Stay updated with the latest research and technology news
arXiv:2603.05054v1 Announce Type: new Abstract: In April 2025 GMV announced a competition for finding the best method to solve a particular polynomial system over a...
arXiv:2603.05055v1 Announce Type: new Abstract: We survey systematic approaches to basis-restricted fragments of propositional logic and modal logics, with an emphasis on how expressive power...
arXiv:2603.05057v1 Announce Type: new Abstract: Urdu toxic span detection remains limited because most existing systems rely on sentence-level classification and fail to identify the specific...
arXiv:2603.05060v1 Announce Type: new Abstract: Multi--task learning seeks to improve the generalization error by leveraging the common information shared by multiple related tasks. One challenge...
arXiv:2603.05062v1 Announce Type: new Abstract: Integrated sensing and communication (ISAC) systems promise efficient spectrum utilization by jointly supporting radar sensing and wireless communication. This paper...
arXiv:2603.05066v1 Announce Type: new Abstract: RL agents are typically trained under a single, fixed reward function, which makes them brittle to reward misspecification and limits...
arXiv:2603.05067v1 Announce Type: new Abstract: Clustering on the unit hypersphere is a fundamental problem in various fields, with applications ranging from gene expression analysis to...
arXiv:2603.05068v1 Announce Type: new Abstract: As artificial intelligence (AI) becomes deeply embedded in critical services and everyday products, it is increasingly exposed to security threats...
arXiv:2603.05069v1 Announce Type: new Abstract: Personal AI agents face a fundamental deployment paradox on mobile: persistent background execution drains battery and violates platform sandboxing policies,...
arXiv:2603.05070v1 Announce Type: new Abstract: Reliable long-term deployment of autonomous robots in agricultural environments remains challenging due to perceptual aliasing, seasonal variability, and the dynamic...
arXiv:2603.05071v1 Announce Type: new Abstract: Infrared small target detection (ISTD) is challenging because tiny, low-contrast targets are easily obscured by complex and dynamic backgrounds. Conventional...
arXiv:2603.05073v1 Announce Type: new Abstract: Shuffler-based differential privacy (shuffle-DP) is a privacy paradigm providing high utility by involving a shuffler to permute noisy report from...
arXiv:2603.05075v1 Announce Type: new Abstract: In real-world multimodal applications, systems usually need to comprehend arbitrarily combined and interleaved multimodal inputs from users, while also generating...
arXiv:2603.05078v1 Announce Type: new Abstract: Reconstructing dynamic 4D scenes remains challenging due to the presence of moving objects that corrupt camera pose estimation. Existing optimization...
arXiv:2603.05079v1 Announce Type: new Abstract: In this work, we propose a new spatio-directional neural encoding that is compact and efficient, and supports all-frequency signals in...
arXiv:2603.05081v1 Announce Type: new Abstract: In the AIGC era, generating high-quality 4D content has garnered increasing research attention. Unfortunately, current 4D synthesis research is severely...
arXiv:2603.05085v1 Announce Type: new Abstract: The increasing popularity of microcontroller platforms like Arduino enables diverse end-user developers to participate in circuit prototyping. Traditionally, follow-along tutorials...
arXiv:2603.05087v1 Announce Type: new Abstract: Prompt tuning has become a prominent strategy for enhancing the performance of Large Language Models (LLMs) on downstream tasks. Many...
arXiv:2603.05092v1 Announce Type: new Abstract: Time series forecasting has witnessed an increasing demand across diverse industrial applications, where accurate predictions are pivotal for informed decision-making....
arXiv:2603.05093v1 Announce Type: new Abstract: Shapley-based attribution is critical for post-hoc XAI but suffers from off-manifold artifacts due to heuristic baselines. While generative methods attempt...
arXiv:2603.05094v1 Announce Type: new Abstract: Large Audio-Language Models (LALMs) typically struggle with localized dialectal prosody due to the scarcity of specialized corpora. We present TW-Sound580K,...
arXiv:2603.05095v1 Announce Type: new Abstract: Temporal Forgery Localization (TFL) aims to precisely identify manipulated segments within videos or audio streams, providing interpretable evidence for multimedia...
arXiv:2603.05097v1 Announce Type: new Abstract: Recent advances in geometric foundation models have emerged as a promising alternative for addressing the challenge of dense reconstruction in...
arXiv:2603.05099v1 Announce Type: new Abstract: The Abstraction and Reasoning Corpus (ARC-AGI) probes few-shot abstraction and rule induction on small visual grids, but progress is difficult...