naïve oculus

Readings in computer vision, machine learning &c., selected by @permutans. Biosci account: @naivelocus, mathematics: @appendens, physics/dynamics: @systems_spin

[naïve oculus @naiveoculus]

📄 Uchendu & Le (2024) Unveiling Topological Structures in Text: A Comprehensive Survey of Topological Data Analysis Applications in NLP https://t.co/GrgV0E5JAC

[naïve oculus @naiveoculus]

📄 Piantadosi & Hill (2022) Meaning without reference in large language models https://t.co/bjzXLmPOxD

[naïve oculus @naiveoculus]

📄 Hill (2023) Why transformers are obviously good models of language https://t.co/mZUk55ZjAQ

[naïve oculus @naiveoculus]

📄 Sculley et al. (2015) Hidden Technical Debt in Machine Learning Systems https://t.co/lLiOaMIDZo
💼 Google

[naïve oculus @naiveoculus]

🎞️ [Slides] The State of Production ML | PyData Global 2023 https://t.co/iHSJtbuL6R
👨‍💻 Alejandro Saucedo @AxSaucedo (@ZalandoTech)

🗃️ awesome-mlops repo: https://t.co/QwdyC7ETWz
📺 PyCon Keynote on ML Monitoring: https://t.co/QN7hLG3Hrk

[naïve oculus @naiveoculus]

📺 Tony Bagnall — Let’s do the time warp again: time series machine learning with distance functions | PyData Amsterdam (PDAMS) 2023 https://t.co/WuhaGySQ2F
💾 aeon https://t.co/0pEbPCjP2Q
🌐 Docs https://t.co/6zzGM8wLeH

[naïve oculus @naiveoculus]

📄 Watanabe et al. (2023) SpectralMAP: Approximating Data Manifold With Spectral Decomposition https://t.co/cTtAo0azJy

[naïve oculus @naiveoculus]

📄 Draganov & Dohn (2023) Unexplainable Explanations: Towards Interpreting tSNE and UMAP Embeddings (arX⠶2306.11898v1 [cs⠶LG]) https://t.co/kEL9jIsD7a

[naïve oculus @naiveoculus]

📄 Kumari et al. (2020) ShapeVis: High-dimensional Data Visualization at Scale (arX⠶2001.05166v2 [cs⠶LG]) https://t.co/FccN0sNFGc
💼 Adobe

[naïve oculus @naiveoculus]

📜 Christopher H.F. Baird — Problematising Speed in and Around Organisations: Struggles Over the Temporal Commons in the British AI Field [DPhil thesis, December 2021] https://t.co/k4hKoZLNbD

[naïve oculus @naiveoculus]

📄 Cao et al. (2023) Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration (arX⠶2309.01131v1 [cs⠶CV]) https://t.co/1mHBGUpmgI

[naïve oculus @naiveoculus]

📄 Liu et al. (2023) Lost in the Middle: How Language Models Use Long Contexts (arX⠶2307.03172v1 [cs⠶CL]) https://t.co/4inIqRGU25

[naïve oculus @naiveoculus]

📄 Ding et al. (2023) LongNet: Scaling Transformers to 1,000,000,000 Tokens (arX⠶2307.02486v2 [cs⠶CL]) https://t.co/FyHoFGQoxe
💾 https://t.co/dCvDRqutny

[naïve oculus @naiveoculus]

📄 Dong et al. (2023) A Survey on Long Text Modeling with Transformers (arX⠶2302.14502v1 [cs⠶CL]) https://t.co/IGKjzU4kge

[naïve oculus @naiveoculus]

📄 Phang et al. (2022) Investigating Efficiently Extending Transformers for Long Input Summarization (arX⠶2208.04347v1 [cs⠶CL]) https://t.co/AGoWIsB6Lq
💾 https://t.co/CDniXiPz4O
🤗 https://t.co/HlxQsFyc8o

[naïve oculus @naiveoculus]

📄 Wang et al. (2023) Exploiting Diffusion Prior for Real-World Image Super-Resolution (arX⠶2305.07015v1 [cs⠶CV]) https://t.co/baadGd4uJb
🌐 https://t.co/gWmR3l2bGx
💾 StableSR https://t.co/9hxFDmKwhp
🤗 https://t.co/xC4r2bqy3a

[naïve oculus @naiveoculus]

📺 CIS 7000: Uncertain: Modern Topics in Uncertainty Quantification https://t.co/zBOOmEmzrb
🌐 Class website https://t.co/0MSxzOUWsk
📄 Lecture notes https://t.co/ZKtsDmGJF6
🎞️ Slides https://t.co/zLu7NMFuhf
👨‍🏫 Aaron Roth https://t.co/ef8ZHMmuMf

[naïve oculus @naiveoculus]

📄 Dhouib et al. (2023) DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documents (arX⠶2304.12484v1 [cs⠶CV]) https://t.co/93elKDL4BY

[naïve oculus @naiveoculus]

📄 Segert & Cohen (2023) Beyond Transformers for Function Learning (arX⠶2304.09979v1 [cs⠶LG]) https://t.co/5qBN3YRdIV

[naïve oculus @naiveoculus]

📄 Liu et al. (2023) DocMAE: Document Image Rectification via Self-supervised Representation Learning (arX⠶2304.10341v1 [cs⠶CV]) https://t.co/aM67jDqktT
💼 iFlytek