Stay updated with the latest research and technology news
arXiv:2603.04083v1 Announce Type: new Abstract: This paper investigates two complementary paradigms for predicting machine translation (MT) quality: source-side difficulty prediction and candidate-side quality estimation (QE)....
arXiv:2603.04090v1 Announce Type: new Abstract: Egocentric human motion estimation is essential for AR/VR experiences, yet remains challenging due to limited body coverage from the egocentric...
arXiv:2603.04091v1 Announce Type: new Abstract: Modeling plant growth dynamics plays a central role in modern agricultural research. However, learning robust predictors from multi-view plant imagery...
arXiv:2603.04092v1 Announce Type: new Abstract: Molecular dynamics (MD) simulates the time evolution of atomic systems governed by interatomic forces, and the fidelity of these simulations...
arXiv:2603.04093v1 Announce Type: new Abstract: Analog Ising machines have been proposed as heuristic hardware solvers for combinatorial optimization problems, with the potential to outperform conventional...
arXiv:2603.04098v1 Announce Type: new Abstract: Always-on egocentric cameras are increasingly used as demonstrations for embodied robotics, imitation learning, and assistive AR, but the resulting video...
arXiv:2603.04099v1 Announce Type: new Abstract: Multi-Layer Perceptron (MLP) models are the foundation of contemporary point cloud processing. However, their complex network architectures obscure the source...
arXiv:2603.04114v1 Announce Type: new Abstract: Multi-modal remote sensing imagery provides complementary observations of the same geographic scene, yet such observations are frequently incomplete in practice....
arXiv:2603.04115v1 Announce Type: new Abstract: Ultra-low bitrate image compression faces a critical challenge: preserving small-font scene text while maintaining overall visual quality. Region-of-interest (ROI) bit...
arXiv:2603.04117v1 Announce Type: new Abstract: Learning rate scheduling plays a critical role in the optimization of deep neural networks, directly influencing convergence speed, stability, and...
arXiv:2603.04118v1 Announce Type: new Abstract: Catheter-based interventions are widely used for the diagnosis and treatment of cardiac diseases. Recently, robotic catheters have attracted attention for...
arXiv:2603.04122v1 Announce Type: new Abstract: Audio Super-Resolution is a set of techniques aimed at high-quality estimation of the given signal as if it would be...
arXiv:2603.04123v1 Announce Type: new Abstract: Large Language Models (LLMs) often generate overly cautious and vague responses on sensitive topics, sacrificing helpfulness for safety. Existing evaluation...
arXiv:2603.04124v1 Announce Type: new Abstract: Can reinforcement learning with hard, verifiable rewards teach a compact language model to reason about physics, or does it primarily...
arXiv:2603.04125v1 Announce Type: new Abstract: Few-Shot Action Recognition (FS-AR) has shown promising results but is often limited by a closed-set assumption that fails in real-world...
arXiv:2603.04127v1 Announce Type: new Abstract: Transformers excel across domains, yet their quadratic attention complexity poses a barrier to scaling. Random-feature attention, as in Performers, can...
arXiv:2603.04128v1 Announce Type: new Abstract: Developing Audio-Visual Large Language Models (AV-LLMs) for unified scene understanding is pivotal in multimodal intelligence. While instruction tuning enables pre-trained...
arXiv:2603.04130v1 Announce Type: new Abstract: Counterfactual generation for chest X-rays (CXR) aims to simulate plausible pathological changes while preserving patient-specific anatomy. However, diffusion-based editing methods...
arXiv:2603.04132v1 Announce Type: new Abstract: Several energy management applications rely on accurate photovoltaic generation forecasts. Common metrics like mean absolute error or root-mean-square error, omit...
arXiv:2603.04134v1 Announce Type: new Abstract: Deep learning (DL) models can now run on microcontrollers (MCUs). Through neural architecture search (NAS), we can search DL models...
arXiv:2603.04135v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) effectively scales LLM reasoning but incurs prohibitive computational costs due to its extensive group-based sampling...
arXiv:2603.04142v1 Announce Type: new Abstract: Continuous physiological monitoring is central to emergency care, yet deploying trustworthy AI is challenging. While LLMs can translate complex physiological...
arXiv:2603.04144v1 Announce Type: new Abstract: In visual simultaneous localization and mapping (SLAM), the quality of the visual vocabulary is fundamental to the system's ability to...
arXiv:2603.04145v1 Announce Type: new Abstract: We present VietNormalizer1, an open-source, zero-dependency Python library for Vietnamese text normalization targeting Text-to-Speech (TTS) and Natural Language Processing (NLP)...