Stay updated with the latest research and technology news
arXiv:2510.19166v2 Announce Type: replace Abstract: For real-world BCI applications, lightweight Electroencephalography (EEG) systems offer the best cost-deployment balance. However, such spatial sparsity of EEG limits...
arXiv:2510.19557v2 Announce Type: replace Abstract: Text-to-image (T2I) models offer great potential for creating virtually limitless synthetic data, a valuable resource compared to fixed and finite...
arXiv:2510.22512v2 Announce Type: replace Abstract: In this work, we present Transitive Reinforcement Learning (TRL), a new value learning algorithm based on a divide-and-conquer paradigm. TRL...
arXiv:2510.22514v2 Announce Type: replace Abstract: This paper presents a constructive framework for synthesizing provably safe controllers for nonlinear multi-agent systems subject to bounded disturbances. The...
arXiv:2510.22839v3 Announce Type: replace Abstract: The optimization of structural parameters, such as mass(m), stiffness(k), and damping coefficient(c), is critical for designing efficient, resilient, and stable...
arXiv:2510.23038v2 Announce Type: replace Abstract: Large Language Models (LLMs) are widely used as judges to evaluate response quality, providing a scalable alternative to human evaluation....
arXiv:2510.23479v3 Announce Type: replace Abstract: Vision-language alignment in multi-modal large language models (MLLMs) relies on supervised fine-tuning (SFT) or reinforcement learning (RL). To align multi-modal...
arXiv:2510.23828v2 Announce Type: replace Abstract: We present a comprehensive evaluation of the ability of large language models (LLMs) to process culturally grounded language, specifically to...
arXiv:2510.24587v2 Announce Type: replace Abstract: Many large-scale stochastic optimization algorithms involve repeated solutions of linear systems or evaluations of log-determinants. In these regimes, computing exact...
arXiv:2510.24856v2 Announce Type: replace Abstract: Grammar refers to the system of rules that governs the structural organization and the semantic relations among linguistic units such...
arXiv:2510.25143v2 Announce Type: replace Abstract: Scientific simulations and observations are producing vast amounts of time-varying vector field data, making it hard to store them for...
arXiv:2510.25232v2 Announce Type: replace Abstract: Psychiatric comorbidity is clinically significant yet challenging due to the complexity of multiple co-occurring disorders. To address this, we develop...
arXiv:2510.25850v2 Announce Type: replace Abstract: We introduce Debate2Create (D2C), a multi-agent LLM framework that formulates robot co-design as structured, iterative debate grounded in physics-based evaluation....
arXiv:2510.26376v2 Announce Type: replace Abstract: Sudden Stratospheric Warmings (SSWs) are key sources of subseasonal predictability and major drivers of extreme weather in winter. Accurate and...
arXiv:2510.26961v2 Announce Type: replace Abstract: Automatic segmentation of diverse heterogeneous brain lesions using multi-modal MRI is a challenging problem in clinical neuroimaging, mainly because of...
arXiv:2510.27246v2 Announce Type: replace Abstract: Evaluating the abilities of large language models (LLMs) for tasks that require long-term memory and thus long-context reasoning, for example...
arXiv:2510.27623v3 Announce Type: replace Abstract: Recent advances in Vision-Language Models (VLMs) have propelled embodied agents by enabling direct perception, reasoning, and planning task-oriented actions from...
arXiv:2511.00574v2 Announce Type: replace Abstract: Understanding probabilistic dependencies among variables is central to analyzing complex systems. Traditional structure learning methods often require extensive observational data...
arXiv:2511.00958v2 Announce Type: replace Abstract: Normalization layers are critical components of modern AI systems, such as ChatGPT, Gemini, DeepSeek, etc. Empirically, they are known to...
arXiv:2511.02780v3 Announce Type: replace Abstract: Smart contracts operate in a highly adversarial environment, where vulnerabilities can lead to substantial financial losses. Thus, smart contracts are...
arXiv:2511.02960v4 Announce Type: replace Abstract: Recently, a natural variant of the Art Gallery problem, known as the \emph{Contiguous Art Gallery problem} was proposed. Given a...
arXiv:2511.03005v2 Announce Type: replace Abstract: We introduce an Analyze-Revise-Finetune (ARF) pipeline that enables smaller open-source language models (LLMs) to surpass substantially larger proprietary models in...
arXiv:2511.04847v4 Announce Type: replace Abstract: Large language model (LLM)-based agents struggle to generalize to novel and complex environments, such as unseen websites or new sets...
arXiv:2511.04934v2 Announce Type: replace Abstract: Unlearning in large language models (LLMs) is critical for regulatory compliance and for building ethical generative AI systems that avoid...