This is my reading note on TokenFlow Consistent Diffusion Features for Consistent Video Editing, which is diffusion based on video editing method. This paper proposes a method to edit a video given text prompt. To do this, the paper relies on two things. First, it extracts bey lames from video and perform image on those key frames jointly. In addition, the paper found that the feature in diffusion has strong correspondence to the pixels. As a results it propose to propagate the features of edited key frames to other frames, accord to the correspondence in the original video.

This is my reading note on Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models. The paper explains the theory of using a pre-trained diffusion model to guide the training of a generator model.it shows that both DreamFusion and GAN are a special case of it: score distillation sampling (SDS) from DreamFusion uses Dirac distribution to represent the generator while GAN learns a discriminator to represents the distribution of data. To this end, it proposes IKL, which is tailored for DMs by calculating the integral of the KL divergence along a diffusion process (instead of a single step), which we show to be more robust in comparing distributions with misaligned supports.

This is my reading note on Efficient Geometry-aware 3D Generative Adversarial Networks. EG3D proposes a 20 to 3D generate method base style gan and triplane based nerf. The high level idea is to use style gan to generate triplane, which is then rendered into images. The rendered image is the discriminated to the input images at two resolutions. The camera pose is also required to generate the triplane.

This is my read note on Tool Learning with Foundation Models

Humans possess an extraordinary ability to create and utilize tools, allowing them to overcome physical limitations and explore new frontiers. With the advent of foundation models, AI systems have the potential to be equally adept in tool use as humans. This paradigm, i.e., tool learning with foundation models, combines the strengths of specialized tools and foundation models to achieve enhanced accuracy, efficiency, and automation in problem-solving. Despite its immense potential, there is still a lack of a comprehensive understanding of key challenges, opportunities, and future endeavors in this field. To this end, we present a systematic investigation of tool learning in this paper. We first introduce the background of tool learning, including its cognitive origins, the paradigm shift of foundation models, and the complementary roles of tools and models. Then we recapitulate existing tool learning research into tool-augmented and tool-oriented learning. We formulate a general tool learning framework: starting from understanding the user instruction, models should learn to decompose a complex task into several subtasks, dynamically adjust their plan through reasoning, and effectively conquer each sub-task by selecting appropriate tools. We also discuss how to train models for improved tool-use capabilities and facilitate the generalization in tool learning. Considering the lack of a systematic tool learning evaluation in prior works, we experiment with 18 representative tools and show the potential of current foundation models in skillfully utilizing tools. Finally, we discuss several open problems that require further investigation for tool learning. Overall, we hope this paper could inspire future research in integrating tools with foundation models.

This is my reading note on Knowledge Distillation: A Survey. As a representative type of model compression and acceleration, knowledge distillation effectively learns a small student model from a large teacher model (p. 1)

This is my reading note on 3D Gaussian Splatting for Real-Time Radiance Field Rendering(best paper of SIGGRAPH 2023) and its extension Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis, which enables it to track dynamic objects/scenes.

This is my set up to enable Obsidian work with Zotero to export Zotero note and publish to my Github website. You could create your own website on Github using JekyII, which requires you to create markdown files with a specific front matter format. Then Github will publish your markdown files to html.

This is my reading note on StableVideo: Text-driven Consistency-aware Diffusion Video Editing. This paper proposes a video editing method based on diffusion. To ensure temporal consistency, the method utilizes neural atlas and inter frame interpolation. The neural atlas separate the videos into foreground and background plane. The lattes defines the mapping of pixel in frame to u v coordinate in atlas. For inter frame interpolation, the edited imago from diffusion is mapping to next frame via atlas, which is then use as initial to denote to the final contents of this frame.

This is my reading note for BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing. The paper proposes a method for generating an image with text prompt and target visual concept. To do that the paper trained blip model to align visual features with text prompt and then concatenate the visual embedding to the text prompt to generate the need. Code and models will be released at https://github.com/salesforce/LAVIS/tree/main/projects/blip-diffusion. Project page at https://dxli94.github.io/BLIP-Diffusion-website/.

This is my reading note on ProlificDreamer High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation. This method proposes variational score sampling to replace score distillation sampling to improve the details of text to image or text to 3D models. Project page: https://ml.cs.tsinghua.edu.cn/prolificdreamer/