Paper Corner

Papers

01 September 2023

1. A Benchmark for General purpose visual representation

31 August 2023

1. Diffusion Models: A Comprehensive Survey of Methods and Applications
2. Efficient Diffusion Models for Vision: A Survey
3. NAVI: Category-Agnostic Image Collections with High Quality 3D Shape and Pose Annotations
4. From data to functa: Your data point is a function and you can treat it like one
   • *Very similar to hyperdiffusion
   • Has it overcome the quality issues?

29 August 2023

1. What is next for bioimage analysis?”
2. A survey on applications of deep learning in microscopy image analysis
3. Deep learning tools for advancing drug discovery and development
4. Image based profiling for drug discovery
5. A theory of cortical map formation in the visual brain

26 August 2023

1. Diffusion Processes for Inverse Problems
   • Talk @Workshop
2. ProcThor: Large-Scale Embodied AI Using Procedural Generation
   • Note: Are there similar environments to cover urban scenes?
   • Or eliminate the need like this: Learning to navigate outdoor environments without outdoor experience

25 August 2023

1. Palette: Image to Image to Diffusion Process
2. A Survey of Vision Language Pre-training models
3. Vision Language Models for Vision tasks: A Survey
4. HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion
5. Super Points

24 August 2023

1. What Can You Learn from Your Muscles? Learning Visual Representation from Human Interactions
2. Efficiently Measuring the Cognitive Ability of LLMS: An Adaptive Testing Perspective
3. VQA-HAT: Human Visual Attention in Visual Question Answering
   • Has this changed wrt to recent models?

23 August 2023

1. 3D Gaussian Splatting for Real-Time Radiance Field Rendering
   • Tutorial Reading
   • Dynamic 3D Gaussians
2. Grokking (not that relevant?)
3. On the theory of stochastic processes, with particular reference to applications
4. Formal Algorithms for Transformers
5. From Gaussian Process to NTK
   • Toward NNGP and NTK: Part I
   • Toward NNGP and NTK: Part II
   • Beyond Periodicity: Towards Unifying framework for activations for coordinate-MLPS
6. Strucutred Randome Receptive Fields Enable Informative Sensory Encodings