H2025.12.23 | 数据工厂提效;棱镜假说统合

2025.12.23 | 数据工厂提效;棱镜假说统合

HuggingFace 每日AI论文速递·2025 年 12 月 24 日·11 分钟
在小宇宙播放
创作者写的节目说明

本期的 15 篇论文如下:

[] ⚙ DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI(DataFlow:面向数据为中心AI时代的统一数据准备与工作流自动化LLM驱动框架)

[] 🔍 The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding(棱镜假说:通过统一自编码协调语义与像素表示)

[] 🎬 Region-Constraint In-Context Generation for Instructional Video Editing(区域约束的上下文生成用于教学视频编辑)

[] 🎥 Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation(无限单应性变换作为相机控制视频生成的鲁棒条件)

[] 🔍 QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation(QuCo-RAG:基于预训练语料的动态检索增强生成不确定性量化)

[] 🤔 Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction(大型语言模型能否评估学生困境?基于能力模拟的人机难度对齐用于试题难度预测)

[] 🧭 LoGoPlanner: Localization Grounded Navigation Policy with Metric-aware Visual Geometry(LoGoPlanner:基于定位与度量感知视觉几何的导航策略)

[] 🎬 WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion(WorldWarp:利用异步视频扩散传播三维几何)

[] 🔍 UCoder: Unsupervised Code Generation by Internal Probing of Large Language Models(UCoder:通过内部探测大语言模型实现无监督代码生成)

[] 🧬 GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators(GenEnv:基于难度对齐的大语言模型智能体与环境模拟器协同进化框架)

[] 🎨 Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs(推理调色板:通过潜在情境化调节推理以实现(视觉)语言模型的可控探索)

[] ⚡ LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding(LoPA:通过前瞻并行解码扩展扩散大语言模型推理)

[] 📱 MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive, and MCP-Augmented Environments(MobileWorld:在智能体-用户交互与MCP增强环境中评测自主移动智能体)

[] ⚖ Does It Tie Out? Towards Autonomous Legal Agents in Venture Capital(它能对上吗?迈向风险投资领域的自主法律智能体)

[] 🎬 StoryMem: Multi-shot Long Video Storytelling with Memory(StoryMem:基于记忆的多镜头长视频故事讲述)

【关注我们】

您还可以在以下平台找到我们,获得播客内容以外更多信息

小红书: AI速递


在小宇宙查看该单集文稿

说明里标出的时间点,点一下跳过去

HuggingFace 每日AI论文速递 · 更多单集

看全部 739 期 →

HuggingFace 每日AI论文速递

H2025.12.23 | 数据工厂提效;棱镜假说统合

HuggingFace 每日AI论文速递 · 2025 年 12 月 24 日 · 11 分钟

2025.12.23 | 数据工厂提效;棱镜假说统合

在小宇宙播放
创作者写的节目说明

本期的 15 篇论文如下:

[] ⚙ DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI(DataFlow:面向数据为中心AI时代的统一数据准备与工作流自动化LLM驱动框架)

[] 🔍 The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding(棱镜假说:通过统一自编码协调语义与像素表示)

[] 🎬 Region-Constraint In-Context Generation for Instructional Video Editing(区域约束的上下文生成用于教学视频编辑)

[] 🎥 Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation(无限单应性变换作为相机控制视频生成的鲁棒条件)

[] 🔍 QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation(QuCo-RAG:基于预训练语料的动态检索增强生成不确定性量化)

[] 🤔 Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction(大型语言模型能否评估学生困境?基于能力模拟的人机难度对齐用于试题难度预测)

[] 🧭 LoGoPlanner: Localization Grounded Navigation Policy with Metric-aware Visual Geometry(LoGoPlanner:基于定位与度量感知视觉几何的导航策略)

[] 🎬 WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion(WorldWarp:利用异步视频扩散传播三维几何)

[] 🔍 UCoder: Unsupervised Code Generation by Internal Probing of Large Language Models(UCoder:通过内部探测大语言模型实现无监督代码生成)

[] 🧬 GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators(GenEnv:基于难度对齐的大语言模型智能体与环境模拟器协同进化框架)

[] 🎨 Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs(推理调色板:通过潜在情境化调节推理以实现(视觉)语言模型的可控探索)

[] ⚡ LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding(LoPA:通过前瞻并行解码扩展扩散大语言模型推理)

[] 📱 MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive, and MCP-Augmented Environments(MobileWorld:在智能体-用户交互与MCP增强环境中评测自主移动智能体)

[] ⚖ Does It Tie Out? Towards Autonomous Legal Agents in Venture Capital(它能对上吗?迈向风险投资领域的自主法律智能体)

[] 🎬 StoryMem: Multi-shot Long Video Storytelling with Memory(StoryMem:基于记忆的多镜头长视频故事讲述)

【关注我们】

您还可以在以下平台找到我们,获得播客内容以外更多信息

小红书: AI速递


在小宇宙查看该单集文稿

说明里标出的时间点,点一下跳过去

HHuggingFace 每日AI论文速递

HuggingFace 每日AI论文速递

面向中文AI从业者与爱好者的每日AI论文速递,工作日高密度速览前沿论文,月末以月度热门论文特辑补充,形成每日速递加月末特…

已收录 739 期 · 最近更新 11 月 10 日

在哪里听

https://feed.xyzfm.space/7jtt3j3lbbra复制

内容版权归创作者,声湃按创作者开放的 RSS 收录。了解收录与 RSS →

更多单集 全部 739 期 →