Stay updated with the latest research and technology news
arXiv:2602.20122v1 Announce Type: new Abstract: How do large language models (LLMs) know what they know? Answering this question has been difficult because pre-training data is...
arXiv:2602.20126v1 Announce Type: new Abstract: Diffusion language models (DLMs) have recently emerged as a promising alternative to autoregressive (AR) approaches, enabling parallel token generation beyond...
arXiv:2602.20127v1 Announce Type: new Abstract: Enormous fluid antenna systems (E-FAS) have recently emerged as a new wireless architecture in which intelligent metasurfaces act as guided...
arXiv:2602.20130v1 Announce Type: new Abstract: Objective: To improve the efficiency of medical question answering (MedQA) with large language models (LLMs) by avoiding unnecessary reasoning while...
arXiv:2602.20132v1 Announce Type: new Abstract: Current reinforcement learning objectives for large-model reasoning primarily focus on maximizing expected rewards. This paradigm can lead to overfitting to...
arXiv:2602.20133v1 Announce Type: new Abstract: The paradigm of automated program generation is shifting from one-shot generation to inference-time search, where Large Language Models (LLMs) function...
arXiv:2602.20134v1 Announce Type: new Abstract: Epidemiological models increasingly rely on self-reported behavioral data such as vaccination status, mask usage, and social distancing adherence to forecast...
arXiv:2602.20135v1 Announce Type: new Abstract: With the rise of large language models (LLMs), they have become instrumental in applications such as Retrieval-Augmented Generation (RAG). Yet...
arXiv:2602.20137v1 Announce Type: new Abstract: Data visualization rules-derived from decades of research in design and perception-ensure trustworthy chart communication. While prior work has shown that...
arXiv:2602.20141v1 Announce Type: new Abstract: Mean Field Games (MFGs) provide a principled framework for modeling interactions in large population models: at scale, population dynamics become...
arXiv:2602.20144v1 Announce Type: new Abstract: We present AgentOptics, an agentic AI framework for high-fidelity, autonomous optical system control built on the Model Context Protocol (MCP)....
arXiv:2602.20150v1 Announce Type: new Abstract: Estimating simulation-ready scenes from real-world observations is crucial for downstream planning and policy learning tasks. Regretfully, existing methods struggle in...
arXiv:2602.20152v1 Announce Type: new Abstract: Inspired by behavioral science, we propose Behavior Learning (BL), a novel general-purpose machine learning framework that learns interpretable and identifiable...
arXiv:2602.20156v1 Announce Type: new Abstract: LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users...
arXiv:2602.20157v1 Announce Type: new Abstract: Current feed-forward 3D/4D reconstruction systems rely on dense geometry and pose supervision -- expensive to obtain at scale and particularly...
arXiv:2602.20160v1 Announce Type: new Abstract: We propose tttLRM, a novel large 3D reconstruction model that leverages a Test-Time Training (TTT) layer to enable long-context, autoregressive...
arXiv:2602.20161v1 Announce Type: new Abstract: Unified multimodal models can both understand and generate visual content within a single architecture. Existing models, however, remain data-hungry and...
arXiv:2101.00753v1 Announce Type: cross Abstract: Recent years have seen various rumor diffusion models being assumed in detection of rumor source research of the online social...
arXiv:2202.10697v4 Announce Type: cross Abstract: Quantum circuit testing is essential for detecting potential faults in realistic quantum devices, while the testing process itself also suffers...
arXiv:2507.19418v1 Announce Type: cross Abstract: Blind image quality assessment (BIQA) methods often incorporate auxiliary tasks to improve performance. However, existing approaches face limitations due to...
arXiv:2511.18765v1 Announce Type: cross Abstract: Existing industrial 3D garment meshes already cover most real-world clothing geometries, yet their texture diversity remains limited. To acquire more...
arXiv:2602.18441v1 Announce Type: cross Abstract: Fast and reliable surrogate models are critical for optimization, control and uncertainty analysis in geological carbon-storage projects, yet high-fidelity multiphase...
arXiv:2602.18476v1 Announce Type: cross Abstract: Protein-ligand scoring is a central component of structure-based drug design, underpinning molecular docking, virtual screening, and pose optimization. Conventional physics-based...
arXiv:2602.18478v1 Announce Type: cross Abstract: We present \texttt{ZUNA}, a 380M-parameter masked diffusion autoencoder trained to perform masked channel infilling and superresolution for arbitrary electrode numbers...