Stay updated with the latest research and technology news
arXiv:2509.08105v4 Announce Type: replace Abstract: Large language models excel in English but still struggle with complex reasoning in many low-resource languages (LRLs). Existing encoder-plus-decoder methods...
arXiv:2509.11629v2 Announce Type: replace Abstract: As large language models (LLMs) continue to advance in capabilities, ensuring their safety against jailbreak attacks remains a critical challenge....
arXiv:2509.13386v2 Announce Type: replace Abstract: We present VEGA, a vehicle-adaptive energy-aware routing system for electric vehicles (EVs) that integrates physics-informed parameter estimation with RL-based charge-aware...
arXiv:2509.14063v2 Announce Type: replace Abstract: Autonomous aircraft must safely operate in non-towered airspace, where coordination relies on voice-based communication among human pilots. Safe operation requires...
arXiv:2509.14210v3 Announce Type: replace Abstract: We present a cooperative aerial-ground search-and-rescue (SAR) framework that pairs two unmanned aerial vehicles (UAVs) with an unmanned ground vehicle...
arXiv:2509.17349v2 Announce Type: replace Abstract: Simultaneous speech-to-text translation systems must balance translation quality with latency. Although quality evaluation is well established, latency measurement remains a...
arXiv:2509.19674v2 Announce Type: replace Abstract: Federated continual learning (FCL) tackles scenarios of learning from continuously emerging task data across distributed clients, where the key challenge...
arXiv:2509.20507v3 Announce Type: replace Abstract: This paper introduces a deep learning approach for predicting time-dependent full-field damage in concrete. The study uses an auto-regressive U-Net...
arXiv:2509.20739v2 Announce Type: replace Abstract: Conventional navigation pipelines for legged robots remain largely geometry-centric, relying on dense SLAM representations that are fragile under rapid motion...
arXiv:2509.21281v2 Announce Type: replace Abstract: Human-like motion generation for robots often draws inspiration from biomechanical studies, which often categorize complex human motions into hierarchical taxonomies....
arXiv:2509.23335v2 Announce Type: replace Abstract: Multi-label class-incremental learning (MLCIL) continuously expands the label space while recognizing multiple co-occurring classes, making it prone to catastrophic forgetting...
arXiv:2509.23405v3 Announce Type: replace Abstract: Diffusion language models have emerged as a powerful alternative to autoregressive models, enabling fast inference through more flexible and parallel...
arXiv:2509.25034v4 Announce Type: replace Abstract: As climate change intensifies extreme weather events, water disasters pose growing threats to global communities, making adaptive reservoir management critical...
arXiv:2510.00502v3 Announce Type: replace Abstract: Diffusion alignment aims to optimize diffusion models for the downstream objective. While existing methods based on reinforcement learning or direct...
arXiv:2510.00803v2 Announce Type: replace Abstract: We study the problem of minimizing polarization and disagreement in the Friedkin-Johnsen opinion dynamics model under incomplete information. Unlike prior...
arXiv:2510.00995v2 Announce Type: replace Abstract: ROSflight is a lean, open-source autopilot ecosystem for unmanned aerial vehicles (UAVs). Designed by researchers for researchers, it is built...
arXiv:2510.01041v2 Announce Type: replace Abstract: Unmanned aerial vehicle (UAV) research requires the integration of cutting-edge technology into existing autopilot frameworks. This process can be arduous,...
arXiv:2510.01082v2 Announce Type: replace Abstract: Pressure sensors are widely integrated into modern Heating, Ventilation and Air Conditioning (HVAC) systems. As they are sensitive to acoustic...
arXiv:2510.05278v2 Announce Type: replace Abstract: While large language models are primarily used on natural language tasks, they have also shown great promise when adapted to...
arXiv:2510.06550v3 Announce Type: replace Abstract: In Bayesian analysis, prior elicitation, or the process of facilitating the expression of one's beliefs to inform statistical modeling, is...
arXiv:2510.07329v4 Announce Type: replace Abstract: In complex production lines, it is essential to have strict, fast-acting rules to determine whether the system is In Control...
arXiv:2510.07967v2 Announce Type: replace Abstract: Lost architectural heritage presents interpretive challenges due to vanished structures and fragmented historical records. Using Hanyuan Hall of the Tang...
arXiv:2510.08023v3 Announce Type: replace Abstract: Recently, Ainsworth et al. empirically demonstrated that, given two independently trained models, applying a parameter permutation that preserves the input-output...
arXiv:2510.08730v2 Announce Type: replace Abstract: Micro-benchmarking offers a solution to the often prohibitive time and cost of language model development: evaluate on a very small...