Stay updated with the latest research and technology news
arXiv:2602.16729v2 Announce Type: replace Abstract: We systematically evaluate the quality of widely used AI safety datasets from two perspectives: in isolation and in practice. In...
arXiv:2602.16820v2 Announce Type: replace Abstract: Despite growing interest in using LLMs to generate feedback on students' writing, little is known about how students respond to...
arXiv:2602.16863v2 Announce Type: replace Abstract: The ability to manipulate tools significantly expands the set of tasks a robot can perform. Yet, tool manipulation represents a...
arXiv:2602.16947v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have become essential in high-stakes domains such as drug discovery, yet their black-box nature remains a...
arXiv:2602.16954v2 Announce Type: replace Abstract: We challenge black-box purely deep neural approaches for molecules and graph generation, which are limited in controllability and lack formal...
arXiv:2602.17050v2 Announce Type: replace Abstract: Embedding tables are critical components of large-scale recommendation systems, facilitating the efficient mapping of high-cardinality categorical features into dense vector...
arXiv:2602.17294v2 Announce Type: replace Abstract: We show that the problem of covering a set of points in the plane with a minimum number of guillotine...
arXiv:2602.17372v2 Announce Type: replace Abstract: Monitoring tree crop expansion is vital for zero-deforestation policies like the European Union's Regulation on Deforestation-free Products (EUDR). However, these...
arXiv:2602.17419v2 Announce Type: replace Abstract: Industrial anomaly detection is important for smart manufacturing, but many deep learning approaches produce only binary decisions and provide limited...
arXiv:2602.17550v2 Announce Type: replace Abstract: Existing Reinforcement Learning with Verifiable Rewards (RLVR) algorithms, such as GRPO, rely on rigid, uniform, and symmetric trust region mechanisms...
arXiv:2602.17554v2 Announce Type: replace Abstract: Training large-scale generative models is resource-intensive and relies heavily on heuristic dataset weighting. We address two fundamental questions: Can we...
arXiv:2602.17646v2 Announce Type: replace Abstract: As humans increasingly rely on multiround conversational AI for high stakes decisions, principled frameworks are needed to ensure such interactions...
arXiv:2602.17817v2 Announce Type: replace Abstract: Collocating deep learning training tasks improves GPU utilization but risks resource contention, severe slowdowns, and out-of-memory (OOM) failures. Accurate memory...
arXiv:2602.17905v2 Announce Type: replace Abstract: Interactive systems such as chatbots and games are increasingly used to persuade and educate on sustainability-related topics, yet it remains...
arXiv:2602.18296v2 Announce Type: replace Abstract: Manufacturing automation in process planning, inspection planning, and digital-thread integration depends on a unified specification that binds the geometric features...
arXiv:2602.18448v2 Announce Type: replace Abstract: Administrative phone tasks drain roughly 1 trillion USD annually from U.S. healthcare, with over 500 million insurance-benefit verification calls manually...
arXiv:2602.18464v2 Announce Type: replace Abstract: A growing body of research assumes that large language model (LLM) agents can serve as proxies for how people form...
arXiv:2602.18470v2 Announce Type: replace Abstract: The integration of artificial intelligence (AI) into science education is transforming the design and function of learning materials, offering new...
arXiv:2602.18568v2 Announce Type: replace Abstract: Large language model (LLM) inference performance is increasingly bottlenecked by the memory wall. While GPUs continue to scale raw compute...
arXiv:2602.18579v2 Announce Type: replace Abstract: Developers often extract methods to improve readability, understanding, and reuse, while inlining keeps logic in one block. Prior work based...
arXiv:2602.18638v2 Announce Type: replace Abstract: Legged locomotion benefits from embodied sensing, where perception emerges from the physical interaction between body and environment. We present a...
arXiv:2602.18746v2 Announce Type: replace Abstract: In the era of Vision-Language Models (VLMs), enhancing multimodal reasoning capabilities remains a critical challenge, particularly in handling ambiguous or...
arXiv:2602.18936v2 Announce Type: replace Abstract: Personalized image generation requires effectively balancing content fidelity with stylistic consistency when synthesizing images based on text and reference examples....
arXiv:2602.19028v2 Announce Type: replace Abstract: This paper offers a phenomenological reading of contemporary machine learning through Heideggerian concepts, aimed at enriching practitioners' reflexive understanding of...