2024.11.26 每日AI论文 | 3D材料生成自动化,零样本图像生成创新。

HuggingFace 每日AI论文速递

本期的 21 篇论文如下: [00:26] 🌐 Material Anything: Generating Materials for Any 3D Object via Diffusion(材料生成:通过扩散生成任意3D对象的材料) [01:05] 🎨 Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator(基于修复的大规模文本到图像模型:零样本主题驱动图像生成器) [01:48] 🤖 From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge(从生成到判断:LLM作为评判者的机遇与挑战) [02:22] 🌐 Knowledge Transfer Across Modalities with Natural Language Supervision(基于自然语言监督的多模态知识迁移) [03:00] 🧠 MH-MoE:Multi-Head Mixture-of-Experts(多头混合专家模型) [03:34] 🎥 DreamRunner: Fine-Grained Storytelling Video Generation with Retrieval-Augmented Motion Adaptation(DreamRunner:基于检索增强的运动适应细粒度故事视频生成) [04:13] 🌐 One Diffusion to Generate Them All(一个扩散模型生成所有) [04:54] 👁 VisualLens: Personalization through Visual History(视觉透镜:通过视觉历史实现个性化) [05:34] 🔍 Factorized Visual Tokenization and Generation(因子分解视觉标记化与生成) [06:15] 🔍 O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?(O1复制之旅 -- 第二部分:通过简单蒸馏超越O1预览版,巨大进步还是苦涩教训?) [07:00] 🩺 GMAI-VL & GMAI-VL-5.5M: A Large Vision-Language Model and A Comprehensive Multimodal Dataset Towards General Medical AI(通用医疗人工智能的大规模视觉语言模型与综合多模态数据集) [07:39] 🌐 SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis(SplatFlow:用于3D高斯喷射合成的多视图校正流模型) [08:25] 🔄 From CISC to RISC: language-model guided assembly transpilation(从CISC到RISC:语言模型引导的汇编转译) [09:03] ⚙ Cautious Optimizers: Improving Training with One Line of Code(谨慎优化器:用一行代码改进训练) [09:49] 🤖 The Impossible Test: A 2024 Unsolvable Dataset and A Chance for an AGI Quiz(不可能的测试:2024年不可解数据集与AGI测验的机会) [10:30] 🔮 Predicting Emergent Capabilities by Finetuning(通过微调预测涌现能力) [11:04] 📊 SegBook: A Simple Baseline and Cookbook for Volumetric Medical Image Segmentation(SegBook:体积医学图像分割的简单基线和操作手册) [11:48] 🩺 Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline(交互式医学图像分割:基准数据集与基线) [12:25] 🤔 LLMs Do Not Think Step-by-step In Implicit Reasoning(大语言模型在隐式推理中不进行逐步思考) [13:00] 🌐 Best of Both Worlds: Advantages of Hybrid Graph Sequence Models(双剑合璧:混合图序列模型的优势) [13:34] 🔗 Edge Weight Prediction For Category-Agnostic Pose Estimation(类别无关姿态估计的边权重预测) 【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

14分钟
99+
1年前

2024.11.25 每日AI论文 | 风格友好SNR采样器提升图像生成,TÜLU 3开源模型性能超越。

HuggingFace 每日AI论文速递

本期的 14 篇论文如下: [00:26] 🎨 Style-Friendly SNR Sampler for Style-Driven Generation(风格友好SNR采样器用于风格驱动生成) [01:08] 🚀 TÜLU 3: Pushing Frontiers in Open Language Model Post-Training(TÜLU 3:推动开放语言模型后训练的前沿) [01:53] 🌐 OminiControl: Minimal and Universal Control for Diffusion Transformer(OminiControl:扩散Transformer的最小且通用控制) [02:31] 🛡 A Flexible Large Language Models Guardrail Development Methodology Applied to Off-Topic Prompt Detection(一种应用于离题提示检测的灵活大型语言模型防护开发方法) [03:08] 🧠 Large Multi-modal Models Can Interpret Features in Large Multi-modal Models(大型多模态模型中的特征解释) [03:49] 🎥 VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection(视频浓缩:通过核心帧选择进行细粒度视频推理的大规模思维链数据集) [04:29] 🎮 BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games(BALROG:在游戏中评估代理型LLM和VLM的推理能力) [05:13] 🎥 Efficient Long Video Tokenization via Coordinated-based Patch Reconstruction(基于协调的补丁重构高效长视频标记化) [05:56] 👴 MyTimeMachine: Personalized Facial Age Transformation(我的时光机:个性化面部年龄转换) [06:34] 🎥 Novel View Extrapolation with Video Diffusion Priors(基于视频扩散先验的新视角外推) [07:10] 🎥 VideoRepair: Improving Text-to-Video Generation via Misalignment Evaluation and Localized Refinement(视频修复:通过错位评估和局部细化改进文本到视频生成) [07:54] ☁ Adapting Vision Foundation Models for Robust Cloud Segmentation in Remote Sensing Images(适应视觉基础模型用于遥感图像中云分割的鲁棒性) [08:31] 🤖 One to rule them all: natural language to bind communication, perception and action(一统天下:自然语言结合通信、感知与行动) [09:15] 🤖 WildLMa: Long Horizon Loco-Manipulation in the Wild(野外长时程移动操作) 【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

10分钟
95
1年前

2024.11.22 每日AI论文 | 混合偏好优化提升推理,多模态自回归预训练创新。

HuggingFace 每日AI论文速递

本期的 14 篇论文如下: [00:26] 🧠 Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization(通过混合偏好优化提升多模态大语言模型的推理能力) [01:12] 🌐 Multimodal Autoregressive Pre-training of Large Vision Encoders(大规模视觉编码器多模态自回归预训练) [01:55] 🧠 Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions(Marco-o1:面向开放式解决方案的开放推理模型) [02:40] 🧠 Hymba: A Hybrid-head Architecture for Small Language Models(Hymba:一种用于小语言模型的混合头架构) [03:22] 🚀 Ultra-Sparse Memory Network(超稀疏内存网络) [03:58] 📚 OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs(开放学者:利用检索增强型语言模型合成科学文献) [04:47] 🧠 Natural Language Reinforcement Learning(自然语言强化学习) [05:26] 🧠 Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models(Insight-V:探索多模态大语言模型的长链视觉推理) [06:08] 🤖 Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models(我了解这个实体吗?语言模型中的知识意识与幻觉) [06:46] 🌊 Stable Flow: Vital Layers for Training-Free Image Editing(稳定流:无需训练的图像编辑关键层) [07:25] 🌐 UnifiedCrawl: Aggregated Common Crawl for Affordable Adaptation of LLMs on Low-Resource Languages(统一爬取:利用Common Crawl为低资源语言的LLM提供经济适用的适应性) [08:03] 🚗 MagicDriveDiT: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control(MagicDriveDiT:基于自适应控制的高分辨率长视频生成用于自动驾驶) [08:44] 🧠 Patience Is The Key to Large Language Model Reasoning(耐心是大型语言模型推理的关键) [09:18] 🌐 Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation(将高斯散射融入扩散去噪器以实现快速且可扩展的单阶段图像到3D生成) 【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

10分钟
99+
1年前

2024.11.21 每日AI论文 | 4比特注意力加速显著,视频生成基准全面评估。

HuggingFace 每日AI论文速递

本期的 8 篇论文如下: [00:28] ⚡ SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration(SageAttention2技术报告:用于即插即用推理加速的精确4比特注意力机制) [01:10] 📹 VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models(VBench++:全面且多功能的视频生成模型基准套件) [01:51] 🎮 VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation(视频自动竞技场:通过用户模拟评估大型多模态模型在视频分析中的能力) [02:33] 🎯 SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory(SAMURAI:利用运动感知记忆机制将分割模型适应于零样本视觉跟踪) [03:10] 🌐 Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents(你的LLM是否秘密地成为互联网的世界模型?基于模型的网络代理规划) [03:52] 🔄 When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training(精度与位置的碰撞:BFloat16在长上下文训练中破坏了RoPE) [04:34] 🎨 Stylecodes: Encoding Stylistic Information For Image Generation(风格编码:为图像生成编码风格信息) [05:11] 🩺 ORID: Organ-Regional Information Driven Framework for Radiology Report Generation(器官-区域信息驱动的放射报告生成框架) 【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

6分钟
82
1年前

2024.11.19 每日AI论文 | 移动设备高效部署,具身AI虚拟探索

HuggingFace 每日AI论文速递

本期的 16 篇论文如下: [00:25] 📱 BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices(BlueLM-V-3B:移动设备上多模态大语言模型的算法与系统协同设计) [01:06] 🌍 Generative World Explorer(生成世界探索者) [01:43] 🔍 Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering(搜索、验证与反馈:通过验证器工程实现下一代基础模型的后训练范式) [02:24] 🎥 AnimateAnything: Consistent and Controllable Animation for Video Generation(动画任何事物:视频生成的连贯可控动画) [03:08] 🧠 Top-$nσ$: Not All Logits Are You Need(Top-$nσ$:并非所有对数都需要) [03:55] 🧠 Awaker2.5-VL: Stably Scaling MLLMs with Parameter-Efficient Mixture of Experts(Awaker2.5-VL:通过参数高效混合专家稳定扩展多模态大语言模型) [04:40] ⚡ SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers(SmoothCache:一种用于扩散变换器的通用推理加速技术) [05:19] 📚 Drowning in Documents: Consequences of Scaling Reranker Inference(文档淹没:扩展重排序器推理的后果) [06:00] 🩺 Comprehensive and Practical Evaluation of Retrieval-Augmented Generation Systems for Medical Question Answering(医疗问答系统中检索增强生成系统的综合与实用评估) [06:37] 📱 SlimLM: An Efficient Small Language Model for On-Device Document Assistance(SlimLM:一种用于设备端文档辅助的高效小型语言模型) [07:19] 🎥 VeGaS: Video Gaussian Splatting(视频高斯喷射) [07:50] 🔄 Adaptive Decoding via Latent Preference Optimization(通过潜在偏好优化的自适应解码) [08:27] 🎥 StableV2V: Stablizing Shape Consistency in Video-to-Video Editing(稳定视频编辑:在视频到视频编辑中保持形状一致性) [09:11] 🇩 LLäMmlein: Compact and Competitive German-Only Language Models from Scratch(LLäMmlein:从头开始构建紧凑且有竞争力的德语专用语言模型) [09:43] 👕 FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on(FitDiT:提升高保真虚拟试穿的真实服装细节) [10:18] 📜 Evaluating the role of `Constitutions' for learning from AI feedback(评估‘宪法’在从AI反馈中学习的作用) 【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

11分钟
99+
1年前

加入我们的 Discord

与播客爱好者一起交流

立即加入

扫描微信二维码

添加微信好友,获取更多播客资讯

微信二维码

播放列表

自动播放下一个

播放列表还是空的

去找些喜欢的节目添加进来吧