本期的 13 篇论文如下:
00:22 🤔 Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth(废话学:用深度解读无意义内容挑战大型语言模型)
00:47 📐 From Editor to Dense Geometry Estimator(从编辑模型到密集几何估计器)
01:08 🧠 Towards a Unified View of Large Language Model Post-Training(迈向大语言模型后训练的统一视角)
01:39 🔄 Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?(逆向IFEval:大型语言模型能否摒弃顽固训练惯例以遵循真实指令?)
02:05 🔬 DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks(深度研究竞技场:基于研讨会任务对大语言模型研究能力的首次考核)
02:26 🚀 Transition Models: Rethinking the Generative Learning Objective(过渡模型:重新思考生成式学习目标)
02:54 🔍 NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings(NER检索器:基于类型感知嵌入的零样本命名实体检索)
03:24 ⚡ Few-step Flow for 3D Generation via Marginal-Data Transport Distillation(基于边缘数据传输蒸馏的少步流3D生成方法)
03:53 🎬 Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding(视频多轮推理:面向长视频理解的强化多轮推理框架)
04:19 🎭 Durian: Dual Reference-guided Portrait Animation with Attribute Transfer(Durian:基于双参考引导的肖像动画与属性迁移)
04:47 📐 Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings(Drawing2CAD:基于序列到序列学习的矢量绘图CAD生成)
05:24 🧠 Delta Activations: A Representation for Finetuned Large Language Models(Delta激活:微调大型语言模型的一种表示方法)
06:01 ⚠ False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize(虚假安全感:为何基于探测的恶意输入检测方法难以泛化)

【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
