**Papers on my list (as of 14/06/24):** - [x] [Towards A Unified Neural Architecture for Visual Recognition and Reasoning](https://arxiv.org/pdf/2311.06386) - [x] [Vamos: Versatile Action Models for Video Understanding](https://arxiv.org/pdf/2311.13627) - [x] [Emergence of Abstract State Representations in Embodied Sequence Modeling](https://arxiv.org/pdf/2311.02171) - [x] [Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?](https://arxiv.org/pdf/2203.17271) - [x] [Self-Correcting Self-Consuming Loops for Generative Model Training](https://arxiv.org/pdf/2402.07087) - [ ] [Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environments](https://arxiv.org/pdf/2302.11649) - [x] [Pre-trained Vision-Language Models Learn Discoverable Visual Concepts](https://arxiv.org/pdf/2404.12652) - [x] [A Survey of Robotic Language Grounding: Tradeoffs Between Symbols and Embeddings](https://arxiv.org/pdf/2405.13245) - [x] [Verifiably Following Complex Robot Instructions with Foundation Models](https://arxiv.org/pdf/2402.11498) - [ ] [HumanPlus: Humanoid Shadowing and Imitation from Humans](https://humanoid-ai.github.io/HumanPlus.pdf) - [ ] [Physically Embodied Gaussian Splatting: A Realtime Correctable World Model for Robotics](https://embodied-gaussians.github.io/) - [ ] [Naturally Supervised 3D Visual Grounding with Language-Regularized Concept Learners](https://arxiv.org/abs/2404.19696) - [ ] [CCIL: Continuity-Based Data Augmentation for Corrective Imitation Learning](https://arxiv.org/pdf/2310.12972) - [ ] [BAKU: An Efficient Transformer for Multi-Task Policy Learning](https://arxiv.org/abs/2406.07539) - [ ] [OmniH2O: Universal and Dexterous Human-toHumanoid Whole-Body Teleoperation and Learning](https://omni.human2humanoid.com/resources/OmniH2O_paper.pdf) **Sparsity, Pruning, and Training Inference:** - [x] [Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency](https://arxiv.org/pdf/2303.11525) - [x] [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://arxiv.org/pdf/1803.03635) **Books:** [Programming Massively Parallel Processors](http://gpu.di.unimi.it/books/PMPP-3rd-Edition.pdf), which I'm writing about [here](obsidian://open?vault=Obsidian%20Vault&file=Notes%20and%20Guides%2FProgramming%20Massively%20Parallel%20Processors%2FCUDA%20Guide%20to%20GPU%20Programming) [Foundations of Computer Vision](https://mitpress.mit.edu/9780262048972/foundations-of-computer-vision/), which I'm using to write about NeRFs [here](obsidian://open?vault=Obsidian%20Vault&file=Notes%20and%20Guides%2FNeural%20Radiance%20Fields). [Understanding Software Dynamics](https://www.usenix.org/publications/loginonline/understanding-software-dynamics), alongside [Phil Eaton](eatonphil.com)'s [book club](https://eatonphil.com/2024-understanding-software-dynamics.html). [AI is Good for You](https://evjang.com/book/), by Eric Jang