Sam Stites @[email protected]

[Arjun Guha @ArjunGuha]

(1/5) Codex and other LLMs for code are usually benchmarked on a single PL (usually Python). We wanted to know: how do they fare on other languages? Can they generalize across PLs?

[Heiko Zimmermann 🦋 [email protected] @zmheiko]

Excited to present my work with Hao Wu (@Hao_Wu_), Babak Esmaeili (@bob_smiley_), and Jan-Willem van de Meent (@jwvdm) on Nested Variational Inference at #NeurIPS2021 today.

Come and join us in poster session 1 at spot C0.

[Sam Stites @[email protected] @SamStites]

@ChadScherrer @probprog Works for me on firefox 93 + nixos. I needed to turn on webrtc.

[Sam Stites @[email protected] @SamStites]

Interested in inference programming? Learn about work from @zmheiko and me at our #uai2021 poster session in 2h (located in https://t.co/1TnTFv8tP5 at poster III-C4)!

[Jan-Willem van de Meent @jwvdm]

New working paper: Learning Proposals for Probabilistic Programs with Inference Combinators

ArXiv: https://t.co/G0GqDqCIIi

Joint work, several years in the making, by Sam Stites* (@SamStites), Heiko Zimmermann* (@zmheiko), Hao Wu (@Hao_Wu_), and Eli Sennesh (@EliSennesh) [1/]

[Jan-Willem van de Meent @jwvdm]

New working paper: Learning Proposals for Probabilistic Programs with Inference Combinators

ArXiv: https://t.co/G0GqDqCIIi

Joint work, several years in the making, by Sam Stites* (@SamStites), Heiko Zimmermann* (@zmheiko), Hao Wu (@Hao_Wu_), and Eli Sennesh (@EliSennesh) [1/]

[PROBPROG 2021 @probprog]

PROBPROG 2021 will take place online on Wed Oct 20 – Fri Oct 22 this year. The deadline for extended abstracts and syndicated submissions is Thu May 6 AOE. See https://t.co/fdlvpQFLD8 for information and submission instructions!

[Torsten Scholak @tscholak]

I’ve got T5 working in @hasktorch.

[Torsten Scholak @tscholak]

we are already drowning in unmanageable complexity of too much software that is ridden with bugs and security flaws, and soon this will be dwarfed by oodles of bug and security flaw ridden synthesized code that fewer and fewer people will be able to maintain and understand.

[julesh @_julesh_]

I'm very happy to close the decade with a new result:

Bayesian updating is lenses - squinting not necessary

I believe this establishes the importance of lenses much more strongly than before. In categorical cybernetics they will be absolutely the central concept

[hardmaru @hardmaru]

Freedom and democracy is worth fighting for.

PyTorch vs TensorFlow or SGD vs Adam... probably not.

[PROBPROG 2021 @probprog]

#CallForSubmissions #CallforPapers PROBPROG 2020 is seeking Extended Abstracts & Syndicated Submissions by *Jan 10 2020* for our April 2020 international conference dedicated to probabilistic programming!
https://t.co/gYh9w0Frzs

[Fritz Obermeyer @ftzo]

Pyro 1.0 is released: stable APIs, a jit-compatible Predictive helper, new normalizing flows, parallel-scan GPs and state space models, more-automatic AutoGuides, an OED tutorial, FoldedDistribution, and PyroModule[-] to make your nn.Modules Bayesian https://t.co/4z1XAg9GDb

[Jan-Willem van de Meent @jwvdm]

1/ New work by Alican (@alicanb_) and Babak (@BabakEsmaeili10): "Evaluating Combinatorial Generalization in Variational Autoencoders" (https://t.co/XtB29f9FVV)

In this paper we ask the question: "To what extent do VAEs generalize to unseen combinations of features?"(thread)

[Jay DeYoung @jaydepun]

We decided to try to measure it: https://t.co/w12i09aac3

@byron_c_wallace @successar_nlp @nazneenrajani @RichardSocher

#NLProc #MachineLearning

[Jan-Willem van de Meent @jwvdm]

1/ New on arXiv: "Amortized Population Gibbs Samplers with Neural Sufficient Statistics" https://t.co/ozTcYyRy3c.

Work by: Hao Wu (@Hao_Wu_), Heiko Zimmermann (@zmheiko), Eli Sennesh (@EliSennesh), and Tuan Anh Le (@tuananhle7).

(thread below)

[Sam Stites @[email protected] @SamStites]

Verifying myself: I am stites on https://t.co/nZzYjeFVys. _sc0wVLnR8e3FNFwSrvM-_gnNi_OrwtyH0bm / https://t.co/17lierJ9v1

[Marco @ocramz_yo]

Are you a researcher or practitioner at the intersection of formal methods and numerical/high-performance computing? We'd love to receive your abstract or paper and meet you at the workshop! Extended FHPNC'19 submission deadline: Saturday, May 25.
https://t.co/wHgRXsblP6

[Sam Stites @[email protected] @SamStites]

@harvardnlp @austinvhuang That sounds great! I'll DM you.

[Delip Rao e/σ @deliprao]

New #nlproc blog post: "Design Patterns for Production NLP Systems" https://t.co/m4a4MYgtfT