3447 papers
This paper generalizes optimal partition selection algorithms to Rényi differential privacy, introducing an improved mechanism for bounded weighted partitions that enhances state-of-the-art methods while demonstrating a fundamental performance gap between additive and non-additive noise approaches when frequency data is also released.
The paper proposes Progressive Split-Mamba (PS-Mamba), a topology-aware hierarchical state-space framework that addresses the spatial distortion and long-range decay limitations of standard Mamba models in image restoration by employing geometry-consistent partitioning and symmetric cross-scale shortcuts to effectively balance local structural preservation with global coherence.
The paper introduces SAGE, the first end-to-end multi-modal large language model that treats raw point clouds as a "foreign language" via a lightweight 3D tokenizer and semantic alignment-based preference optimization, achieving superior performance and efficiency over existing encoder-based methods in 3D understanding tasks.
This paper introduces STONE, a large-scale, multi-modal off-road dataset featuring synchronized LiDAR, camera, and radar data with automated, annotation-free 3D traversability labels, alongside a new benchmark for voxel-level traversability prediction.
This paper evaluates the practical effectiveness of LLM-driven index tuning against Microsoft's Database Tuning Advisor (DTA) using industrial and real-world workloads, finding that while LLMs can identify superior configurations and capture human-intuitive insights, their substantial performance variance and high validation costs currently limit their direct adoption in production as a standalone replacement for DTA.
This paper presents a robust spatiotemporal motion planning framework for multi-agent autonomous racing that combines topological gap identification via stochastic Gaussian processes with a PTC-accelerated Linear Time-Varying MPC to achieve high-speed overtaking with strict kinematic feasibility and significantly reduced computational latency.
ZipPIR is a high-throughput single-server Private Information Retrieval protocol that achieves over 2 GB/s performance without requiring client-side storage by compressing LWE ciphertexts into Paillier ciphertexts during an almost silent offline phase, thereby overcoming the scalability and dynamic database limitations of existing solutions.
This paper proposes a hierarchical Observe-Orient-Decide-Act (H-OODA) framework that integrates cloud-edge-terminal layers and network function virtualization to enhance the adaptability, scalability, and decision-making efficiency of UAV swarms operating in uncertain environments.
WESPR is a lightweight, real-time framework that integrates geometric perception and local weather data to predict wind fields generated by environmental obstacles, enabling quadrotors to proactively plan safe, energy-efficient paths and adapt control strategies for robust flight in turbulent conditions.
This paper proposes a geometry-aware metric learning framework using rotation- and scale-invariant inter-joint angle descriptors derived from static hand keypoints to achieve robust cross-lingual few-shot sign language recognition, significantly outperforming conventional coordinate-based methods across diverse sign languages.
This paper introduces PIM-SHERPA, a software-only method that resolves memory attribute and layout inconsistencies in product-level PIM-enabled systems to enable efficient on-device LLM inference, achieving significant memory capacity savings while maintaining near-theoretical performance.
TubeMLLM is a unified foundation model that integrates topological priors via natural language prompting and a shared-attention architecture to achieve state-of-the-art, robust, and zero-shot generalizable topology-aware perception and generation for vessel-like anatomy across diverse medical imaging modalities.
This paper proposes a lightweight distributed convolutional neural network (DisCNN) trained with a novel loss function that maps positive samples to a compact high-dimensional space while pushing negative samples to the origin, thereby disentangling positive-class features to achieve robust object recognition and detection even in complex backgrounds and for unseen classes.
The paper introduces UniField, a unified framework that leverages pre-trained 3D foundation models and a novel Field-Aware Spectral Rectification Mechanism to overcome data scarcity and spectral bias in MRI field-strength enhancement, supported by the release of a large-scale multi-field dataset that significantly outperforms state-of-the-art methods.
The paper introduces TRIP-Bag, a portable, suitcase-contained teleoperation system that enables rapid, high-fidelity data collection for robot learning by eliminating the embodiment gap through direct joint-to-joint control in diverse, non-laboratory environments.
This paper introduces Flash-KMeans, an IO-aware and contention-free GPU implementation that eliminates memory bottlenecks in the assignment stage and resolves atomic write contention in the update stage through novel kernel-level innovations, achieving up to 17.9 speedup over existing baselines and enabling -means as a high-performance online primitive.
HelixTrack is a fully event-driven method that jointly tracks propeller-like objects and estimates their RPM with microsecond latency by back-warping events to a rotor plane and refining pose through phase-coupled geometry, validated on a newly introduced TQE dataset where it outperforms existing baselines.
This paper introduces MORLAX, a GPU-native multi-objective reinforcement learning algorithm, and MO-Playground, a suite of GPU-accelerated environments, which together enable massively parallelized training that achieves 25–270x speedups and superior Pareto fronts for complex robotics tasks compared to legacy CPU-based approaches.
The paper proposes RAE-NWM, a navigation world model that operates in a dense DINOv2 feature space using a Conditional Diffusion Transformer with a decoupled head and time-driven gating to achieve superior structural stability and action accuracy compared to traditional latent-space approaches.
This paper introduces Geometric Semantic Decoupling (GSD), a parameter-free module that enhances the generalizability of AI-generated image detectors by explicitly removing dominant semantic priors from learned representations, thereby forcing models to rely on robust forensic artifacts rather than failing via "semantic fallback" when encountering unseen generation pipelines.