本期的 11 篇论文如下: [00:27] 🔍 Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders(解构SDXL Turbo:使用稀疏自编码器解释文本到图像模型) [01:05] 🧠 What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective(LLMs训练中快速与慢速思考的层级差异:梯度视角) [01:43] 🔍 A Pointer Network-based Approach for Joint Extraction and Detection of Multi-Label Multi-Class Intents(基于指针网络的多标签多类别意图联合提取与检测方法) [02:23] 🔄 Constraint Back-translation Improves Complex Instruction Following of Large Language Models(约束反向翻译提升大型语言模型复杂指令遵循能力) [02:59] 📄 Language Models can Self-Lengthen to Generate Long Texts(语言模型能够自我延长以生成长文本) [03:35] 📊 BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays(BenchX:胸部X光片医学视觉-语言预训练统一基准框架) [04:17] 💾 BitStack: Fine-Grained Size Control for Compressed Large Language Models in Variable Memory Environments(BitStack:在可变内存环境中压缩大型语言模型的细粒度大小控制) [05:04] 🤖 Navigating the Unknown: A Chat-Based Collaborative Interface for Personalized Exploratory Tasks(探索未知:基于聊天的个性化探索任务协作界面) [05:40] 🤖 SelfCodeAlign: Self-Alignment for Code Generation(自代码对齐:代码生成中的自对齐方法) [06:18] 🎥 DELTA: Dense Efficient Long-range 3D Tracking for any video(DELTA:高效密集长程3D视频追踪) [06:57] 🎥 Learning Video Representations without Natural Videos(无需自然视频即可学习视频表示) 【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
本期的 5 篇论文如下: [00:29] 🗣 CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation(CORAL:多轮对话增强生成基准测试) [01:09] 🤖 A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks(大型递归动作模型:xLSTM为机器人任务实现快速推理) [01:50] 🔍 Stealing User Prompts from Mixture of Experts(从混合专家模型中窃取用户提示) [02:26] 🩺 AutoMIR: Effective Zero-Shot Medical Information Retrieval without Relevance Labels(自动医疗信息检索:无需相关标签的有效零样本检索) [02:58] 🔄 TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters(TokenFormer:重新思考Transformer的扩展与模型参数的标记化) 【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
本期的 8 篇论文如下: [00:33] 🧠 CLEAR: Character Unlearning in Textual and Visual Modalities(CLEAR:文本与视觉模态中的字符遗忘) [01:10] 🤖 AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions(AutoKaggle:一种用于自主数据科学竞赛的多智能体框架) [01:46] 🤖 SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization(社交GPT:通过贪婪段优化提示LLMs进行社交关系推理) [02:26] 🌐 OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization(开放式网络航海者:通过迭代现实世界探索、反馈和优化构建多模态网络代理) [03:13] 🧠 Flow-DPO: Improving LLM Mathematical Reasoning through Online Multi-Agent Learning(Flow-DPO:通过在线多智能体学习提升LLM数学推理能力) [03:52] 🚀 ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference(ShadowKV:高吞吐量长上下文LLM推理的KV缓存优化) [04:31] 🤖 Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Dataset(机器人预训练机器人:基于大规模机器人数据集的以操作为中心的机器人表示) [05:17] 🤖 Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning(基于人机协作强化学习的精确灵巧机器人操作) 【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
本期的 17 篇论文如下: [00:24] 🇵 Bielik 7B v0.1: A Polish Language Model -- Development, Insights, and Evaluation(Bielik 7B v0.1:波兰语言模型——开发、洞察与评估) [01:00] 🤖 AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistant(AgentStore:可扩展的异构代理作为专业化通才计算机助手集成) [01:39] 🤖 GPT-4o System Card(GPT-4o系统卡片) [02:21] 📄 Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction(文档解析揭秘:结构化信息提取的技术、挑战与前景) [03:08] 🤖 LongReward: Improving Long-context Large Language Models with AI Feedback(长奖励:通过AI反馈提升长上下文大语言模型) [03:43] 🎥 MarDini: Masked Autoregressive Diffusion for Video Generation at Scale(MarDini:大规模视频生成的掩码自回归扩散模型) [04:22] 🌟 DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation(DreamClear:高容量真实世界图像修复与隐私安全数据集构建) [05:10] 🧩 GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation(GrounDiT:基于噪声补丁移植的扩散变换器空间定位) [05:49] 📚 A Survey of Small Language Models(小语言模型综述) [06:23] 💾 COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training(COAT:压缩优化器状态和激活以实现高效的FP8训练) [06:58] ⚡ Fast Best-of-N Decoding via Speculative Rejection(基于推测拒绝的快速最佳N解码) [07:36] 🔍 Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Engines(视觉搜索助手:赋能视觉-语言模型作为多模态搜索引擎) [08:25] 🎥 LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior(LARP:利用学习到的自回归生成先验进行视频标记化) [09:00] 🤖 Neural Fields in Robotics: A Survey(机器人学中的神经场:综述) [09:40] 🗣 Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extraction(对话2流程:预训练软对比动作驱动句子嵌入用于自动对话流程提取) [10:15] 🩺 Language Models And A Second Opinion Use Case: The Pocket Professional(语言模型与第二意见应用案例:口袋专家) [10:55] 🤖 Leveraging Locality to Boost Sample Efficiency in Robotic Manipulation(利用局部性提升机器人操作的样本效率) 【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
本期的 13 篇论文如下: [00:25] 🚀 ROCKET-1: Master Open-World Interaction with Visual-Temporal Context Prompting(ROCKET-1:利用视觉-时间上下文提示掌握开放世界交互) [01:14] 🗣 Continuous Speech Synthesis using per-token Latent Diffusion(基于每标记潜在扩散的连续语音合成) [01:55] ⚡ Teach Multimodal LLMs to Comprehend Electrocardiographic Images(教授多模态大语言模型理解心电图图像) [02:39] 🌐 Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data(无限多模态:通过大规模高质量指令数据扩展多模态性能) [03:23] ⚡ FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality(FasterCache:无训练视频扩散模型加速与高质量生成) [03:56] 🎧 MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark(大规模多任务音频理解与推理基准) [04:34] 🧠 Counting Ability of Large Language Models and Impact of Tokenization(大型语言模型的计数能力及其对分词的影响) [05:08] 🧠 Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning(通过先决学习利用虚构合成数据提升LLM事实性) [05:46] 🤖 Reflection-Bench: probing AI intelligence with reflection(反射-基准:通过反射探测AI智能) [06:23] 🤖 Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback(混合偏好:学习路由实例以进行人机反馈) [06:57] 🔍 Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration(利用未标注的先验数据进行高效在线探索) [07:35] 🔍 Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance(LLM是否优于报告?检测标签错误并减轻其对模型性能的影响) [08:15] 🤖 Dynamic 3D Gaussian Tracking for Graph-Based Neural Dynamics Modeling(基于图神经网络的动态三维高斯跟踪用于神经动力学建模) 【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
本期的 5 篇论文如下: [00:44] TOP1(🔥79) | ⚡ FrugalNeRF: Fast Convergence for Few-shot Novel View Synthesis without Learned Priors(节俭NeRF:无学习先验的少样本新视角合成快速收敛) [02:42] TOP2(🔥60) | 🌳 SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree(SAM2Long:通过无训练记忆树增强SAM 2以实现长视频分割) [04:19] TOP3(🔥58) | 🚀 Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss(打破内存壁垒:对比损失的近无限批量规模扩展) [06:11] TOP4(🔥55) | 🤖 CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution(指南针评判者-1:一体化评判模型助力模型评估与进化) [08:28] TOP5(🔥52) | 💼 UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models(UCFE:面向用户的大语言模型金融专业能力基准) 【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
本期的 21 篇论文如下: [00:26] 🚀 Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss(打破内存壁垒:对比损失的近无限批量规模扩展) [01:09] 🔄 LOGO -- Long cOntext aliGnment via efficient preference Optimization(LOGO -- 通过高效偏好优化实现长上下文对齐) [01:45] 🧠 Unleashing Reasoning Capability of LLMs via Scalable Question Synthesis from Scratch(从零开始释放LLMs的推理能力:可扩展的问题合成方法) [02:30] 🤔 Can Knowledge Editing Really Correct Hallucinations?(知识编辑真的能纠正幻觉吗?) [03:17] 🎮 Unbounded: A Generative Infinite Game of Character Life Simulation(无界:生成式无限角色生活模拟游戏) [04:02] 🎥 Framer: Interactive Frame Interpolation(Framer:交互式帧插值) [04:48] 📊 Distill Visual Chart Reasoning Ability from LLMs to MLLMs(从LLMs到MLLMs的视觉图表推理能力提炼) [05:35] 📉 Why Does the Effective Context Length of LLMs Fall Short?(为什么大型语言模型的有效上下文长度不足?) [06:14] 🔒 Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances(基于生成先验的鲁棒水印技术对抗图像编辑:从基准测试到进展) [06:52] 🔧 Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs(天工奖励:LLM奖励建模的技巧包) [07:27] 🌍 CAMEL-Bench: A Comprehensive Arabic LMM Benchmark(CAMEL-Bench:一个全面的阿拉伯语大型多模态模型基准) [08:09] 📊 Should We Really Edit Language Models? On the Evaluation of Edited Language Models(我们真的应该编辑语言模型吗?关于编辑语言模型的评估) [08:43] 🌐 ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning(ADEM-VL:高效视觉语言调优的自适应嵌入融合方法) [09:20] 🌐 WAFFLE: Multi-Modal Model for Automated Front-End Development(WAFFLE:自动化前端开发的多模态模型) [09:52] 📚 CCI3.0-HQ: a large-scale Chinese dataset of high quality designed for pre-training large language models(CCI3.0-HQ:一个用于预训练大型语言模型的高质量大规模中文数据集) [10:30] 🔄 Stable Consistency Tuning: Understanding and Improving Consistency Models(稳定一致性调优:理解与改进一致性模型) [11:10] 🧮 Language Models are Symbolic Learners in Arithmetic(语言模型在算术中的符号学习者角色) [12:00] 🐍 Taipan: Efficient and Expressive State Space Language Models with Selective Attention(Taipan:高效且表达丰富的状态空间语言模型与选择性注意力) [12:44] 🔄 Value Residual Learning For Alleviating Attention Concentration In Transformers(残差值学习缓解Transformer中的注意力集中问题) [13:23] 📚 Multi-Draft Speculative Sampling: Canonical Architectures and Theoretical Limits(多草稿推测采样:典型架构与理论极限) [14:03] 🤖 Data Scaling Laws in Imitation Learning for Robotic Manipulation(机器人操作中的模仿学习数据缩放定律) 【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
本期的 10 篇论文如下: [00:25] 🖼 MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models(多图像增强直接偏好优化:大型视觉语言模型) [01:09] 🌍 WorldSimBench: Towards Video Generation Models as World Simulators(世界模拟器:迈向视频生成模型作为世界模拟器) [01:47] 🌊 Scaling Diffusion Language Models via Adaptation from Autoregressive Models(通过自回归模型适应扩展扩散语言模型) [02:20] 📱 Lightweight Neural App Control(轻量级神经应用控制) [03:01] 🏠 ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding(ARKit标签制造者:室内3D场景理解的新尺度) [03:47] 🖼 Scalable Ranked Preference Optimization for Text-to-Image Generation(可扩展的文本到图像生成中的排序偏好优化) [04:23] 🌆 DynamicCity: Large-Scale LiDAR Generation from Dynamic Scenes(动态城市:动态场景的大规模LiDAR生成) [05:05] 🩺 MedINST: Meta Dataset of Biomedical Instructions(医学指令元数据集:MedINST) [05:52] 🌍 M-RewardBench: Evaluating Reward Models in Multilingual Settings(多语言环境下的奖励模型评估:M-RewardBench) [06:27] 📊 TP-Eval: Tap Multimodal LLMs' Potential in Evaluation by Customizing Prompts(TP-Eval:通过定制提示挖掘多模态大语言模型的评估潜力) 【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
本期的 8 篇论文如下: [00:27] 🔍 PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction(金字塔式视觉冗余减少:通过金字塔视觉冗余减少加速大型视觉-语言模型) [01:09] 🌟 SpectroMotion: Dynamic 3D Reconstruction of Specular Scenes(光谱运动:镜面场景的动态三维重建) [01:48] 🤖 Aligning Large Language Models via Self-Steering Optimization(通过自引导优化对齐大型语言模型) [02:30] 🇯 JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation(JMMMU:一个用于文化意识评估的日本大规模多学科多模态理解基准) [03:11] 🧬 EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary Search(EvoPress:通过进化搜索实现最优动态模型压缩) [03:53] 🧠 MiniPLM: Knowledge Distillation for Pre-Training Language Models(MiniPLM:预训练语言模型的知识蒸馏) [04:30] 🔍 Mitigating Object Hallucination via Concentric Causal Attention(通过同心因果注意力缓解对象幻觉) [05:19] 🧠 Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes(数学神经外科:仅使用前向传递隔离语言模型的数学推理能力) 【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
本期的 21 篇论文如下: [00:24] 🤖 CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution(指南针评判者-1:一体化评判模型助力模型评估与进化) [01:11] 🌲 SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree(SAM2长:通过无需训练的记忆树增强SAM 2以实现长视频分割) [01:55] 🌐 PUMA: Empowering Unified MLLM with Multi-granular Visual Generation(PUMA:赋予统一多模态大语言模型多粒度视觉生成能力) [02:37] 🤖 AutoTrain: No-code training for state-of-the-art models(AutoTrain:无代码训练最先进的模型) [03:10] ⚡ FrugalNeRF: Fast Convergence for Few-shot Novel View Synthesis without Learned Priors(节俭NeRF:无学习先验的少样本新视角合成快速收敛) [03:56] 📊 Baichuan Alignment Technical Report(百川对齐技术报告) [04:39] 🌍 Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages(泛亚:一个完全开放的多语种多模态LLM,涵盖39种语言) [05:21] 🔍 RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style(RM-Bench:评估语言模型奖励模型的细致性与风格敏感度) [06:05] 📚 Meta-Chunking: Learning Efficient Text Segmentation via Logical Perception(元分块:通过逻辑感知学习高效的文本分割) [06:41] 🔍 Pre-training Distillation for Large Language Models: A Design Space Exploration(大型语言模型预训练蒸馏:设计空间探索) [07:16] 🔬 Alchemy: Amplifying Theorem-Proving Capability through Symbolic Mutation(炼金术:通过符号变异增强定理证明能力) [07:55] 🔄 SemiEvol: Semi-supervised Fine-tuning for LLM Adaptation(半监督微调:LLM适应的半监督微调框架) [08:31] 📚 Selecting Influential Samples for Long Context Alignment via Homologous Models' Guidance and Contextual Awareness Measurement(通过同源模型引导和上下文意识测量选择长上下文对齐的关键样本) [09:11] 🤖 Zero-shot Model-based Reinforcement Learning using Large Language Models(基于大语言模型的零样本模型强化学习) [09:53] 🗣 Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant(一护:混合模态早期融合实时语音助手) [10:28] 🧠 CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy(CBT-Bench:评估大型语言模型在辅助认知行为疗法中的应用) [11:12] 🛠 Router-Tuning: A Simple and Effective Approach for Enabling Dynamic-Depth in Transformers(路由器调优:一种简单有效的Transformer动态深度调整方法) [11:58] 🧠 Hallucination Detox: Sensitive Neuron Dropout (SeND) for Large Language Model Training(幻觉解毒:用于大型语言模型训练的敏感神经元丢弃方法) [12:45] 🌍 Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs(多语言大语言模型的跨语言自动评估) [13:25] 🗣 DM-Codec: Distilling Multimodal Representations for Speech Tokenization(多模态表示蒸馏用于语音标记化) [14:17] 🧠 In-context learning and Occam's razor(上下文学习与奥卡姆剃刀) 【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
本期的 12 篇论文如下: [00:27] 🌐 Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation(拥有世界模型的网络代理:学习和利用环境动态进行网页导航) [01:11] 👗 MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models(魔法裁缝:文本到图像扩散模型中的组件可控个性化) [01:48] 💼 UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models(UCFE:面向用户的大语言模型金融专业能力基准) [02:37] 🧠 NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples(自然对抗样本:评估视觉语言模型) [03:12] 🧠 SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs(SeerAttention:在LLMs中学习内在稀疏注意力) [03:54] 📊 Are AI Detectors Good Enough? A Survey on Quality of Datasets With Machine-Generated Texts(AI检测器足够好吗?机器生成文本数据集质量调查) [04:25] 🌐 Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion(扩散课程:通过图像引导扩散实现合成到真实的生成课程学习) [05:08] 🎥 DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking Head Video Generation(DAWN: 非自回归扩散框架动态帧头像的讲话头视频生成) [05:50] 🔄 A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement(基于边际的语言模型对齐常见陷阱:梯度纠缠) [06:31] 🧬 DPLM-2: A Multimodal Diffusion Protein Language Model(DPLM-2: 一种多模态扩散蛋白质语言模型) [07:12] 📰 Context is Key(NMF): Modelling Topical Information Dynamics in Chinese Diaspora Media(关键在于上下文(NMF):建模华人媒体中的主题信息动态) [07:56] 🧠 How Do Training Methods Influence the Utilization of Vision Models?(训练方法如何影响视觉模型的利用?) 【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
本期的 5 篇论文如下: [00:45] TOP1(🔥80) | 🌐 Baichuan-Omni Technical Report(百川-Omni 技术报告) [02:20] TOP2(🔥58) | 📊 MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures(MixEval-X:从现实世界数据混合中进行任意到任意评估) [04:20] TOP3(🔥58) | 🎥 Movie Gen: A Cast of Media Foundation Models(电影生成:媒体基础模型集合) [06:27] TOP4(🔥53) | 🤖 LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models(LOKI:基于大型多模态模型的综合合成数据检测基准) [08:23] TOP5(🔥48) | 🌐 MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models(大规模多模态交错理解基准测试) 【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
与播客爱好者一起交流
播放列表还是空的
去找些喜欢的节目添加进来吧