Stay updated with the latest research and technology news
arXiv:2603.01545v1 Announce Type: new Abstract: Reasoning Video Object Segmentation (ReasonVOS) is a challenging task that requires stable object segmentation across video sequences using implicit and...
arXiv:2603.01547v1 Announce Type: new Abstract: Accurate classification of pediatric central nervous system tumors remains challenging due to histological complexity and limited training data. While pathology...
arXiv:2603.01548v1 Announce Type: new Abstract: Tool-using LLM agents face a reliability-cost tradeoff: routing every decision through the LLM improves correctness but incurs high latency and...
arXiv:2603.01549v1 Announce Type: new Abstract: Humans learn not only how their bodies move, but also how the surrounding world responds to their actions. In contrast,...
arXiv:2603.01550v1 Announce Type: new Abstract: Large Language Models (LLMs) have been widely adopted to enhance Task-Oriented Dialogue Systems (TODS) by modeling complex language patterns and...
arXiv:2603.01552v1 Announce Type: new Abstract: Generative AI framework-based modeling and prediction of longitudinal human brain images offer an efficient mechanism to track neurodegenerative progression, essential...
arXiv:2603.01553v1 Announce Type: new Abstract: Signal delay poses a fundamental challenge in continuous control and reinforcement learning (RL) by introducing a temporal gap between interaction...
arXiv:2603.01554v1 Announce Type: new Abstract: The smart home is a key domain within the Society 5.0 vision for a human-centered society. Smart home technologies rapidly...
arXiv:2603.01555v1 Announce Type: new Abstract: We consider piecewise linear interpolation from the perspective of kernel interpolation and quadrature. If the Sobolev space $W_2^1(0, 1)$ is...
arXiv:2603.01556v1 Announce Type: new Abstract: Fully Homomorphic Encryption (FHE) relies heavily on the Number Theoretic Transform (NTT), making NTT a major performance bottleneck due to...
arXiv:2603.01557v1 Announce Type: new Abstract: Large language models (LLMs) can generate fluent clinical summaries of remote therapeutic monitoring time series. However, it remains unclear whether...
arXiv:2603.01558v1 Announce Type: new Abstract: Mask-based paradigms for road topology understanding, such as TopoMaskV2, offer a complementary alternative to query-based methods by generating centerlines via...
arXiv:2603.01560v1 Announce Type: new Abstract: Motorsport has historically driven technological innovation in the automotive industry. Autonomous racing provides a proving ground to push the limits...
arXiv:2603.01562v1 Announce Type: new Abstract: As Large Language Model (LLM) alignment evolves from simple completions to complex, highly sophisticated generation, Reward Models are increasingly shifting...
arXiv:2603.01563v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has achieved remarkable success in improving autoregressive models, especially in domains requiring correctness like...
arXiv:2603.01564v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift...
arXiv:2603.01568v1 Announce Type: new Abstract: Generalization to novel visual conditions remains a central challenge for both human and machine vision, yet standard robustness metrics offer...
arXiv:2603.01570v1 Announce Type: new Abstract: Benchmark workloads are extremely important to the database management research community, especially as more machine learning components are integrated into...
arXiv:2603.01571v1 Announce Type: new Abstract: Recent advancements in Generative Reward Models (GRMs) have demonstrated that scaling the length of Chain-of-Thought (CoT) reasoning considerably enhances the...
arXiv:2603.01574v1 Announce Type: new Abstract: Recent intelligent systems integrate powerful Large Language Models (LLMs) through APIs, but their trustworthiness may be critically undermined by targeted...
arXiv:2603.01576v1 Announce Type: new Abstract: Geo-Foundation Models (GFMs) have been evaluated across diverse Earth observation task including multiple domains and have demonstrated strong potential of...
arXiv:2603.01579v1 Announce Type: new Abstract: Generating realistic and structurally plausible human images into existing scenes remains a significant challenge for current generative models, which often...
arXiv:2603.01580v1 Announce Type: new Abstract: Reasoning traces produced by generative language models are increasingly used for tasks ranging from mathematical problem solving to automated fact...
arXiv:2603.01581v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models build a token-domain robot control paradigm, yet suffer from low speed. Speculative Decoding (SD) is an optimization...