For almost all of 2022 I have been reading a paper a day, not necessarily Machine Learning or even Computer Science. This year being motivated by Lex Fridman I will be maintaining my reading list.
Jan 1: Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks (https://arxiv.org/abs/1810.00825)
Jan 2:Â A Generalization of ViT/MLP-Mixer to Graphs (https://arxiv.org/abs/2212.13350)
Jan 3: ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders (https://arxiv.org/abs/2301.00808)
Jan 4: Muse: Text-To-Image Generation via Masked Generative Transformers (https://arxiv.org/abs/2301.00704)
Jan 5: PHANGS-JWST First Results: Variations in PAH Fraction as a Function of ISM Phase and Metallicity (https://arxiv.org/abs/2301.00578)
Jan 6: Learning One Abstract Bit at a Time Through Self-Invented Experiments Encoded as Neural Networks (https://arxiv.org/abs/2212.14374)
Jan 7: Rethinking Mobile Block for Efficient Neural Models (https://arxiv.org/abs/2301.01146)
Jan 8: Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve (https://arxiv.org/abs/2212.03905)
Jan 9: The Forward-Forward Algorithm: Some Preliminary Investigations (https://arxiv.org/abs/2212.13345)
Jan 10-12: Highly accurate protein structure prediction with AlphaFold, Supplementary (https://static-content.springer.com/esm/art%3A10.1038%2Fs41586-021-03819-2/MediaObjects/41586_2021_3819_MOESM1_ESM.pdf)
Jan 13: Scalable Diffusion Models with Transformers (https://arxiv.org/abs/2212.09748)
Jan 14: WIRE: Wavelet Implicit Neural Representations (https://arxiv.org/abs/2301.05187)
Jan 15: SemPPL: Predicting pseudo-labels for better contrastive representations (https://arxiv.org/abs/2301.05158)
Jan 16: Tracr: Compiled Transformers as a Laboratory for Interpretability (https://arxiv.org/abs/2301.05062)
Jan 17: Guiding Text-to-Image Diffusion Model Towards Grounded Generation (https://arxiv.org/abs/2301.05221)
Jan 18: Domain Generalization using Causal Matching (https://arxiv.org/abs/2006.07500)
Jan19: Fast Jacobian-Vector Product for Deep Networks (https://arxiv.org/abs/2104.00219)
Jan 20: On the Continuity of Rotation Representations in Neural Networks (http://arxiv.org/abs/1812.07035)
February 8-11: Causal Effect Inference with Deep Latent-Variable Models (https://proceedings.neurips.cc/paper/2017/file/94b5bde6de888ddf9cde6748ad2523d1-Paper.pdf)
February 12: A Critical Look at the Consistency of Causal Estimation with Deep Latent Variable Models (https://proceedings.neurips.cc/paper/2021/file/21c5bba1dd6aed9ab48c2b34c1a0adde-Paper.pdf)
February 12-13: Do learned representations respect causal relationships? (https://openaccess.thecvf.com/content/CVPR2022/papers/Wang_Do_Learned_Representations_Respect_Causal_Relationships_CVPR_2022_paper.pdf)
February 14-16: Scaling Vision Transformers to 22 Billion Parameters (https://arxiv.org/abs/2302.05442)
February 17: Denoising Diffusion Probabilistic Models for Robust Image Super-Resolution in the Wild (https://arxiv.org/abs/2302.07864)
February 18: Big Little Transformer Decoder (https://arxiv.org/abs/2302.07863)
February19: Energy Transformer (https://arxiv.org/abs/2302.07253)