2025.10.24 | AdaSPEC挑40% token提速两成；AutoPage 10美分生成交互网页

本期的 15 篇论文如下：

[00:23] 🎯 AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders（AdaSPEC：面向高效推测解码的选择性知识蒸馏）

[00:57] 🤖 Human-Agent Collaborative Paper-to-Page Crafting for Under $0.1（低成本人机协作论文一键成页：低于0.1美元）

[01:35] 🔍 Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence（Open-o3视频：显式时空证据支撑的开放域视频推理）

[02:06] 🎬 HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives（HoloCine：端到端生成多镜头长时电影级叙事视频）

[02:52] 🌀 Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall（绕过离散扩散采样墙的确定性捷径）

[03:33] 💎 Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values（每个问题都有它的价值：显式人类价值驱动的强化学习）

[04:06] ⚖ The Massive Legal Embedding Benchmark (MLEB)（大规模法律嵌入评测基准（MLEB））

[04:48] 🔍 DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion（DyPE：面向超高分辨率扩散模型的动态位置外推方法）

[05:33] 🕵 Conan: Progressive Learning to Reason Like a Detective over Multi-Scale Visual Evidence（柯南：像侦探一样在多尺度视觉证据上渐进式推理）

[06:12] 🤖 Search Self-play: Pushing the Frontier of Agent Capability without Supervision（搜索自博弈：无需监督即可拓展智能体能力边界）

[06:56] 🎭 Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations（探究大音频语言模型在说话人情绪变化下的安全漏洞）

[07:42] 🖼 LayerComposer: Interactive Personalized T2I via Spatially-Aware Layered Canvas（LayerComposer：基于空间感知分层画布的交互式个性化文生图）

[08:10] 🎧 SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models（SAKE：面向大型音频-语言模型听觉属性知识编辑的探索）

[08:51] 🖼 ARGenSeg: Image Segmentation with Autoregressive Image Generation Model（ARGenSeg：基于自回归图像生成的图像分割）

[09:39] 🧩 Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets（Seed3D 1.0：从单张图像生成高保真、可仿真的3D资产）

【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