Stay updated with the latest research and technology news
arXiv:2511.01266v5 Announce Type: replace Abstract: Current motion-conditioned video generation methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction. We...
arXiv:2511.03153v2 Announce Type: replace Abstract: Large Language Models (LLMs) have substantially influenced various software engineering tasks. Indeed, in the case of software refactoring, traditional LLMs...
arXiv:2511.04439v3 Announce Type: replace Abstract: Group-Relative Policy Optimization (GRPO) has emerged as the standard for training reasoning capabilities in large language models through reinforcement learning....
arXiv:2511.08344v3 Announce Type: replace Abstract: Surface electromyography (sEMG)-based gesture recognition plays a critical role in human-machine interaction (HMI), particularly for rehabilitation and prosthetic control. However,...
arXiv:2511.11086v2 Announce Type: replace Abstract: Complex multilayer network datasets have become ubiquitous in various applications, including neuroscience, social sciences, economics, and genetics. Notable examples include...
arXiv:2511.11391v2 Announce Type: replace Abstract: Phase-time arrays, which integrate phase shifters (PSs) and true-time delays (TTDs), have emerged as a cost-effective architecture for generating frequency-dependent...
arXiv:2511.11991v3 Announce Type: replace Abstract: Time series forecasting is crucial for applications in various domains. Conventional methods often rely on global decomposition into trend, seasonal,...
arXiv:2511.12185v3 Announce Type: replace Abstract: Data is found everywhere, from health and human infrastructure to the surge of sensors and the proliferation of internet-connected devices....
arXiv:2511.13197v2 Announce Type: replace Abstract: Ultrasound (US) machines display images on a built-in monitor, but routine transfer to hospital systems relies on DICOM. We propose...
arXiv:2511.13306v2 Announce Type: replace Abstract: Gaining sustainable performance improvement with scaling data and model budget remains a pivotal yet unresolved challenge in autonomous driving. While...
arXiv:2511.14599v2 Announce Type: replace Abstract: The accurate segmentation of brain tumors from multi-modal MRI is critical for clinical diagnosis and treatment planning. While integrating complementary...
arXiv:2511.16786v2 Announce Type: replace Abstract: Multimodal large language models suffer from substantial inference overhead since multimodal KV Cache grows proportionally with the visual input length....
arXiv:2511.17781v2 Announce Type: replace Abstract: We present a novel, regulator-driven approach for the temporal verification of black-box autonomous robot policies, inspired by real-world certification processes...
arXiv:2511.17929v2 Announce Type: replace Abstract: Temporal Action Detection (TAD) aims to identify and localize actions by determining their starting and ending frames within untrimmed videos....
arXiv:2511.18140v2 Announce Type: replace Abstract: We propose Observer Actor (ObAct), a novel framework for active vision imitation learning in which the observer moves to optimal...
arXiv:2511.19854v3 Announce Type: replace Abstract: Reconstructing high-fidelity and animatable 3D head avatars from monocular videos remains a challenging yet essential task. Existing methods based on...
arXiv:2511.21033v2 Announce Type: replace Abstract: Legal decisions should be logical and based on statutory laws. While large language models(LLMs) are good at understanding legal text,...
arXiv:2511.21105v3 Announce Type: replace Abstract: Radar sensors provide reliable perception across adverse weather, lighting, and long-range conditions, yet existing machine learning approaches remain fragmented and...
arXiv:2511.21161v2 Announce Type: replace Abstract: The development of embodied agents for complex commercial environments is hindered by a critical gap in existing robotics datasets and...
arXiv:2511.21276v2 Announce Type: replace Abstract: Accurate and efficient seismic response prediction is essential for the design of resilient structures. While the Finite Element Method (FEM)...
arXiv:2511.21399v2 Announce Type: replace Abstract: Activation steering - adding a vector to a language model's residual stream - is widely used to elicit latent behaviors...
arXiv:2511.22914v2 Announce Type: replace Abstract: This paper investigates the reconfiguration variant of the Constraint Satisfaction Problem (CSP), referred to as the Reconfiguration CSP (RCSP). Given...
arXiv:2511.23170v3 Announce Type: replace Abstract: Contrastive vision-language pre-training frameworks such as CLIP have demonstrated impressive zero-shot performance across a range of vision-language tasks. Recent studies...
arXiv:2512.00470v3 Announce Type: replace Abstract: Diffusion models have demonstrated strong capabilities for modeling human-like driving behaviors in autonomous driving, but their iterative sampling process induces...