Skip to content
TrackPodcasts

Seventy3

任雨山

ZH-CN702 episodes
technologyeducationscience

73播客,名字取材于Sheldon最喜欢的数字,内容由NotebookLM生成,每天跟随AI读AI业界论文。

Get every episode summarized

Each time Seventy3 publishes, we email you a written briefing from the transcript — the topics, who appeared, and any specific claims, with the ad reads skipped.

Email me new episodes

Free for 3 shows. No card needed.

Notable Guests

Episodes (702)

【第261期】LMM-R1: Reasoning Enhancement for LMM

Seventy3

Jun 18, 202516:22pending

【第260期】Vision-R1: Reasoning in Multimodal LLM

Seventy3

Jun 17, 202512:44pending

【第259期】Agentic Reward Modeling

Seventy3

Jun 16, 202517:26pending

【第258期】Forecasting Rare Language Model Behaviors

Seventy3

Jun 15, 202525:58pending

【第257期】UPFT:The First Few Tokens Are All You Need

Seventy3

Jun 14, 202516:24pending

【第256期】LightThinker: Thinking Step-by-Step Compression

Seventy3

Jun 13, 202518:31pending

【第255期】用FFT替代传统自注意力机制

Seventy3

Jun 12, 202517:04pending

【第254期】Thinking Faster by Drafting Less: Chain of Draft

Seventy3

Jun 11, 202512:27pending

【第253期】SECOND ME:AI-Native Memory Management

Seventy3

Jun 10, 202514:58pending

【第252期】Inductive Moment Matching for Generative Modeling

Seventy3

Jun 9, 202526:49pending

【第251期】YOLOE:Real-Time Seeing Anything with Open Prompts

Seventy3

Jun 8, 202514:49pending

【第250期】EasyControl:效率和灵活性指导的条件图像生成

Seventy3

Jun 7, 202523:08pending

【第249期】R1-Searcher: RL for Enhanced LLM Search Capabilities

Seventy3

Jun 6, 202518:55pending

【第248期】VisualThinker-R1-Zero: Multimodal Reasoning via RL

Seventy3

Jun 5, 202513:06pending

【第247期】Vision-R1:推理视觉大模型

Seventy3

Jun 4, 202516:32pending

【第246期】用LLM做Encoder,进行机器翻译

Seventy3

Jun 3, 202524:27pending

【第245期】固定文本长度做RAG

Seventy3

Jun 2, 202514:33pending

【第244期】TokenOCR:Token基本文本图像LLM

Seventy3

Jun 1, 202519:07pending

【第243期】AppAgentX:智能手机上的Agent

Seventy3

May 31, 202510:42pending

【第242期】MPO:Meta Plan Optimization

Seventy3

May 30, 202524:10pending

【第241期】LLaVE:一种新型视觉模型

Seventy3

May 29, 202514:50pending

【第240期】Optimal Brain Apoptosis

Seventy3

May 28, 202515:47pending

【第239期】SoS1:O1和R1模型可以解决Hilbert第17问题难度相当大问题

Seventy3

May 27, 202526:14pending

【第238期】xAR:Next-X Prediction

Seventy3

May 26, 202514:32pending

【第237期】PlanGEN:多智能体的计划生成框架

Seventy3

May 25, 202519:47pending

【第236期】NeoBERT:新一代BERT

Seventy3

May 24, 202518:26pending

【第235期】AI co-scientist:AI协作科学家

Seventy3

May 23, 202516:08pending

【第234期】Transformers without Normalization

Seventy3

May 22, 202517:18pending

【第233期】A-MEM:LLM Agent的记忆系统

Seventy3

May 21, 202516:03pending

【第232期】KV-Edit:精确保留背景信息的图像编辑方法

Seventy3

May 20, 202513:33pending

【第231期】DICEPTION:一种通用的视觉Diffusion模型

Seventy3

May 19, 202529:18pending

【第230期】olmOCR:PDF文档高质量提取模型

Seventy3

May 18, 202515:47pending

【第229期】Persona Hub:10亿个角色的数据合成方法

Seventy3

May 17, 202518:09pending

【第228期】从优化角度理解Duffusion模型

Seventy3

May 16, 202517:27pending

【第227期】NullFace:免于训练的面部匿名化方法

Seventy3

May 15, 202514:32pending

【第226期】SegAgent:像素级理解能力探究

Seventy3

May 14, 202520:19pending

【第225期】OmniMamba:基于 Mamba-2 的多模态模型

Seventy3

May 13, 202518:01pending

【第224期】过度思考带来的问题

Seventy3

May 12, 202514:35pending

【第223期】LLM对自我知识的认知程度研究

Seventy3

May 11, 202515:50pending

【第222期】HOMIE:人形机器人远程操作系统

Seventy3

May 10, 202515:35pending

【第221期】STP:Self-play LLM定理证明器

Seventy3

May 9, 202512:00pending

【第220期】SWE-RL:读开源代码学成软件工程师

Seventy3

May 8, 202514:04pending

【第219期】AgenticLU:通过Chain-of-Clarifications提升模型长文本回答能力

Seventy3

May 7, 202511:09pending

【第218期】MoBA:块注意力混合模型

Seventy3

May 6, 202512:38pending

【第217期】Open-Reasoner-Zero:开源的推理能力提升方法

Seventy3

May 5, 202521:04pending

【第216期】LLMSelector:选择不同模型做不同任务

Seventy3

May 4, 202510:00pending

【第215期】SWE-Lancer:评估AI在自由职业软件任务中的能力

Seventy3

May 3, 202512:24pending

【第214期】AI co-scientist:AI科学家助理

Seventy3

May 2, 202519:15pending

【第213期】SOLOMON:专业领域中增强LLM能力

Seventy3

May 1, 202514:13pending

【第212期】Self-Backtracking:自我回溯

Seventy3

Apr 30, 202523:43pending
......