V
主页
[论文速览]Generative Modeling by Estimating Gradients of the Data Dist[1907.05600]
发布人
论文题目: Generative Modeling by Estimating Gradients of the Data Distribution / NCSN / score based method 论文地址: http://arxiv.org/abs/1907.05600 代码:https://github.com/ermongroup/ncsn * 本视频旨在传递一篇论文的存在推荐感兴趣的您阅读,并不是详细介绍,受up能力限制经常出现中英混杂,散装英语等现象,请见谅。如论文报道出了偏差,欢迎各位怒斥。 ** 新论文推荐,过往论文查找,欢迎编辑这个文档: https://docs.qq.com/sheet/DSUdOTG9xWUdydVB6 *** Slides每1-2月会上传到置顶动态地址
打开封面
下载高清视频
观看高清视频
视频下载器
扩散模型的【经典论文】入门学习路径
[论文夕拾]Diffusion Models for Robotics
[论文简析]VQ-VAE:Neural discrete representation learning[1711.00937]
[论文简析]Visual Autoregressive Modeling: ...via Next-Scale Prediction[2404.02905]
[论文速览]DDPG&TD3[1509.02971][1802.09477]
[论文简析]VAE: Auto-encoding Variational Bayes[1312.6114]
[论文简析]Deep Unsupervised Learning using Nonequilibrium Thermodynamics[1503.03585]
【公式推导】条件流匹配CFM:证明FM和CFM的目标关于参数的梯度一致【3.2节】【定理2】
[论文简析]DeiT: Data-efficient Image Transformers[2012.12877]
2.1介绍流Flow的定义和作用,理解向量场vt和ODE
[论文简析]SAC: Soft Actor-Critic Part 1[1801.01290]
[论文速览]Denoising Diffusion Implicit Models / DDIM[2010.02502]
西交|深度学习研讨班-4|从Attention到Transformer再到Mamba
2.2介绍连续归一化流CNF(Continuous Normalizing Flows)的定义和性质【流flow、向量场v和概率密度p三者之间的关系】
[论文速览]Decision Transformer: RL via Sequence Modeling[2106.01345]
[论文速览]Visual Prompt Tuning / VPT[2203.12119]
[论文速览]Open Vocab. Semantic Seg. with Patch Aligned Contrastive...[2212.04994]
[论文速览]LoRA: Low-Rank Adaptation of Large Language Models[2106.09685]
[论文速览]Open-vocabulary Object Segmentation with Diffusion Models[2301.05221]
[论文速览]RetNet: A Successor to Transformer for Large Language Models[2307.08621]
[论文简析]Reinforcement Learning with Augmented Data: RAD[2004.14990]
[论文速览]Autoregressive Image Generation using Residual Quantization[2203.01941]
[论文速览]Rethinking the Truly Unsupervised Image-to-Image Translation[2006.06500]
[论文速览]Token Turing Machines[2211.09119]
[论文速览]Flamingo: a Visual Language Model for Few-Shot Learning[2204.14198]
[论文简析]Representation Learning with Contrastive Predictive Coding[1807.03748]
[论文速览]Drag Your GAN: Interactive Point-based Manipulation...[2305.10973]
[论文速览]LLaRA: Supercharging Robot Learning Data for VLM Policy[2406.20095]
[论文简析]Large Language Models as General Pattern Machines[2307.04721]
[论文速览]Diffusion Policy: Visuomotor Policy Learning via Action Diff.[2303.04137]
[论文简析]A Laplacian Pyramid Translation Network[2105.09188]
[论文简析]Contrastive Learning for Unpaired Image-to-Image Translation[2007.15651]
[论文简析]RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real[2006.09001]
扩散模型论文概述(一):OpenAI系列工作
[论文简析]DAT: Vision Transformer with Deformable Attention[2201.00520]
[论文简析]FlowNet3D: Learning Scene Flow in 3D Point Clouds[1806.01411]
讲座 | HiDiffusion:高效、无需训练的更高分辨率图像生成框架——旷视研究院高级研究员张慎
[论文速览]EViT: Expediting Vision Transformers via Token Reorganizations[2202.07800]
[论文速览]Personalizing Text2Img Generation using Textual Inversion[2208.01618]
[论文速览]LLaMA-Adapter: Efficient Fine-tuning..Zero-init Attention[2303.16199]