本期的 12 篇论文如下：
[00:24] 🤔 Why Language Models Hallucinate（语言模型为何产生幻觉）
[00:47] 🎨 Symbolic Graphics Programming with Large Language Models（使用大型语言模型进行符号化图形编程）
[01:17] ⚡ Set Block Decoding is a Language Model Inference Accelerator（集合块解码：一种语言模型推理加速器）
[01:43] 🎼 WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning（WildScore：多模态大语言模型在真实场景下的符号音乐推理基准测试）
[02:14] 🌍 LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation（LatticeWorld：基于多模态大语言模型的交互式复杂世界生成框架）
[02:42] 💡 LuxDiT: Lighting Estimation with Video Diffusion Transformer（LuxDiT：基于视频扩散变换器的光照估计）
[03:15] 📷 WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool（WinT3R：基于窗口流式重建与相机令牌池）
[03:44] 📉 On Robustness and Reliability of Benchmark-Based Evaluation of LLMs（基于基准测试的LLM评估的鲁棒性与可靠性研究）
[04:07] 🔍 MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting（MedVista3D：用于减少3D CT疾病检测、理解和报告中诊断错误的视觉语言建模）
[04:43] 🦾 U-ARM : Ultra low-cost general teleoperation interface for robot manipulation（U-ARM：用于机器人操作的超低成本通用遥操作接口）
[05:16] 🔍 Behavioral Fingerprinting of Large Language Models（大型语言模型的行为指纹识别）
[05:45] 🚀 Bootstrapping Task Spaces for Self-Improvement（自改进任务空间的引导构建）
【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
Informações
- Podcast
- FrequênciaDiário
- Publicado8 de setembro de 2025 às 23:00 UTC
- Duração6min
- ClassificaçãoLivre