Stay updated with the latest research and technology news
arXiv:2602.19346v1 Announce Type: new Abstract: Modular small-scale robots offer the potential for on-demand assembly and disassembly, enabling task-specific adaptation in dynamic and constrained environments. However,...
arXiv:2602.19348v1 Announce Type: new Abstract: Acquiring aligned visuo-tactile datasets is slow and costly, requiring specialised hardware and large-scale data collection. Synthetic generation is promising, but...
arXiv:2602.19349v1 Announce Type: new Abstract: LiDAR-camera fusion enhances 3D panoptic segmentation by leveraging camera images to complement sparse LiDAR scans, but it also introduces a...
arXiv:2602.19350v1 Announce Type: new Abstract: Digitizing humans and synthesizing photorealistic avatars with explicit 3D pose and camera controls are central to VR, telepresence, and entertainment....
arXiv:2602.19352v1 Announce Type: new Abstract: Despite having growing awareness and concerns about privacy, technology users are often insufficiently informed of the data practices of various...
arXiv:2602.19353v1 Announce Type: new Abstract: Research Software Engineers (RSEs) have become indispensable to computational research and scholarship. The fast rise of RSEs in higher education...
arXiv:2602.19354v1 Announce Type: new Abstract: Lightweight fine-tuning techniques and the rise of 'open' AI model marketplaces have enabled individuals to easily build and release generative...
arXiv:2602.19355v1 Announce Type: new Abstract: Generalization is often regarded as an essential property of machine learning systems. However, perhaps not every component of a system...
arXiv:2602.19357v1 Announce Type: new Abstract: Spatial visualization is the mental ability to imagine, transform, and manipulate the spatial characteristics of objects and actions. This intelligence...
arXiv:2602.19358v1 Announce Type: new Abstract: Precise, object-aware control over visual content is essential for advanced image editing and compositional generation. Yet, most existing approaches operate...
arXiv:2602.19359v1 Announce Type: new Abstract: Calibrating a robot simulator's physics parameters (friction, damping, material stiffness) to match real hardware is often done by hand or...
arXiv:2602.19360v1 Announce Type: new Abstract: Federated data processing (FDP) offers a promising approach for enabling collaborative analysis of sensitive data without centralizing raw datasets. However,...
arXiv:2602.19362v1 Announce Type: new Abstract: Reinforcement learning (RL) approaches for Large Language Models (LLMs) frequently use on-policy algorithms, such as PPO or GRPO. However, policy...
arXiv:2602.19366v1 Announce Type: new Abstract: We study how to scale distributed bandit submodular coordination under realistic communication constraints in bandwidth, data rate, and connectivity. We...
arXiv:2602.19367v1 Announce Type: new Abstract: The Platonic Representation Hypothesis posits that learned representations from models trained on different modalities converge to a shared latent structure...
arXiv:2602.19368v1 Announce Type: new Abstract: Data cleaning is often framed as a technical preprocessing step, yet in practice it relies heavily on human judgment. We...
arXiv:2602.19372v1 Announce Type: new Abstract: Solving complex, long-horizon robotic manipulation tasks requires a deep understanding of physical interactions, reasoning about their long-term consequences, and precise...
arXiv:2602.19373v1 Announce Type: new Abstract: Deep reinforcement learning systems often suffer from unstable training dynamics due to non-stationarity, where learning objectives and data distributions evolve...
arXiv:2602.19375v1 Announce Type: new Abstract: This paper develops a charge-conservative mixed finite element method with optimal convergence rates for the stationary incompressible inductionless MHD equations...
arXiv:2602.19379v1 Announce Type: new Abstract: Microwave linear analog computer (MiLAC) has emerged as a promising architecture for implementing linear multiple-input multiple-output (MIMO) processing in the...
arXiv:2602.19380v1 Announce Type: new Abstract: Temporal stability in glottic opening localization remains challenging due to the complementary weaknesses of single-frame detectors and foundation-model trackers: the...
arXiv:2602.19383v1 Announce Type: new Abstract: Rebuilding packages from open source is a common practice to improve the security of software supply chains, and is now...
arXiv:2602.19385v1 Announce Type: new Abstract: Recognizing implicit visual and textual patterns is essential in many real-world applications of modern AI. However, tackling long-tail pattern recognition...
arXiv:2602.19386v1 Announce Type: new Abstract: The growing deployment of nonlinear, converter interfaced distributed energy resources (DERs) in DC microgrids demands decentralized controllers that remain stable...