Multimodal

Diffusion

Important

• [calvinyluo.com] Understanding Diffusion Models: A Unified Perspective

• [arxiv] Tutorial on Diffusion Models for Imaging and Vision

• Diffusion Augmented Agents: A Framework for Efficient Exploration and Transfer Learning

Tech

• [anthropic.com]

  • Anthropic Research

  • Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

  • Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet

  • Towards Understanding Sycophancy in Language Models

  • Specific versus General Principles for Constitutional AI

  • Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

  • Simple probes can catch sleeper agents

  • Challenges in evaluating AI systems

  • AI Governance and Accountability: An Analysis of Anthropic’s Claude

  • Claude (Claude on Bedrock)

• [mistral.ai] Mixtral (Mixtral on Bedrock)

• [ai.meta.com Llama (Llama on Bedrock)

• [stability.ai] Stable Diffusion (Stable Diffusion on Bedrock)

• [blog.google] Gemini

• [openai.com]

  • GPT-4o

  • [DALL·E]: Creating images from text

  • [SoRa]: Video generation models as world simulators

  • DALL·E 2

Resources

Industry

• Amazon Science: ML, GenAI

  • A quick guide to Amazon’s papers at ICML 2024

  • List of publications

  • Conversational AI

  • Large language models (LLMs)

  • Computer vision

  • Code and datasets

  • AWS News Blog:

    • Category: Amazon Machine Learning

    • Category: Generative AI

• Pinterest

  • PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest

• [research.google] Transformers in music recommendation

Misc

• Yann LeCun

  • Google Scholar Page

  • Arxiv Page

• [neptune.ai] 6 GAN Architectures You Really Should Know

Paper List

Year	Paper
2023	Align your latents: High-resolution video synthesis with latent diffusion models
2023	Photorealistic video generation with diffusion models
2023	Patch n’Pack: NaViT a Vision Transformer for any Aspect Ratio and Resolution
2023	Scalable diffusion models with transformers
2023	Improving image generation with better captions
2022	Generating long videos of dynamic scenes
2022	NUwa: Visual synthesis pre-training for neural visual world creation
2022	Imagen video: High definition video generation with diffusion models
2022	Masked autoencoders are scalable vision learners
2022	High-resolution image synthesis with latent diffusion models
2022	Elucidating the design space of diffusion-based generative models
2022	Scaling autoregressive models for content-rich text-to-image generation
2022	Hierarchical text-conditional image generation with clip latents
2021	Videogpt: Video generation using vq-vae and transformers
2021	Vivit: A video vision transformer
2021	Improved denoising diffusion probabilistic models
2021	Diffusion Models Beat GANs on Image Synthesis
2021	Zero-shot text-to-image generation
2021	Sdedit: Guided image synthesis and editing with stochastic differential equations
2020	Language models are few-shot learners
2020	An image is worth 16x16 words: Transformers for image recognition at scale
2020	Denoising diffusion probabilistic models
2020	Generative pretraining from pixels
2019	Adversarial video generation on complex datasets
2018	World models
2018	Mocogan: Decomposing motion and content for video generation
2017	Recurrent environment simulators
2017	Attention is all you need
2016	Generating videos with scene dynamics
2015	Unsupervised learning of video representations using lstms
2015	Deep unsupervised learning using nonequilibrium thermodynamics
2013	Auto-encoding variational bayes