🔥 AI & 科技
Large-scale image generation has benefited from advances in data scale, quality, rebalancing, and recaptioning, yet conventional pipelines typically optimize task-specific datasets in isolation. A central challenge is not only how to curate each task-specific corpus, but also how to organize heterog
📅 08-18📎 arXiv AI Papers
Memory-based self-improving agents–those that learn from an online stream of tasks and improve over time by maintaining a textual memory bank–have shown great promise in recent literature. However, the reliability aspects of these methods have been critically overlooked. In this work, we conduct a
📅 08-18📎 arXiv AI Papers
Autonomous LLM agents that converse on a user’s behalf are an emerging design pattern in matching platforms, yet their viability depends on a condition rarely examined: users must accept not only delegating conversation to an agent, but also receiving agent-mediated communication from others. We stu
📅 08-18📎 arXiv AI Papers
Urban traffic congestion reduces productivity and increases travel cost and emissions. Network-wide live travel-time shortest-path rerouting can be highly effective in simulation, but assumes that essentially every on-road vehicle is replanned every decision period. We propose HLSR, a selective hybr
📅 08-18📎 arXiv AI Papers
AI agents increasingly perform knowledge work (i.e., produce and modify persistent digital artifacts such as code repositories, documents, spreadsheets, slides, reports), yet the parsed views they search, the native files they edit, the changes they review, and the artifacts they submit can refer to
📅 08-18📎 arXiv AI Papers
MRI reconstruction methods for undersampled k-space data naturally utilize complex-valued measurements. Parallel developments in sparse phase retrieval have shown that magnitude-only measurements may provide complementary information for signal recovery. However, their use in MRI reconstruction rema
📅 08-18📎 arXiv AI Papers
GPT风格模型在符号音乐任务中表现不佳，根源在于其压缩方式与音乐结构不匹配。本文深入分析这一坐标系统错位问题，揭示语言模型高频词压缩策略对音符序列的失效机制，并给出针对性改进方向，为音乐AI模型设计提供重要理论参考。
📅 08-18📎 arXiv AI Papers
本文提出一种基于先验引导的语义LLM方法，用于解释飞行安全事件。通过融合领域知识与大语言模型推理能力，自动生成结构化的事件原因分析，提升航空安全报告的准确性与可读性，为智能航空安全管理提供新工具。
📅 08-18📎 arXiv AI Papers
本文提出从LLM反馈中进行策略不变奖励塑形的新框架，适用于混合强化学习智能体。该方法在不改变最优策略的前提下，利用语言模型先验知识调整奖励信号，有效加速学习过程并提升泛化能力，为RL与LLM结合提供稳健解决方案。
📅 08-18📎 arXiv AI Papers
针对生物科学中人工智能应用的可信度挑战，提出“可追溯信任”框架，确保AI决策过程透明、可审计，从而支持行动就绪的智能系统。该框架融合数据溯源、模型解释与验证机制，增强研究人员对AI结果的信心，推动AI在生命科学领域的可靠落地与伦理合规。
📅 08-18📎 arXiv AI Papers
本文汇总了近期Google在创新与AI领域的最新进展，涵盖Gemini模型的升级、多模态能力拓展以及应用场景落地。文章强调AI技术如何驱动产品革新，从搜索引擎到智能助手，全面赋能用户生活与工作。同时，也展望了未来AI发展方向，凸显Google在技术创新中的领先地位与社会责任。
📎 Gemini Updates