Andrew Campbell @AndrewC_ML

AI Scientist at Xaira Therapeutics. Previously PhD Student, Dept. Statistics University of Oxford andrew-cr.github.io Joined August 2021

Tweets

16
Followers

612
Following

113
Likes

47

Frank Noe @FrankNoeBerlin

9 months ago

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/10.110…

23 204 720 163K 300

Download Video

Sulin Liu @su_lin_liu

11 months ago

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 57 236 40K 162

Download Image

Jason Yim @json_yim

2 years ago

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/mu… 1/8

2 97 468 73K 243

Download Gif

Andrew Campbell @AndrewC_ML

2 years ago

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

0 21 92 9K 27

Download Gif

Andrew Campbell @AndrewC_ML

4 years ago

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/RLandVI/ 📰 arxiv.org/abs/2110.13549

1 12 36 0 14

Arnaud Doucet @ArnaudDoucet1

4 years ago

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.