@AndrewC_ML profile picture
Andrew Campbell @AndrewC_ML

Research Scientist, Google DeepMind. Previous: @Xaira_Thera, PhD @oxcsml

Joined August 2021
  • Tweets 19
  • Following 141
  • Followers 775
6 Photos and videos
I will be attending @iclr_conf this week, please reach out if you'd like to chat about generative models or AI for science!
3
41
2,823
Very excited to share our preprint: Self-Speculative Masked Diffusions We speed up sampling of masked diffusion models by ~2x by using speculative sampling and a hybrid non-causal / causal transformer arxiv.org/abs/2510.03929 w/ @ValentinDeBort1 @thjashin @ArnaudDoucet1
1
40
184
11,075
Andrew Campbell retweeted
Frank Noe@FrankNoeBerlin
6 Dec 2024
Super excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equilibrium ensembles with generative deep learning from @MSFTResearch AI for Science. #ML #AI #NeuralNetworks #Biology #AI4Science biorxiv.org/content/10.1101/…
0:14
23
202
712
165,405
Andrew Campbell retweeted
Sulin Liu
@su_lin_liu
16 Oct 2024
Discrete generative models use denoisers for generation, but they can slip up. What if generation *isn’t only* about denoising?🤔 Introducing DDPD: Discrete Diffusion with Planned Denoising🤗🧵(1/11) w/ @junonam_ @AndrewC_ML @HannesStaerk @xuyilun2 Tommi Jaakkola @RGBLabMIT
6
55
234
40,395
Andrew Campbell retweeted
Jason Yim@json_yim
25 Feb 2024
Combining discrete and continuous data is an important capability for generative models. To address this for protein design, we introduce Multiflow, a generative model for structure and sequence generation. Preprint: arxiv.org/abs/2402.04997 Code: github.com/jasonkyuyim/multi… 1/8
2
99
471
74,812
New paper: how to do flow matching on discrete data. Flows give a simple generative framework and better performance than discrete diffusion models. Discrete flows are easily combined with continuous flow matching for multimodal models. arxiv.org/abs/2402.04997 A thread 1/7
4
48
294
32,862
more replies
We are giving a talk about the work this Tuesday 11am EST/4pm GMT @valence_ai portal.valencelabs.com/event… Code for the pure discrete model: github.com/andrew-cr/discret… Code for protein co-design experiments: github.com/jasonkyuyim/multi… 6/7
1
2
8
1,354
Big thanks to amazing co-lead @json_yim and our advisors @BarzilayRegina , @tom_rainforth , Tommi Jaakkola. 7/7
1
5
1,100
How can we apply diffusion models to data with varying dimensionality? We use jump diffusions to simultaneously generate the size and state values for varying size data e.g. molecules arxiv.org/abs/2305.16261 w/ @willarvey @wh1lo @ValentinDeBort1 @tom_rainforth @ArnaudDoucet1
22
92
8,779
📰A Continuous Time Framework for Discrete Denoising Models Operating in continuous time gives us higher performance generative samplers and error bounds on discrete spaces. arxiv.org/abs/2205.14987 w/ @JoeJBenton @ValentinDeBort1 @tom_rainforth @GeorgeDeligian9 @ArnaudDoucet1
2
19
51
Code and models available at github.com/andrew-cr/tauLDR

GitHub - andrew-cr/tauLDR: Code for the paper https://arxiv.org/abs/2205.14987v2

Code for the paper https://arxiv.org/abs/2205.14987v2 - andrew-cr/tauLDR

github.com
1
1
3
I have written a blog post describing our use of Reinforcement Learning to create an online objective for sequential Variational Inference 🌐 andrew-cr.github.io/posts/RL… 📰 arxiv.org/abs/2110.13549
1
13
37
Andrew Campbell retweeted
Arnaud Doucet@ArnaudDoucet1
27 Oct 2021
Online Variational Filtering and Parameter Learning arxiv.org/abs/2110.13549 with @AndrewC_ML @YuyangShi0 & @tom_rainforth accepted as Oral #NeurIPS2021. We exploit forward Bellman recursions for the ELBO & its gradients in state-space models and RL ideas.

Online Variational Filtering and Parameter Learning

We present a variational method for online state estimation and parameter learning in state-space models (SSMs), a ubiquitous class of latent variable models for sequential data. As per standard...

arxiv.org
2
15
78
Load more