periodic update

bookshelf/papers/06c15c86dccb7f0534ade3dedcbadee4-li-zhengqi-and-tuck/info.yaml

@@ -0,0 +1,34 @@
+abstract: We present an approach to modeling an image-space prior on scene dynamics.
+  Our prior is learned from a collection of motion trajectories extracted from real
+  video sequences containing natural, oscillating motion such as trees, flowers, candles,
+  and clothes blowing in the wind. Given a single image, our trained model uses a
+  frequency-coordinated diffusion sampling process to predict a per-pixel long-term
+  motion representation in the Fourier domain, which we call a neural stochastic motion
+  texture. This representation can be converted into dense motion trajectories that
+  span an entire video. Along with an image-based rendering module, these trajectories
+  can be used for a number of downstream applications, such as turning still images
+  into seamlessly looping dynamic videos, or allowing users to realistically interact
+  with objects in real pictures.
+archiveprefix: arXiv
+author: Li, Zhengqi and Tucker, Richard and Snavely, Noah and Holynski, Aleksander
+author_list:
+- family: Li
+  given: Zhengqi
+- family: Tucker
+  given: Richard
+- family: Snavely
+  given: Noah
+- family: Holynski
+  given: Aleksander
+eprint: 2309.07906v1
+file: 2309.07906v1.pdf
+files:
+- li-zhengqi-and-tucker-richard-and-snavely-noah-and-holynski-aleksandergenerative-image-dynamics2023.pdf
+month: Sep
+primaryclass: cs.CV
+ref: 2309.07906v1
+time-added: 2023-09-21-10:22:52
+title: Generative Image Dynamics
+type: article
+url: http://arxiv.org/abs/2309.07906v1
+year: '2023'

bookshelf/papers/0c32fb3c9790514c9f5c519107798b5b/info.yaml

@@ -0,0 +1,11 @@
+language: en
+month: August
+ref: noauthor_transformer:_2017
+shorttitle: Transformer
+time-added: 2023-09-21-16:10:31
+title: 'Transformer: {A} {Novel} {Neural} {Network} {Architecture} for {Language}
+  {Understanding}'
+type: misc
+url: https://blog.research.google/2017/08/transformer-novel-neural-network.html
+urldate: '2023-09-21'
+year: '2017'

bookshelf/papers/18bffe3e55f688320583a30cbab243b3-zhou-wangchunshu-an/info.yaml

@@ -0,0 +1,53 @@
+abstract: The fixed-size context of Transformer makes GPT models incapable of generating
+  arbitrarily long text. In this paper, we introduce RecurrentGPT, a language-based
+  simulacrum of the recurrence mechanism in RNNs. RecurrentGPT is built upon a large
+  language model (LLM) such as ChatGPT and uses natural language to simulate the Long
+  Short-Term Memory mechanism in an LSTM. At each timestep, RecurrentGPT generates
+  a paragraph of text and updates its language-based long-short term memory stored
+  on the hard drive and the prompt, respectively. This recurrence mechanism enables
+  RecurrentGPT to generate texts of arbitrary length without forgetting. Since human
+  users can easily observe and edit the natural language memories, RecurrentGPT is
+  interpretable and enables interactive generation of long text. RecurrentGPT is an
+  initial step towards next-generation computer-assisted writing systems beyond local
+  editing suggestions. In addition to producing AI-generated content (AIGC), we also
+  demonstrate the possibility of using RecurrentGPT as an interactive fiction that
+  directly interacts with consumers. We call this usage of generative models by ``AI
+  As Contents'' (AIAC), which we believe is the next form of conventional AIGC. We
+  further demonstrate the possibility of using RecurrentGPT to create personalized
+  interactive fiction that directly interacts with readers instead of interacting
+  with writers. More broadly, RecurrentGPT demonstrates the utility of borrowing ideas
+  from popular model designs in cognitive science and deep learning for prompting
+  LLMs. Our code is available at https://github.com/aiwaves-cn/RecurrentGPT and an
+  online demo is available at https://www.aiwaves.org/recurrentgpt.
+archiveprefix: arXiv
+author: Zhou, Wangchunshu and Jiang, Yuchen Eleanor and Cui, Peng and Wang, Tiannan
+  and Xiao, Zhenxin and Hou, Yifan and Cotterell, Ryan and Sachan, Mrinmaya
+author_list:
+- family: Zhou
+  given: Wangchunshu
+- family: Jiang
+  given: Yuchen Eleanor
+- family: Cui
+  given: Peng
+- family: Wang
+  given: Tiannan
+- family: Xiao
+  given: Zhenxin
+- family: Hou
+  given: Yifan
+- family: Cotterell
+  given: Ryan
+- family: Sachan
+  given: Mrinmaya
+eprint: 2305.13304v1
+file: 2305.13304v1.pdf
+files:
+- zhou-wangchunshu-and-jiang-yuchen-eleanor-and-cui-peng-and-wang-tiannan-and-xiao-zhenxin-and-hou-yifan-and-cotterell-ryan-and-sachan-mrinmayar.pdf
+month: May
+primaryclass: cs.CL
+ref: 2305.13304v1
+time-added: 2023-09-21-09:11:38
+title: 'RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text'
+type: article
+url: http://arxiv.org/abs/2305.13304v1
+year: '2023'

bookshelf/papers/18cb5019904c96b57b3b26d4361bb077-penrose-roger/info.yaml

@@ -0,0 +1,12 @@
+author: Penrose, Roger
+author_list:
+- family: Penrose
+  given: Roger
+files:
+- penrose-rogercycles-of-time-an-extraordinary-new-view-of-the-universe2010.pdf
+publisher: Random House
+ref: penrose2010cycles
+time-added: 2023-09-21-19:31:35
+title: 'Cycles of time: an extraordinary new view of the universe'
+type: book
+year: '2010'

bookshelf/papers/18de98e2a35851f416d675fadc6d15bb/info.yaml

@@ -0,0 +1,12 @@
+abstract: The Signal Protocol is a set of cryptographic specifications that provides
+  end-to-end encryption for private communications exchanged daily by billions of
+  people around the world. After its publication in 2013, the Signal Protocol was
+  adopted not only by Signal but well beyond. Technical informat...
+journal: Signal Messenger
+language: en
+ref: noauthor_quantum_nodate
+time-added: 2023-09-20-08:22:14
+title: Quantum {Resistance} and the {Signal} {Protocol}
+type: misc
+url: https://signal.org/blog/pqxdh/
+urldate: '2023-09-20'

bookshelf/papers/19fc620a0726b4bbc79fd65e8a0c1b29-pueyo-tomas/info.yaml

@@ -0,0 +1,12 @@
+abstract: The near infinite ramifications of having a uterus
+author: Pueyo, Tomas
+author_list:
+- family: Pueyo
+  given: Tomas
+language: en
+ref: pueyo_what_nodate
+time-added: 2023-09-20-09:02:58
+title: What {Makes} {Men} and {Women} {Different}?
+type: misc
+url: https://unchartedterritories.tomaspueyo.com/p/what-makes-men-and-women-different
+urldate: '2023-09-20'

bookshelf/papers/1f20ba18f56a2b44649e26e2ba9595e4-contreras-gilberto/info.yaml

@@ -0,0 +1,16 @@
+author: Contreras, Gilberto and Martonosi, Margaret
+author_list:
+- family: Contreras
+  given: Gilberto
+- family: Martonosi
+  given: Margaret
+booktitle: 2008 IEEE International Symposium on Workload Characterization
+files:
+- contreras-gilberto-and-martonosi-margaretcharacterizing-and-improving-the-performance-of-intel-threading-building-blocks2008.pdf
+organization: IEEE
+pages: 57--66
+ref: contreras2008characterizing
+time-added: 2023-09-19-16:39:44
+title: Characterizing and improving the performance of intel threading building blocks
+type: inproceedings
+year: '2008'

bookshelf/papers/23a9b0ebe5e83846153d56cbc6b1637d-besta-maciej-and-sc/info.yaml

@@ -0,0 +1,35 @@
+abstract: The growing size of data center and HPC networks pose unprecedented requirements
+  on the scalability of simulation infrastructure. The ability to simulate such large-scale
+  interconnects on a simple PC would facilitate research efforts. Unfortunately, as
+  we first show in this work, existing shared-memory packet-level simulators do not
+  scale to the sizes of the largest networks considered today. We then illustrate
+  a feasibility analysis and a set of enhancements that enable a simple packet-level
+  htsim simulator to scale to the unprecedented simulation sizes on a single PC. Our
+  code is available online and can be used to design novel schemes in the coming era
+  of omnipresent data centers and HPC clusters.
+archiveprefix: arXiv
+author: Besta, Maciej and Schneider, Marcel and Girolamo, Salvatore Di and Singla,
+  Ankit and Hoefler, Torsten
+author_list:
+- family: Besta
+  given: Maciej
+- family: Schneider
+  given: Marcel
+- family: Girolamo
+  given: Salvatore Di
+- family: Singla
+  given: Ankit
+- family: Hoefler
+  given: Torsten
+eprint: 2105.12663v1
+file: 2105.12663v1.pdf
+files:
+- besta-maciej-and-schneider-marcel-and-girolamo-salvatore-di-and-singla-ankit-and-hoefler-torstentowards-million-server-network-simulations-on-jus.pdf
+month: May
+primaryclass: cs.NI
+ref: 2105.12663v1
+time-added: 2023-09-19-11:39:50
+title: Towards Million-Server Network Simulations on Just a Laptop
+type: article
+url: http://arxiv.org/abs/2105.12663v1
+year: '2021'

bookshelf/papers/255236f5b53554af5e9435fe0b4bbbf6-badiru-adedeji-b-an/info.yaml

@@ -0,0 +1,15 @@
+author: Badiru, Adedeji B and Asaolu, Olumuyiwa
+author_list:
+- family: Badiru
+  given: Adedeji B
+- family: Asaolu
+  given: Olumuyiwa
+files:
+- badiru-adedeji-b-and-asaolu-olumuyiwahandbook-of-mathematical-and-digital-engineering-foundations-for-artificial-intelligence-a-systems-methodology.pdf
+publisher: CRC Press
+ref: badiru2023handbook
+time-added: 2023-09-23-19:02:20
+title: 'Handbook of Mathematical and Digital Engineering Foundations for Artificial
+  Intelligence: A Systems Methodology'
+type: book
+year: '2023'

bookshelf/papers/26884f501d0e10a77421f24afb9ed046-pedro-domingos-and/info.yaml

@@ -0,0 +1,14 @@
+author: Pedro, Domingos and Lowd, D
+author_list:
+- family: Pedro
+  given: Domingos
+- family: Lowd
+  given: D
+files:
+- pedro-domingos-and-lowd-dmarkov-logic-an-interface-layer-for-artificial-intelligence2009.pdf
+journal: Morgan \& Claypool
+ref: pedro2009markov
+time-added: 2023-09-23-19:01:55
+title: 'Markov Logic: An Interface Layer for Artificial Intelligence'
+type: article
+year: '2009'

bookshelf/papers/4b7c021f4bcae47f168c48f19eba0faf-bierlaire-michel/info.yaml

@@ -0,0 +1,13 @@
+author: Bierlaire, Michel
+author_list:
+- family: Bierlaire
+  given: Michel
+files:
+- bierlaire-micheloptimization-principles-and-algorithms2015.pdf
+number: BOOK
+publisher: EPFL Press
+ref: bierlaire2015optimization
+time-added: 2023-09-23-19:03:56
+title: 'Optimization: principles and algorithms'
+type: book
+year: '2015'

bookshelf/papers/59c269858a7b382f870cf160f4328203-croll-angus/info.yaml

@@ -0,0 +1,12 @@
+author: Croll, Angus
+author_list:
+- family: Croll
+  given: Angus
+files:
+- croll-angusif-hemingway-wrote-javascript2014.pdf
+publisher: No Starch Press
+ref: croll2014if
+time-added: 2023-09-19-16:35:30
+title: If Hemingway wrote javascript
+type: book
+year: '2014'

bookshelf/papers/60b2805624fbe75f9cf340d224f81e8c-cassioli-andrea/info.yaml

@@ -0,0 +1,12 @@
+author: Cassioli, Andrea
+author_list:
+- family: Cassioli
+  given: Andrea
+files:
+- cassioli-andreaa-tutorial-on-black-box-optimization2013.pdf
+publisher: 'Available also from: https://www. lix. polytechnique. fr/\~{} dambrosio~…'
+ref: cassioli2013tutorial
+time-added: 2023-09-22-15:37:41
+title: A tutorial on black--box optimization
+type: article
+year: '2013'

bookshelf/papers/6959b66a0758ec2c8e27db890597db70-yang-chengrun-and-w/info.yaml

@@ -0,0 +1,42 @@
+abstract: Optimization is ubiquitous. While derivative-based algorithms have been
+  powerful tools for various problems, the absence of gradient imposes challenges
+  on many real-world applications. In this work, we propose Optimization by PROmpting
+  (OPRO), a simple and effective approach to leverage large language models (LLMs)
+  as optimizers, where the optimization task is described in natural language. In
+  each optimization step, the LLM generates new solutions from the prompt that contains
+  previously generated solutions with their values, then the new solutions are evaluated
+  and added to the prompt for the next optimization step. We first showcase OPRO on
+  linear regression and traveling salesman problems, then move on to prompt optimization
+  where the goal is to find instructions that maximize the task accuracy. With a variety
+  of LLMs, we demonstrate that the best prompts optimized by OPRO outperform human-designed
+  prompts by up to 8% on GSM8K, and by up to 50% on Big-Bench Hard tasks.
+archiveprefix: arXiv
+author: Yang, Chengrun and Wang, Xuezhi and Lu, Yifeng and Liu, Hanxiao and Le, Quoc
+  V. and Zhou, Denny and Chen, Xinyun
+author_list:
+- family: Yang
+  given: Chengrun
+- family: Wang
+  given: Xuezhi
+- family: Lu
+  given: Yifeng
+- family: Liu
+  given: Hanxiao
+- family: Le
+  given: Quoc V.
+- family: Zhou
+  given: Denny
+- family: Chen
+  given: Xinyun
+eprint: 2309.03409v1
+file: 2309.03409v1.pdf
+files:
+- yang-chengrun-and-wang-xuezhi-and-lu-yifeng-and-liu-hanxiao-and-le-quoc-v.-and-zhou-denny-and-chen-xinyunlarge-language-models-as-optimizers202.pdf
+month: Sep
+primaryclass: cs.LG
+ref: 2309.03409v1
+time-added: 2023-09-18-09:05:38
+title: Large Language Models as Optimizers
+type: article
+url: http://arxiv.org/abs/2309.03409v1
+year: '2023'

bookshelf/papers/9380f5dcae18e8970e532d0d58ea2965-varley-thomas-f./info.yaml

@@ -0,0 +1,39 @@
+abstract: 'In the 21st century, many of the crucial scientific and technical issues
+  facing humanity can be understood as problems associated with understanding, modelling,
+  and ultimately controlling complex systems: systems comprised of a large number
+  of non-trivially interacting components whose collective behaviour can be difficult
+  to predict. Information theory, a branch of mathematics historically associated
+  with questions about encoding and decoding messages, has emerged as something of
+  a lingua franca for those studying complex systems, far exceeding its original narrow
+  domain of communication systems engineering. In the context of complexity science,
+  information theory provides a set of tools which allow researchers to uncover the
+  statistical and effective dependencies between interacting components; relationships
+  between systems and their environment; mereological whole-part relationships; and
+  is sensitive to non-linearities missed by commonly parametric statistical models.   In
+  this review, we aim to provide an accessible introduction to the core of modern
+  information theory, aimed specifically at aspiring (and established) complex systems
+  scientists. This includes standard measures, such as Shannon entropy, relative entropy,
+  and mutual information, before building to more advanced topics, including: information
+  dynamics, measures of statistical complexity, information decomposition, and effective
+  network inference. In addition to detailing the formal definitions, in this review
+  we make an effort to discuss how information theory can be interpreted and develop
+  the intuition behind abstract concepts like "entropy," in the hope that this will
+  enable interested readers to understand what information is, and how it is used,
+  at a more fundamental level.'
+archiveprefix: arXiv
+author: Varley, Thomas F.
+author_list:
+- family: Varley
+  given: Thomas F.
+eprint: 2304.12482v2
+file: 2304.12482v2.pdf
+files:
+- varley-thomas-f.information-theory-for-complex-systems-scientists2023.pdf
+month: Apr
+primaryclass: cs.IT
+ref: 2304.12482v2
+time-added: 2023-09-18-17:06:01
+title: Information Theory for Complex Systems Scientists
+type: article
+url: http://arxiv.org/abs/2304.12482v2
+year: '2023'

bookshelf/papers/9a3b61f61d39ce760a45a67c4fcfc788-edelkamp-stefan/info.yaml

@@ -2,6 +2,8 @@ author: Edelkamp, Stefan
 author_list:
 - family: Edelkamp
   given: Stefan
+files:
+- edelkamp-stefanalgorithmic-intelligence-towards-an-algorithmic-foundation-for-artificial-intelligence2023.pdf
 publisher: Springer
 ref: edelkamp2023algorithmic
 time-added: 2023-06-12-10:49:51

bookshelf/papers/9b53cc9fac94bb9e2bd425ac5b39ae4f-vieira-tim/info.yaml

@@ -0,0 +1,11 @@
+author: Vieira, Tim
+author_list:
+- family: Vieira
+  given: Tim
+date: '2023'
+ref: noauthor_archive_nodate
+time-added: 2023-09-22-15:39:48
+title: Archive — {Graduate} {Descent}
+type: misc
+url: https://timvieira.github.io/blog/
+urldate: '2023-09-22'

bookshelf/papers/a18af6d122f0fb3737814bea861e149f-pettit-philip/info.yaml

@@ -0,0 +1,12 @@
+author: Pettit, Philip
+author_list:
+- family: Pettit
+  given: Philip
+files:
+- pettit-philipa-theory-of-freedom-from-the-psychology-to-the-politics-of-agency2001.pdf
+publisher: Oxford University Press, USA
+ref: pettit2001theory
+time-added: 2023-09-23-19:03:25
+title: 'A theory of freedom: from the psychology to the politics of agency'
+type: book
+year: '2001'