Stay updated with the latest research and technology news
arXiv:2602.19477v1 Announce Type: new Abstract: The sandpile automata of Bak, Tang, and Wiesenfeld (Phys. Rev. Lett., 1987) are a simple model for the diffusion of...
arXiv:2602.19483v1 Announce Type: new Abstract: Quantifying uncertainty in clinical predictions is critical for high-stakes diagnosis tasks. Conformal prediction offers a principled approach by providing prediction...
arXiv:2602.19485v1 Announce Type: new Abstract: The rapid advancement of large AI models imposes stringent demands on data volume and computational resources. Federated learning, though designed...
arXiv:2602.19486v1 Announce Type: new Abstract: This paper introduces a mixed H-infinity-passivity framework that enables district heating systems (DHSs) with heat pumps to support electric-grid frequency...
arXiv:2602.19487v1 Announce Type: new Abstract: Whole slide images, with their gigapixel-scale panoramas of tissue samples, are pivotal for precise disease diagnosis. However, their analysis is...
arXiv:2602.19489v1 Announce Type: new Abstract: We present Federated Learning Playground, an interactive browser-based platform inspired by and extends TensorFlow Playground that teaches core Federated Learning...
arXiv:2602.19490v1 Announce Type: new Abstract: Traditional database fuzzing techniques primarily focus on syntactic correctness and general SQL structures, leaving critical yet obscure DBMS features, such...
arXiv:2602.19491v1 Announce Type: new Abstract: Trust remains a critical barrier to the effective integration of Artificial Intelligence (AI) into human-centric domains. Disembodied agents, such as...
arXiv:2602.19497v1 Announce Type: new Abstract: Recent advancements in Unified Multimodal Models (UMMs) have enabled remarkable image understanding and generation capabilities. However, while models like Gemini-2.5-Flash-Image...
arXiv:2602.19498v1 Announce Type: new Abstract: The merit of Conformal Prediction (CP), as a distribution-free framework for uncertainty quantification, depends on generating prediction sets that are...
arXiv:2602.19502v1 Announce Type: new Abstract: Agentic AI systems are increasingly capable of autonomous data science workflows, yet clinical prediction tasks demand domain expertise that purely...
arXiv:2602.19503v1 Announce Type: new Abstract: As drone-based object detection technology continues to evolve, the demand is shifting from merely detecting objects to enabling users to...
arXiv:2602.19505v1 Announce Type: new Abstract: We propose ControlMLLM++, a novel test-time adaptation framework that injects learnable visual prompts into frozen multimodal large language models (MLLMs)...
arXiv:2602.19506v1 Announce Type: new Abstract: Feature caching approaches accelerate diffusion transformers (DiTs) by storing the output features of computationally expensive modules at certain timesteps, and...
arXiv:2602.19507v1 Announce Type: new Abstract: Collecting patient-reported outcome measures (PROMs) is essential for clinical care and research, yet traditional form-based approaches are often tedious for...
arXiv:2602.19509v1 Announce Type: new Abstract: Large Language Models (LLMs) face a persistent trade-off between inference cost and reasoning capability. While "Oracle" models (e.g., Llama-3-70B) achieve...
arXiv:2602.19510v1 Announce Type: new Abstract: Data mixing--the strategic reweighting of training domains--is a critical component in training robust machine learning models. This problem is naturally...
arXiv:2602.19512v1 Announce Type: new Abstract: We introduce a variational framework for diffusion models with anisotropic noise schedules parameterized by a matrix-valued path $M_t(\theta)$ that allocates...
arXiv:2602.19514v1 Announce Type: new Abstract: Autonomous AI agents can now programmatically hire human workers through marketplaces using REST APIs and Model Context Protocol (MCP) integrations....
arXiv:2602.19516v1 Announce Type: new Abstract: Discovering physical laws directly from high-dimensional visual data is a long-standing human pursuit but remains a formidable challenge for machines,...
arXiv:2602.19517v1 Announce Type: new Abstract: We introduce \CFE{} (\textbf{C}lassroom \textbf{F}inal \textbf{E}xam), a multimodal benchmark for evaluating the reasoning capabilities of large language models across more...
arXiv:2602.19518v1 Announce Type: new Abstract: Anticipating and adapting to failures is a key capability robots need to collaborate effectively with humans in complex domains. This...
arXiv:2602.19519v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly being deployed in cost and latency-sensitive settings. While chain-of-thought improves reasoning, it can waste...
arXiv:2602.19523v1 Announce Type: new Abstract: Generative image composition aims to regenerate the given foreground object in the background image to produce a realistic composite image....