordination.
The paper introduces FunnyNodules, a fully parameterized synthetic dataset of lung nodule-like shapes with controllable visual attributes and known decision rules, designed to systematically evaluate and benchmark explainable AI models by verifying whether they learn correct attribute-target relations and align their attention with relevant diagnostic features.
Bi-AQUA is a novel bilateral control-based imitation learning framework for underwater robot arms that integrates transformer-based action chunking with explicit lighting modeling to achieve robust performance in challenging, variable illumination conditions.