3462 papers
ReTac-ACT is a state-gated vision-tactile fusion transformer that achieves high-precision assembly in occluded, contact-rich environments by dynamically prioritizing tactile feedback through bidirectional cross-attention and proprioception-conditioned gating, outperforming vision-only baselines on the NIST Assembly Task Board M1 benchmark.
The paper introduces GeoAlignCLIP, a unified framework that enhances fine-grained vision-language alignment in remote sensing by leveraging multi-granular semantic learning and intra-modal consistency, supported by a newly constructed hierarchical dataset (RSFG-100k) to outperform existing methods on diverse benchmarks.
This paper presents a case study demonstrating that a virtualized XRootD frontend architecture, utilizing a heterogeneous VM cluster with BBR congestion control and TCP extensions, successfully sustained an aggregate throughput of 51.3 Gb/s and peaked at 41.5 Gb/s to Fermilab under high-intensity WAN transfer conditions.
This paper introduces the Panorama-Language Modeling (PLM) paradigm and the PanoVQA dataset to enable holistic $360^\circ$ vision-language reasoning in adverse omni-scenes, demonstrating that a unified panoramic approach yields superior understanding compared to stitching multiple narrow-field-of-view inputs.
This paper introduces BinaryAttention, a theoretically grounded method that replaces floating-point dot products with 1-bit sign-based operations and learnable biases to achieve over 2x speedup over FlashAttention2 while matching or exceeding full-precision accuracy in vision and diffusion transformers.
This paper presents a proprioception-only framework for quadrupedal robots that combines a 2.5-D terrain estimation method with safety-critical control barrier functions to achieve robust state estimation and rigorous safety guarantees on uneven terrain.
This paper proposes a game-theoretic framework for modeling stealthy Advanced Persistent Threat (APT) defense on attack graphs, where a defender strategically deploys sensors to secure critical assets against an MDP-based attacker operating under asymmetric temporal dynamics and varying levels of informational knowledge.
This paper proposes a two-phase coverage control method based on the Generalized Voronoi Graph that achieves efficient multi-robot coverage in non-convex environments by first partitioning the region and balancing robot allocation according to sub-region quality, followed by a collaborative coverage phase with a new controller.
This paper introduces a genetic programming-based method for the symbolic discovery of stochastic differential equations that jointly optimizes drift and diffusion functions via maximum likelihood estimation, enabling the accurate, scalable, and interpretable modeling of noisy dynamical systems.
This paper presents a project-based AI engineering curriculum that integrates agile practices with generative AI tools to prepare students for modern software development, demonstrating through a seven-sprint case study that embedding AI across the engineering lifecycle fosters hands-on competence while necessitating adaptations for tool evolution and foundational learning verification.
Nemo is a novel flash cache design that reduces application-level write amplification for tiny-object workloads by intentionally increasing hash collisions to improve set fill rates, while simultaneously maintaining high memory efficiency and low miss ratios through a bloom filter-based indexing mechanism and hybrid hotness tracking.
The paper proposes ParTY, a novel framework that improves text-to-motion synthesis by introducing part-guided networks, part-aware text grounding, and holistic-part fusion to overcome the limitations of existing methods in aligning specific body part actions with text while maintaining full-body motion coherence.
This paper proposes a saccade-inspired image classification method that leverages DINO's Vision Transformer attention maps to selectively focus processing on task-relevant regions, achieving performance comparable to or better than full-image analysis while offering a biologically plausible approach to efficient visual processing.
This paper proposes a zero-shot MRI super-resolution framework that leverages explicit, physics-driven 3D Gaussian representations and parallel brick-based rasterization to achieve high-quality, efficient reconstruction without relying on costly paired training data.
This paper introduces Quantization-aware Distilled Restoration (QDR), a novel framework that employs Decoder-Free Distillation and Learnable Magnitude Reweighting to overcome bottlenecks in quantization-aware training, enabling high-performance, edge-deployed image restoration models that achieve near-FP32 accuracy and significant speedups.
This paper presents OTPL-VIO, a robust stereo visual-inertial odometry system that enhances performance in low-texture and illumination-challenging environments by employing a training-free deep descriptor with entropy-regularized optimal transport for line association and introducing adaptive uncertainty weighting to stabilize estimation.
This paper initiates the study of proportionality degree in participatory budgeting by establishing tight theoretical bounds for the Method of Equal Shares and Phragmen's Sequential Rule, demonstrating that despite their differing axiomatic properties, they achieve comparable quantitative proportionality, a finding further validated through extensive experiments on real-world datasets.
The paper presents DiffWind, a physics-informed differentiable framework that unifies wind-object interaction modeling, video-based reconstruction, and forward simulation by combining 3D Gaussian Splatting, the Material Point Method, and Lattice Boltzmann constraints to accurately recover and simulate wind-driven object dynamics from video observations.
VarSplat is an uncertainty-aware 3D Gaussian Splatting SLAM system that explicitly learns per-splat appearance variance to render differentiable uncertainty maps, thereby guiding tracking and optimization toward reliable regions to achieve robust pose estimation and high-fidelity reconstruction in challenging real-world environments.
This paper introduces FootMR, a method that refines 3D foot motion in markerless monocular human motion capture by lifting 2D keypoints to 3D using large-scale motion capture data and context-aware residual prediction, alongside the new MOOF dataset, to significantly outperform existing state-of-the-art approaches in accuracy and generalization.