2443 papers
This paper presents a decentralized, communication-free learning framework for teams of quadruped robots to cooperatively transport ungraspable objects through physical contact alone, utilizing a hierarchical policy and a specialized reward formulation to achieve robust, scalable coordination without rigid mechanical coupling.
The paper introduces VocSegMRI, a multimodal framework that leverages cross-attention fusion and contrastive learning to integrate video, audio, and phonological signals, achieving state-of-the-art vocal tract segmentation in real-time MRI with a Dice score of 0.95 and robust performance even when audio is unavailable.
This paper presents the first large-scale empirical study of floating-point arithmetic usage in statically typed languages across millions of GitHub repositories, revealing that while existing benchmarks are partially representative, they do not fully capture real-world code patterns, and releasing a dataset of 10 million extracted functions to guide future reasoning techniques.
CoRe-GS is a coarse-to-refine Gaussian Splatting framework that accelerates 3D reconstruction for robotic applications by selectively optimizing only task-relevant points of interest, thereby significantly reducing training time and mitigating artifacts while maintaining high-quality semantic segmentation.
This paper introduces Adaptive Tamaraw, a unified framework that clusters traffic traces to dynamically apply lightweight, set-specific padding parameters, thereby achieving provable security against website fingerprinting attacks while significantly reducing communication overhead compared to traditional defenses.
YOPO is a minimalist, single-stage transformer framework that unifies 2D object detection and category-level 9-DoF pose estimation from monocular RGB images without requiring pseudo-depth or CAD models, achieving state-of-the-art performance on multiple benchmarks.
This paper introduces FieldLVLM, a novel framework that enhances Large Vision-Language Models' ability to interpret complex scientific field data by combining a specialized pipeline for extracting physical features into structured text with a data-compressed tuning strategy, resulting in superior performance on scientific benchmarks.
This paper introduces a large-scale, privacy-preserving dataset of ten years of user interactions on the Austrian newspaper DerStandard, comprising over 75 million comments and 400 million votes with anonymized identifiers and pre-computed vector embeddings to facilitate research on online discourse dynamics in the German language.
This paper proposes SpikeSMOKE, a low-power monocular 3D object detection framework based on Spiking Neural Networks that introduces a Cross-Scale Gating Coding mechanism and a lightweight residual block to overcome information loss and computational inefficiency, achieving superior performance on KITTI and other datasets while significantly reducing energy consumption and model complexity compared to traditional ANN-based approaches.
This paper presents a comprehensive empirical study evaluating state-of-the-art pre-trained and large language models for multilingual vulnerability detection across seven programming languages at both function and line levels, revealing that instruction-tuned GPT-4o significantly outperforms other models, particularly in identifying high-severity and unique multilingual vulnerabilities.
This paper introduces EasyText, a controllable Diffusion Transformer framework that leverages character positioning encoding and position interpolation to achieve high-quality, precise multilingual text rendering, supported by a newly constructed large-scale synthetic dataset for pretraining and fine-tuning.
This paper proposes MARRS, a novel framework that generates coordinated and fine-grained human reaction motions by combining a Unit-distinguished Motion VAE, Action-Conditioned Fusion with token masking, and Adaptive Unit Modulation to overcome the limitations of vector quantization and enhance inter-unit interaction.
This paper introduces M4-SAR, a large-scale, multi-resolution, multi-polarization, and multi-source dataset with nearly one million labeled instances, alongside a unified benchmarking toolkit and a novel end-to-end fusion framework (E2E-OSDet) that collectively advance optical-SAR object detection by demonstrating significant performance gains over single-source methods in complex environments.
This paper introduces inverse Tool-use Planning (iTuP) and its associated Stable Dynamic Grasp Network (SDG-Net), which enhance robotic tool use success by selecting grasps that minimize predicted task-induced wrench and torque rather than relying solely on perception or static geometry.
This paper introduces SPDL, an open-source, framework-agnostic library that significantly accelerates GPU data loading by leveraging concurrent thread pool execution with GIL release, achieving up to 74% faster iteration and reduced resource usage compared to PyTorch DataLoader while demonstrating further performance gains with Free-Threaded Python.
This paper introduces BR-Gen, a large-scale dataset of 150,000 locally forged images with diverse scene-aware annotations, and proposes NFA-ViT, a noise-guided Vision Transformer that amplifies subtle forgery traces to significantly improve the detection and generalization of localized AI-generated image forgeries.
This paper proposes a novel semi-supervised teacher-student framework for biomedical image segmentation that leverages denoising diffusion probabilistic models to generate and iteratively refine pseudo-labels, demonstrating superior performance over state-of-the-art methods in scenarios with limited annotated data.
This paper establishes an equivalence between right actegories with hom-objects and right-enriched categories with copowers over non-closed, non-symmetric monoidal bases, a generalization motivated by the need to support higher-order process passing in the concurrent language CaMPL.
This paper introduces NeurCC, a novel learned concurrency control algorithm that utilizes Bayesian optimization and a graph reduction search to efficiently learn a high-performance function mapping database states to control actions, thereby consistently outperforming state-of-the-art algorithms across diverse and dynamic workloads.
This paper introduces RS-STE, a novel unified framework that synergistically integrates text recognition and editing via a multi-modal parallel decoder and cyclic self-supervised fine-tuning to achieve state-of-the-art scene text editing performance on both synthetic and real-world benchmarks.