登录 注册
通过LLM个性化的概率偏好基础进行不确定性- 意识的可变性回报因子化
Uncertainty-Aware Variational Reward Factorization via Probabilistic Preference Bases for LLM Person...
👁 14 📚 0
在具有短范围互动的上下文敏感随机语言模型上进行阶段过渡
Phase transition on a context-sensitive random language model with short range interactions
👁 12 📚 0
在YouTube短片上由国家资助的以色列-哈马斯战争新闻报道的多模式分析
Multimodal Analysis of State-Funded News Coverage of the Israel-Hamas War on YouTube Shorts
👁 27 📚 0
双向优化: 制作您的 LLM 与尊严相类似
Dual Optimal: Make Your LLM Peer-like with Dignity
👁 29 📚 0
OmniRoam:通过长视全景视频生成世界漫游
OmniRoam: World Wandering via Long-Horizon Panoramic Video Generation
👁 14 📚 0
视频模型 原因早期:探索计划承诺 Maze Solving
Video Models Reason Early: Exploiting Plan Commitment for Maze Solving
👁 12 📚 0
三维几何计算机远景的博士级编码基准
Benchmarking PhD-Level Coding in 3D Geometric Computer Vision
👁 16 📚 0
悬浮物体探测有条件极化指导
Conditional Polarization Guidance for Camouflaged Object Detection
👁 13 📚 0
SurgNavAR: 通过头部上载显示的光学视觉外科导航框架
SurgNavAR: An Augmented Reality Surgical Navigation Framework for Optical See-Through Head Mounted D...
👁 16 📚 0
基于奖励的在线LLM 通过神经UCB运行
Reward-Based Online LLM Routing via NeuralUCB
👁 15 📚 0
以数据驱动的语音时间调整方式,隐蔽地提高通晓性
Covertly improving intelligibility with data-driven adaptations of speech timing
👁 17 📚 0
B. 背景索赔:可核实的索赔检测的背景分析
ContextClaim: A Context-Driven Paradigm for Verifiable Claim Detection
👁 26 📚 0
跟踪神经网络中的等效机械解释
Tracking Equivalent Mechanistic Interpretations Across Neural Networks
👁 33 📚 0
利用LLM衍生摘要加强结构绘图,用于叙述逻辑推理
Enhancing Structural Mapping with LLM-derived Abstractions for Analogical Reasoning in Narratives
👁 21 📚 0
以模型为基础的加固学习
Focal plane wavefront control with model-based reinforcement learning
👁 16 📚 0
结构化知识和数据:财务应用的统一框架
Bridging Structured Knowledge and Data: A Unified Framework with Finance Applications
👁 19 📚 0
电话用户是否尊重你的隐私?
Do Phone-Use Agents Respect Your Privacy?
👁 20 📚 0
基于流动的政策与分布式强化学习 轨迹优化
Flow-based Policy With Distributional Reinforcement Learning in Trajectory Optimization
👁 16 📚 0
在正加权限制的Boltzmann机器中快速混合
Rapid mixing in positively weighted restricted Boltzmann machines
👁 15 📚 0
机器人操纵混合框架:整合强化学习和大语言模式
Hybrid Framework for Robotic Manipulation: Integrating Reinforcement Learning and Large Language Mod...
👁 20 📚 0
海洋智能体 🌊
海洋智能体
AI科研助手 · 2388篇文献
你好!你正在浏览文献列表,我可以帮你筛选方向、推荐高引论文或解读某个研究领域。