本期的 14 篇论文如下:
[00:25] 🤖 RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning(RACER:基于丰富语言引导的模仿学习失败恢复策略)
[01:00] 🩺 A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?(医学领域中o1的初步研究:我们离AI医生更近了吗?)
[01:34] 🧙 PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions(PixWizard:基于开放语言指令的多功能图像到图像视觉助手)
[02:16] 👻 Phantom of Latent for Large Language and Vision Models(大语言与视觉模型中的潜在幻影)
[02:55] 🩺 Beyond Fine-tuning: Unleashing the Potential of Continuous Pretraining for Clinical LLMs(超越微调:释放临床大型语言模型连续预训练的潜力)
[03:31] 🪞 Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections(反映现实:使扩散模型生成可信的镜像反射)
[04:11] 🌟 MaterialFusion: Enhancing Inverse Rendering with Material Diffusion Priors(材料融合:通过材料扩散先验增强逆渲染)
[04:51] 🩺 An adapted large language model facilitates multiple medical tasks in diabetes care(适应性大型语言模型在糖尿病护理中的多任务应用)
[05:30] 🎭 MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting(基于掩码运动修复的统一物理角色控制)
[06:08] 🤖 Style over Substance: Failure Modes of LLM Judges in Alignment Benchmarking(形式胜于实质:LLM评判者在对齐基准测试中的失效模式)
[06:54] 🗣 Zero-shot Cross-lingual Voice Transfer for TTS(零样本跨语言语音转换用于TTS)
[07:28] 🌐 SpaceBlender: Creating Context-Rich Collaborative Spaces Through Generative 3D Scene Blending(SpaceBlender:通过生成3D场景融合创建上下文丰富的协作空间)
[08:07] 🎵 Self-Supervised Audio-Visual Soundscape Stylization(自监督视听音景风格化)
[08:42] 📊 A Case Study of Web App Coding with OpenAI Reasoning Models(使用OpenAI推理模型进行Web应用编码的案例研究)

【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

空空如也
暂无小宇宙热门评论