2024.10.04 每日AI论文 | 字幕类型影响模型表现,长视频生成技术突破。

本期的 19 篇论文如下: [00:24] 🔄 Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models(重新审视大规模图像-文本数据在多模态基础模型预训练中的作用) [01:04] 🎥 Loong: Generating Minute-level Long Videos with Autoregressive Language Models(使用自回归语言模型生成分钟级长视频) [01:39] 🎥 Video Instruction Tuning With Synthetic Data(使用合成数据进行视频指令调优) [02:18] 🧐 LLaVA-Critic: Learning to Evaluate Multimodal Models(LLaVA-Critic:学习评估多模态模型) [02:56] 🔍 Contrastive Localized Language-Image Pre-Training(对比本地化语言-图像预训练) [03:31] 🌱 VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment(VinePPO:通过精细化的信用分配解锁LLM推理的RL潜力) [04:07] 🌟 Depth Pro: Sharp Monocular Metric Depth in Less Than a Second(Depth Pro:不到一秒内实现锐利的单目度量深度) [04:51] 🔗 Large Language Models as Markov Chains(大型语言模型作为马尔可夫链) [05:26] 🧠 CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling(CLIP-MoE:通过多样化多重升级构建CLIP的专家混合模型) [06:03] 🔄 Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models(消除扩散模型中高指导尺度引起的过饱和和伪影) [06:51] 🔄 Training Language Models on Synthetic Edit Sequences Improves Code Synthesis(在合成编辑序列上训练语言模型改进代码合成) [07:36] ⚡ SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration(SageAttention:用于即插即用推理加速的精确8位注意力机制) [08:14] 🌐 MVGS: Multi-view-regulated Gaussian Splatting for Novel View Synthesis(MVGS:多视角调节的高斯喷射用于新视角合成) [08:54] 📚 L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?(L-CiteEval:长上下文模型是否真正利用上下文进行响应?) [09:38] 🩺 MedVisionLlama: Leveraging Pre-Trained Large Language Model Layers to Enhance Medical Image Segmentation(利用预训练大型语言模型层增强医学图像分割) [10:24] 🎥 Vinoground: Scrutinizing LMMs over Dense Temporal Reasoning with Short Videos(Vinoground: 通过短视频密集时间推理审视大型多模态模型) [11:01] 🗣 Distilling an End-to-End Voice Assistant Without Instruction Training Data(无需指令训练数据的端到端语音助手蒸馏) [11:46] ♟ Learning the Latent Rules of a Game from Data: A Chess Story(从数据中学习游戏的潜在规则:一个国际象棋的故事) [12:29] 🎵 Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data(Synthio:使用合成数据增强小规模音频分类数据集) 【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

13分钟
92
6个月前

2024.10.03 每日AI论文 | 分层调试提升代码准确性,多模态模型优化图像任务。

本期的 20 篇论文如下: [00:23] 🐞 From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging(从代码到正确性:通过分层调试解决代码生成的最后一步) [01:08] 📄 LEOPARD : A Vision Language Model For Text-Rich Multi-Image Tasks(LEOPARD:用于文本丰富的多图像任务的视觉语言模型) [01:48] 📊 Is Preference Alignment Always the Best Option to Enhance LLM-Based Translation? An Empirical Analysis(偏好对齐是否总是提升基于LLM的翻译的最佳选择?一项实证分析) [02:27] 🖼 ComfyGen: Prompt-Adaptive Workflows for Text-to-Image Generation(ComfyGen:文本到图像生成的提示自适应工作流) [03:08] 🧠 RATIONALYST: Pre-training Process-Supervision for Improving Reasoning(RATIONALYST:通过预训练过程监督改进推理) [03:45] 🧠 Not All LLM Reasoners Are Created Equal(并非所有LLM推理器都相同) [04:18] 📊 Quantifying Generalization Complexity for Large Language Models(量化大型语言模型的泛化复杂性) [04:59] 🔍 3DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for 3D Object Detection(3DGS-DET:利用边界引导和框聚焦采样增强3D高斯喷洒进行3D物体检测) [05:45] 🔄 HelpSteer2-Preference: Complementing Ratings with Preferences(HelpSteer2-Preference:通过偏好补充评分) [06:25] 🗣 MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages(MOSEL:用于欧盟语言开源语音基础模型训练的95万小时语音数据) [07:03] 🤖 Closed-loop Long-horizon Robotic Planning via Equilibrium Sequence Modeling(通过平衡序列建模实现闭环长期机器人规划) [07:40] 🌐 EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis(EVER:实时视图合成的精确体积椭球体渲染) [08:22] 📄 FactAlign: Long-form Factuality Alignment of Large Language Models(FactAlign:大型语言模型的长篇事实对齐) [08:57] 📹 E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding(E.T. 基准:面向开放式事件级视频语言理解) [09:37] 🌍 BordIRlines: A Dataset for Evaluating Cross-lingual Retrieval-Augmented Generation(BordIRlines:评估跨语言检索增强生成的数据集) [10:13] 🔊 SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios(SonicSim:移动声源场景下语音处理的定制化仿真平台) [10:53] 🔄 HarmoniCa: Harmonizing Training and Inference for Better Feature Cache in Diffusion Transformer Acceleration(HarmoniCa:在扩散Transformer加速中协调训练与推理以实现更好的特征缓存) [11:35] 🔍 Selective Aggregation for Low-Rank Adaptation in Federated Learning(联邦学习中低秩适应的选择性聚合) [12:14] 📚 Old Optimizer, New Norm: An Anthology(旧优化器,新范数:文集) [12:49] 📱 InfiniPot: Infinite Context Processing on Memory-Constrained LLMs(InfiniPot:内存受限的LLM无限上下文处理) 【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

13分钟
79
6个月前

2024.10.02 每日AI论文 | 跨能力任务表现受限,边缘设备高效部署模型

本期的 13 篇论文如下: [00:26] 🔗 Law of the Weakest Link: Cross Capabilities of Large Language Models(最弱环节法则:大型语言模型的跨能力) [01:05] 🌐 TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices(TPI-LLM:在低资源边缘设备上高效服务70B规模的大型语言模型) [01:46] 🌍 Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect(Atlas-Chat:为低资源摩洛哥阿拉伯方言定制的大型语言模型) [02:22] 🎥 One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos(一令分段:视频中的语言指令推理分割) [02:59] 🌐 Flex3D: Feed-Forward 3D Generation With Flexible Reconstruction Model And Input View Curation(Flex3D:利用灵活的重建模型和输入视图优化进行前馈3D生成) [03:46] 🎨 Illustrious: an Open Advanced Illustration Model(辉煌:一个开放的高级插画模型) [04:22] 🚗 SyntheOcc: Synthesize Geometric-Controlled Street View Images through 3D Semantic MPIs(通过3D语义MPIs合成几何控制街景图像) [05:00] 📸 Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration(后验均值校正流:迈向最小均方误差照片真实图像恢复) [05:47] 🎨 ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer(遵循扩散变换器的全方位创作者和编辑) [06:22] 🎥 Visual Context Window Extension: A New Perspective for Long Video Understanding(视觉上下文窗口扩展:长视频理解的新视角) [07:05] 🤖 Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models(帮助型DoggyBot:使用四足机器人和视觉语言模型进行开放世界物体抓取) [07:46] 🎥 DressRecon: Freeform 4D Human Reconstruction from Monocular Video(DressRecon:单目视频中的自由形式4D人体重建) [08:32] 🤖 What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Study(性别偏见的影响?通过以人为本的研究量化机器翻译中的性别偏见) 【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

9分钟
78
6个月前

2024.10.01 每日AI论文 | 多模态模型提升图像理解,长度控制方法增强生成精确性。

本期的 11 篇论文如下: [00:26] 🌐 MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning(MM1.5:多模态大语言模型微调的方法、分析与见解) [01:04] 📏 Ruler: A Model-Agnostic Method to Control Generated Length for Large Language Models(Ruler:一种用于控制大型语言模型生成长度的模型无关方法) [01:41] 🗣 DiaSynth -- Synthetic Dialogue Generation Framework(DiaSynth -- 合成对话生成框架) [02:22] 📊 Hyper-Connections(OLMo-1B:探索DHC和SHC中的规模与训练) [02:57] 🤖 UniAff: A Unified Representation of Affordances for Tool Usage and Articulation with Vision-Language Models(UniAff:一种结合视觉语言模型的工具使用和关节运动的统一表示方法) [03:35] 🔍 Cottention: Linear Transformers With Cosine Attention(Cottention:基于余弦注意力的线性变换器) [04:10] 🤖 Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers(通过异构预训练Transformer扩展本体感觉-视觉学习) [04:49] 🏋 Coffee-Gym: An Environment for Evaluating and Improving Natural Language Feedback on Erroneous Code(咖啡健身房:评估和改进错误代码的自然语言反馈环境) [05:29] 🖼 Image Copy Detection for Diffusion Models(扩散模型图像复制检测) [06:09] 🧠 Can Models Learn Skill Composition from Examples?(模型能否从示例中学习技能组合?) [06:43] 🎧 IDEAW: Robust Neural Audio Watermarking with Invertible Dual-Embedding(IDEAW:具有可逆双嵌入的鲁棒神经音频水印) 【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

7分钟
74
6个月前

2024.09.30 每日AI论文 | Emu3简化多模态设计,MIO提升视频理解表现。

本期的 9 篇论文如下: [00:24] 🧠 Emu3: Next-Token Prediction is All You Need(Emu3:下一个词预测是您所需要的全部) [00:53] 🌐 MIO: A Foundation Model on Multimodal Tokens(多模态标记的基础模型:MIO) [01:26] 🔍 VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models(VPTQ:大语言模型的极端低比特向量后训练量化) [02:21] 🎥 PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation(PhysGen:基于刚体物理的图像到视频生成) [03:05] 🔄 Modulated Intervention Preference Optimization (MIPO): Keep the Easy, Refine the Difficult(调制干预偏好优化(MIPO):保持简单,细化困难) [03:46] 📄 MinerU: An Open-Source Solution for Precise Document Content Extraction(MinerU:一种用于精确文档内容提取的开源解决方案) [04:24] 🤖 MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making(MSI-Agent:将多尺度洞察融入具身代理以提升规划与决策能力) [05:01] 🤖 A Survey on the Honesty of Large Language Models(大型语言模型诚实性综述) [05:45] 📊 LML: Language Model Learning a Dataset for Data-Augmented Prediction(LML:用于数据增强预测的数据集学习语言模型) 【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
61
6个月前

2024.09.27 每日AI论文 | 3D感知能力提升,计算开销减少。

本期的 12 篇论文如下: [00:27] 🌐 LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness(LLaVA-3D:一种简单而有效的路径,赋予多模态模型3D感知能力) [01:10] 🧩 MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models(MaskLLM:大型语言模型的可学习半结构化稀疏性) [01:49] 🎭 EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions(EMOVA:赋予语言模型以生动的情感,使其能够看、听和说) [02:35] 🌸 Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction(莲花:基于扩散的高质量密集预测视觉基础模型) [03:15] ⚡ Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction(探索早期层的瑰宝:通过1000倍输入令牌减少加速长上下文LLM) [03:58] 🖼 Pixel-Space Post-Training of Latent Diffusion Models(潜在扩散模型的像素空间后训练) [04:36] 🔍 Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling(通过令牌池化减少多向量检索的足迹并保持最小性能影响) [05:17] 🎭 Disco4D: Disentangled 4D Human Generation and Animation from a Single Image(Disco4D:从单张图像生成和动画化分离的4D人体模型) [05:55] 🧠 Instruction Following without Instruction Tuning(无需指令微调的指令跟随) [06:30] 📊 The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends(大语言模型时代对话分析的必要性:任务、技术与趋势综述) [07:07] 🤖 Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction(机器人看机器人做:通过单目4D重建模仿关节物体操作) [07:43] ⚽ Enhancing Structured-Data Retrieval with GraphRAG: Soccer Data Case Study(增强结构化数据检索与GraphRAG:足球数据案例研究) 【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

8分钟
87
6个月前

2024.09.26 每日AI论文 | 提升预训练数据质量,多模态模型开源创新

本期的 10 篇论文如下: [00:32] 🤖 Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale(编程每个示例:大规模提升预训练数据质量如专家) [01:13] 🌐 Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models(Molmo 和 PixMo:用于最先进多模态模型的开源权重和数据) [01:51] 🩺 Boosting Healthcare LLMs Through Retrieved Context(通过检索上下文提升医疗领域大语言模型) [02:31] 📊 AIM 2024 Sparse Neural Rendering Challenge: Dataset and Benchmark(AIM 2024 稀疏神经渲染挑战:数据集与基准) [03:12] 🎸 Synchronize Dual Hands for Physics-Based Dexterous Guitar Playing(基于物理模拟的灵巧吉他演奏双手同步) [03:52] 🎭 DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusion(DreamWaltz-G:从骨骼引导的2D扩散生成富有表现力的3D高斯头像) [04:28] 🚁 Game4Loc: A UAV Geo-Localization Benchmark from Game Data(基于游戏数据的无人机地理定位基准) [05:13] 🌐 Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors(基于扩散先验的退化引导一步图像超分辨率) [05:53] 🎥 TalkinNeRF: Animatable Neural Fields for Full-Body Talking Humans(TalkinNeRF:用于全身说话人类动画的可动画神经场) [06:32] 🤖 HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale(HyperAgent:通用软件工程代理解决大规模编码任务) 【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

7分钟
73
6个月前

2024.09.25 每日AI论文 | HelloBench评估长文本生成,迈向通用全能语言模型的未来

本期的 17 篇论文如下: [00:28] 📄 HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models(HelloBench:评估大型语言模型的长文本生成能力) [01:14] 🌐 Making Text Embedders Few-Shot Learners(利用大语言模型使多语言文本嵌入器成为少样本学习者) [01:51] 🌐 OmniBench: Towards The Future of Universal Omni-Language Models(OmniBench:迈向通用全能语言模型的未来) [02:29] 🔄 Present and Future Generalization of Synthetic Image Detectors(合成图像检测器的现状与未来泛化) [03:08] 🎥 MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling(MIMO:基于空间分解建模的可控角色视频合成) [03:43] 🔄 MonoFormer: One Transformer for Both Diffusion and Autoregression(MonoFormer:一个Transformer同时处理扩散和自回归) [04:16] 🌍 EuroLLM: Multilingual Language Models for Europe(欧洲多语言模型:EuroLLM) [04:53] 🖼 MaskBit: Embedding-free Image Generation via Bit Tokens(MaskBit: 通过比特令牌实现无嵌入图像生成) [05:33] 👁 Seeing Faces in Things: A Model and Dataset for Pareidolia(事物中的面孔:幻觉模型与数据集) [06:19] 🤖 Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation(Gen2Act:在新场景中生成人类视频以实现可泛化的机器人操作) [06:57] 🎨 Improvements to SDXL in NovelAI Diffusion V3(NovelAI Diffusion V3中SDXL的改进) [07:41] 🔄 Reward-Robust RLHF in LLMs(大语言模型中的奖励鲁棒RLHF) [08:16] 🤖 DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control(DynaMo:视觉运动控制的域内动力学预训练) [08:54] 🇮 SLIMER-IT: Zero-Shot NER on Italian Language(SLIMER-IT:意大利语零样本命名实体识别) [09:33] 📈 Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts(基于专家混合的十亿级时间序列基础模型) [10:17] 🛡 RRM: Robust Reward Model Training Mitigates Reward Hacking(RRM:鲁棒奖励模型训练缓解奖励作弊) [10:50] 📊 Tabular Data Generation using Binary Diffusion(使用二进制扩散生成表格数据) 【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
73
6个月前

2024.09.24 每日AI论文 | 语言指导增强机器人恢复,AI医生在医学领域展现潜力

本期的 14 篇论文如下: [00:25] 🤖 RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning(RACER:基于丰富语言引导的模仿学习失败恢复策略) [01:00] 🩺 A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?(医学领域中o1的初步研究:我们离AI医生更近了吗?) [01:34] 🧙 PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions(PixWizard:基于开放语言指令的多功能图像到图像视觉助手) [02:16] 👻 Phantom of Latent for Large Language and Vision Models(大语言与视觉模型中的潜在幻影) [02:55] 🩺 Beyond Fine-tuning: Unleashing the Potential of Continuous Pretraining for Clinical LLMs(超越微调:释放临床大型语言模型连续预训练的潜力) [03:31] 🪞 Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections(反映现实:使扩散模型生成可信的镜像反射) [04:11] 🌟 MaterialFusion: Enhancing Inverse Rendering with Material Diffusion Priors(材料融合:通过材料扩散先验增强逆渲染) [04:51] 🩺 An adapted large language model facilitates multiple medical tasks in diabetes care(适应性大型语言模型在糖尿病护理中的多任务应用) [05:30] 🎭 MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting(基于掩码运动修复的统一物理角色控制) [06:08] 🤖 Style over Substance: Failure Modes of LLM Judges in Alignment Benchmarking(形式胜于实质:LLM评判者在对齐基准测试中的失效模式) [06:54] 🗣 Zero-shot Cross-lingual Voice Transfer for TTS(零样本跨语言语音转换用于TTS) [07:28] 🌐 SpaceBlender: Creating Context-Rich Collaborative Spaces Through Generative 3D Scene Blending(SpaceBlender:通过生成3D场景融合创建上下文丰富的协作空间) [08:07] 🎵 Self-Supervised Audio-Visual Soundscape Stylization(自监督视听音景风格化) [08:42] 📊 A Case Study of Web App Coding with OpenAI Reasoning Models(使用OpenAI推理模型进行Web应用编码的案例研究) 【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

9分钟
84
7个月前

2024.09.23 每日AI论文 | 无调优个性化图像生成,多模态讽刺理解评估

本期的 11 篇论文如下: [00:26] 🎨 Imagine yourself: Tuning-Free Personalized Image Generation(想象自己:无调优个性化图像生成) [01:02] 😂 YesBut: A High-Quality Annotated Multimodal Dataset for evaluating Satire Comprehension capability of Vision-Language Models(YesBut:评估视觉语言模型讽刺理解能力的高质量多模态数据集) [01:40] 🌍 Prithvi WxC: Foundation Model for Weather and Climate(Prithvi WxC:天气和气候的基础模型) [02:15] 🎵 MuCodec: Ultra Low-Bitrate Music Codec(MuCodec:超低比特率音乐编解码器) [02:51] 🌈 Colorful Diffuse Intrinsic Image Decomposition in the Wild(在野外进行彩色漫反射内在图像分解) [03:29] 🎥 Portrait Video Editing Empowered by Multimodal Generative Priors(基于多模态生成先验的肖像视频编辑) [04:01] 🎥 Temporally Aligned Audio for Video with Autoregression(基于自回归的视频音频时间对齐生成) [04:38] 📱 V^3: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussians(V^3:通过可流式2D动态高斯函数在移动设备上观看体积视频) [05:21] 📚 Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation(事实、获取与推理:检索增强生成的统一评估) [05:57] 🛡 Hackphyr: A Local Fine-Tuned LLM Agent for Network Security Environments(Hackphyr:用于网络安全环境的本地微调LLM代理) [06:34] 🎻 Minstrel: Structural Prompt Generation with Multi-Agents Coordination for Non-AI Experts(Minstrel:面向非AI专家的多智能体协同结构化提示生成) 【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

7分钟
77
7个月前
EarsOnMe

加入我们的 Discord

与播客爱好者一起交流

立即加入

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