Miguel Angel Bautista
@itsbautistam
Followers
2,541
Following
192
Media
42
Statuses
902
I am a research scientist @ Apple ML Research, seeking a grand unification of generative modeling 🇪🇸🇺🇸
San Francisco, CA
Joined April 2014
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
#WeAreSeriesEP12
• 336946 Tweets
LINGLING TSOU OST
• 266813 Tweets
FREENBECKY PILOT TLP REACTION
• 187427 Tweets
PondPhuwin WeAre EP12
• 141778 Tweets
3Days Left Kabir Prakat Diwas
• 109826 Tweets
#BREAKOUT
• 72372 Tweets
#Juneteenth
• 69894 Tweets
Albania
• 65952 Tweets
Croatia
• 46984 Tweets
#スノの衝動
• 38644 Tweets
Stonehenge
• 35261 Tweets
WeAre WinnySatang EP12
• 29581 Tweets
アンジュルム
• 29577 Tweets
あんスタ
• 29448 Tweets
Batshuayi
• 25746 Tweets
スタフォニ
• 21807 Tweets
Just Stop Oil
• 20348 Tweets
GAME TO BUSAN
• 15577 Tweets
#CROALB
• 12523 Tweets
マリノス
• 11263 Tweets
Pistons
• 10419 Tweets
Galveston
• 10161 Tweets
Pinned Tweet
I am looking for strong PhD interns to join Apple MLR early 2024! Topics will be around diffusion generative models broadly speaking and you’ll be in the bay area (SF/Cupertino). Apply here
4
46
199
Excited for this to be out! Introducing GAUDI: a generative model for 3D indoor scenes. We tackle the problem of learning a generative model of 3D scenes parametrized as radiance fields. This has been a great collaboration across multiple teams at
@Apple
.
GAUDI: A Neural Architect for Immersive 3D Scene Generation
abs:
github:
1
28
130
21
114
438
Introducing Generative Scene Networks (GSN), a generative model for learning radiance fields for realistic scenes. With GSN we can sample scenes from the learned prior and move through them with a freely moving camera.
Arxiv:
Scenes sampled from the prior:
Unconstrained Scene Generation with Locally Conditioned Radiance Fields
pdf:
abs:
1
13
82
5
46
230
I find it interesting that the perception of the ML community is that
@Apple
"does not publish" or that it "does not contribute frameworks". Anyways, I'm going to start actively sharing my colleagues works to gently push back on that perception :)
11
10
202
Interested in neural fields and generative models? Check out Diffusion Probabilistic Fields (DPF) ! A diffusion model that can be trained directly on fields in a single stage. DPF outperforms recent approaches based on latent representations of fields. 1/5
1
35
156
We are looking for residents to join MLR at
@Apple
for 2023! We are specially interested in candidates with a strong expertise (MSc/PhD) on physical sciences (eg. physics, climate, bio, chem) and exposure to computational models/ML.
3
40
133
Introducing Manifold Diffusion Fields (MDF), our new work on learning generative models over fields defined on curved geometries. This is joint work with our intern
@Ahmed_AI035
(who hasn’t even started his PhD yet!) and
@jsusskin
at
@Apple
MLR 🧵
Manifold Diffusion Fields
present Manifold Diffusion Fields (MDF), an approach to learn generative models of continuous functions defined over Riemannian manifolds. Leveraging insights from spectral geometry analysis, we define an intrinsic coordinate system on the manifold via
3
47
171
1
28
117
1/n Check out our
@Apple
research paper "On the generalization of learning-based 3D reconstruction" (or 3D43D)
2
22
110
Code is now available at . Check out the interactive exploration notebook where you can move though scenes sampled from the generator!
Unconstrained Scene Generation with Locally Conditioned Radiance Fields
pdf:
abs:
1
13
82
2
19
97
Congrats to my lead authors at Apple on getting two great papers accepted to
#ICLR2024
:
-
@Ahmed_AI035
with Manifold Diffusion Fields ()
-
@xmzhao_
with Dynamic Novel View Synthesis ()
1
12
81
We will be presenting GAUDI at
#NeurIPS2022
! Excited to chat about this and more generative models for 3D in Nola. I’ll share more about code release and checkpoints for GAUDI after ICLR deadline.
Excited for this to be out! Introducing GAUDI: a generative model for 3D indoor scenes. We tackle the problem of learning a generative model of 3D scenes parametrized as radiance fields. This has been a great collaboration across multiple teams at
@Apple
.
21
114
438
4
11
76
Thanks for sharing
@ak92501
! I’ve always been interested in simple yet effective methods that scale. In this recent
@Apple
paper on learning 3D view synthesis we follow that philosophy.
Fast and Explicit Neural View Synthesis
pdf:
abs:
model obtains comparable or even better performance than recent sota approaches using radiance fields, while rendering objects at over 400x speed up
1
12
80
0
12
75
Congratulations
@Ahmed_AI035
well deserved! It was a pleasure to host you at
@Apple
MLR! What a way to start your PhD! 💪💪💪
Best Student Paper Award-:)
Congrats to all the team and thanks to the workshop organizers!
10
22
287
1
6
70
Some intern positions still open at the Machine Learning Research team
@Apple
! If you are a PhD student interested in generative models, neural rendering and language grounded 3D vision please consider applying through the links or DM me.
4
15
65
Two papers by our ML research team at
@Apple
accepted to
@ICCV_2021
! More details/code coming soon. Congratulations to all my amazing colleagues!
@DevriesTerrance
@nitishsr
@jsusskin
@uoguelph_mlrg
@mikeroberts3000
@anuragranj
@jramapuram
3
4
64
We wrote a blogpost summarizing our generative model for scene level radiance fields (GSN) paper to be presented at
@ICCV_2021
. If this post and area of research are interesting to you check out FT/intern opportunities on our team
0
15
64
Official code release for our Generative Scene Networks
@ICCV_2021
paper! We provide code, training data and pre-trained models for you to try out. Check out the interactive exploration notebook, you can move through scenes sampled from the generator!
1
8
55
Here’s a way to speed up training even more. Optimize the parameters of the neural network jointly on a training set of multiple samples (eg. multiple scenes for NeRF, multiple objects for SDFs, etc). Let the hash tables be specific for each sample. Boom! Now you are amortizing!
Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
paper:
project page:
github:
21
359
2K
1
6
53
I’ll be at the
@Apple
booth at
@NeurIPSConf
today from 1-3pm. Come say hi and lets chat about all things Apple MLR!
#NeurIPS23
0
1
46
Attending
#NeurIPS2022
after a few year hiatus! I will be giving an expo talk about “Generative Understanding of 3D Scenes”
@Apple
Mon at 3pm, and presenting the poster for GAUDI () on Thu at 9:30am. Will also be at the booth on Tue from 3-5pm. Come say hi!
1
7
45
Happy that this cool work lead by
@pengsheng_guo
has been accepted at
#wacv2022
. Updated preprint with results on DTU and project page coming soon!
Fast and Explicit Neural View Synthesis
pdf:
abs:
model obtains comparable or even better performance than recent sota approaches using radiance fields, while rendering objects at over 400x speed up
1
12
80
0
6
45
Happy to announce that our paper “On the generalization of learning-based 3D reconstruction” was accepted to
@wacv2021
!!! I would like to highlight that we got very insightful reviews and comments that will be included in the camera-ready version.
1/n Check out our
@Apple
research paper "On the generalization of learning-based 3D reconstruction" (or 3D43D)
2
22
110
3
8
42
Using
@code
to ssh into compute, commit code and submit experiments from 38k feet has to be one of the greatest achievements of human history.
1
2
42
If you are attending
@NeurIPSConf
check out all the papers we are presenting! Also swing by our booth if you want to hear more about internships and FTE opportunities! I will be there on Weds 11am-1pm to answer all your questions :)
0
6
42
Interested in generative models and neural fields/INRs? Come by our poster where we present “Diffusion Probabilistic Fields” an approach for learning distributions over fields that can be trained in a single stage. Tuesday morning poster session!
#ICLR2023
0
14
40
If you are at
#ICML2023
please check out the following Apple papers . I won’t make it in person this year but please reach out to any of my fantastic colleagues that are around!
0
11
39
Starting the long trip to Kigali! Excited for
@iclr_conf
and catching up colleagues! If you want to chat about internship/FT opportunities at
@Apple
let me know!
3
2
37
Planning to attend
@CVPR
? Check out the workshop sessions on Sunday, I will be talking about generative modeling for fields and manifolds at the
@_LXAI
workshop!
2
9
37
We then learn a generative model over latent representations using a diffusion model. This allows us to tackle both unconditional and conditional inference tasks. Like generating 3D scenes and camera trajectories from text prompts (additional results on ):
1
4
32
More cool stuff on 3D scene generation! I’ve been waiting for someone to look into 3D consistency for inpainting-style objectives. IMO, having the text prompt being spatially distributed is the next layer of complexity.
SceneScape: Text-Driven Consistent Scene Generation
abs:
project page:
text-driven perpetual view generation -- synthesizing long videos of arbitrary scenes solely from an input text describing the scene and camera poses
8
98
353
0
2
31
Excited to be part of the mentoring panel for
@_LXAI
at
@ICCV_2021
, come by and chat with me to learn about the ML/CV opportunities at
@Apple
.
0
5
30
I finally have some time to engage in the discussion of our conformer generation paper sparkled by
@tkipf
's tweets. There's 3 things I'd like to clarify:
1) Symmetries are really important for any learning algorithm! Without structure learning gets harder!
Since this tweet sparked quite a bit of lively discussion, I'd like to add a bit more nuance:
1) I think we absolutely should study symmetry in the context of (scalable) ML; this particular result only reinforces this IMO. Understanding trade-offs w.r.t. symmetry group "size",
2
11
107
3
2
27
Interesting times ahead, as bigger 3D datasets become available I predict the community will shift to “3D gen models from the ground up” as opposed to “distilling 2D models into 3D”.
Objaverse: A Universe of Annotated 3D Objects
800K+ 3D models with descriptive captions
arxiv:
website:
2
18
164
1
2
29
Generative models for 3D are 🔥. This Friday at
@ml_collective
I will be talking about GAUDI, our approach to learn generative models of unconstrained 3D scenes. Check if you are interested in attending. Really looking forward to a great discussion!
Excited for this to be out! Introducing GAUDI: a generative model for 3D indoor scenes. We tackle the problem of learning a generative model of 3D scenes parametrized as radiance fields. This has been a great collaboration across multiple teams at
@Apple
.
21
114
438
0
3
29
This is the best explanation of the Laplace operator for geometry processing that I have seen so far.
@JustinMSolomon
0
4
27
Generative Scene Networks was accepted at
@ICCV_2021
! Congratulations
@DevriesTerrance
and collaborators
@nitishsr
@jsusskin
@uoguelph_mlrg
! Excited for what’s coming next :)
Introducing Generative Scene Networks (GSN), a generative model for learning radiance fields for realistic scenes. With GSN we can sample scenes from the learned prior and move through them with a freely moving camera.
Arxiv:
Scenes sampled from the prior:
5
46
230
2
4
28
NeRF papers have become quite frequent nowadays (and I predict it will become even more so). Out of all the papers that have come out recently, to me this is the one that points to the most interest direction so far.
Zero-Shot Text-Guided Object Generation with Dream Fields
abs:
project page:
combine neural rendering with multi-modal image and text representations to synthesize diverse 3D objects solely from natural language descriptions
5
64
318
1
0
27
Making progress in breaking stereotypes around Apple and ML research ☺️ really looking forward for people to try MLX!
This may be Apple's biggest move on open-source AI so far: MLX, a PyTorch-style NN framework optimized for Apple Silicon, e.g. laptops with M-series chips.
The release did an excellent job on designing an API familiar to the deep learning audience, and showing minimalistic
59
586
4K
0
4
26
More work from MLR at Apple! Check out this fantastic paper by
@AggieInCA
and team. How can we effectively evaluate SSL models without requiring labels? :)
ICLR24 Spotlight: To train general-purpose SSL models, it's important to measure the quality of representations during training. But how can we do this w/o downstream labels?
We propose a new label-free metric to eval SSL models, called Linear Discrimination Analysis Rank(LiDAR)
6
61
267
0
0
25
What would happen if we pretend all samples are neural fields in diffusion generative models? I’ll be talking about work that we have been doing on this direction at
#Apple
MLR on Sunday 1:30pm
@_LXAI
workshop!
#CVPR2023
#neuralfields
0
8
24
Congratulations
@Ahmed_AI035
this is so exciting! It was a pleasure to host you for your first internship at
@Apple
even before you started your Phd!!! Cant wait to see all the cool stuff you will do!
0
2
23
The great
@YuyangW95
and I will be presenting this tomorrow at
@genbio_workshop
in the morning poster session! Come to learn about why a non SE(3) equivariant model gets state of the art performance in conformer generation!
1/n New preprint alert! Introducing Generative Molecular Conformer Fields (MCF) a generative model for molecular conformer generation that obtains state-of-the-art results without using any domain specific inductive biases!
4
33
247
0
4
20
Happy to get an outstanding reviewer award from
@ICCV_2021
, I will be donating my free registration to a researcher from an under-represented group that wishes to attend. Will share details soon.
2
0
20
MDF is an oral at the Diffusion Models workshop tomorrow at
@NeurIPSConf
! Catch
@Ahmed_AI035
’s talk (via zoom because well…visas) and also
@YuyangW95
and I will be around in the poster session! Come say hi and lets chat about practical diffusion models on manifolds!
Introducing Manifold Diffusion Fields (MDF), our new work on learning generative models over fields defined on curved geometries. This is joint work with our intern
@Ahmed_AI035
(who hasn’t even started his PhD yet!) and
@jsusskin
at
@Apple
MLR 🧵
1
28
117
0
5
19
Excited to catch with folks at
@CVPR
and chat about generative models for functions (including our recent MDF work)!
1
1
18
Cool stuff! Although I wonder how would the training speed/accuracy compare if you replace the 27 SH parameters per voxel vertex with a single linear layer of the same dimension. IMO that’s the right baseline to compare with. Are SH params easier to learn?
Plenoxels: Radiance Fields without Neural Networks
abs:
project page:
propose a view-dependent sparse voxel model, Plenoxel, that can optimize to the same fidelity as NeRFs without any neural networks
11
166
902
0
2
19
I will visiting
@CMU_Robotics
next week to talk about generative models of fields in the VASC seminar . Excited to chat with the awesome faculty and students! If you are around and want to chat please ping me :). Thanks for the invite
@FerranDeLaTorre
!
2
4
18
Diffusion models tend to be notoriously slow during inference. Check out this amazing piece of work by great colleagues at
@Apple
looking at the problem of distilling diffusion models for single-step sampling. Congrats
@D_Berthelot_ML
and team!
New paper TRACT - Faster diffusion model sampling
- Single-step diffusion SotA for CIFAR10 and ImageNet64 with L2 loss without architecture changes
- Up to 2.4x FID improvement
9
78
245
0
2
18
Very exciting times ahead for the interplay of powerful generative models and 3D data! Shoutout to everyone involved in this effort
@pengsheng_guo
@samiraabnar
@Waltertalbott
@toshev
@ZhuoyuanChen
@laurent_dinh
@zhaisf
@hanlingoh
@jsusskin
.
1
0
18
Data scale + transformers + autoregressive objective is the gift that keeps on giving! Now also in vision :) What an incredible work led by
@alaaelnouby
and team from Apple MLR. Check out the repo with checkpoints and bindings to MLX/Jax!
Excited to share AIM 🎯 - a set of large-scale vision models pre-trained solely using an autoregressive objective. We share the code & checkpoints of models up to 7B params, pre-trained for 1.2T patches (5B images) achieving 84% on ImageNet with a frozen trunk.
(1/n) 🧵
8
56
215
0
1
17
Publication link also available at:
Project page with some additional visualizations now online at (source code will be available in the next few weeks)
Introducing Generative Scene Networks (GSN), a generative model for learning radiance fields for realistic scenes. With GSN we can sample scenes from the learned prior and move through them with a freely moving camera.
Arxiv:
Scenes sampled from the prior:
5
46
230
0
5
16
I’ve had several situations where a paper wasn’t ready to submit by conf. deadline date. This usually causes added stress (specially to phd students/interns), being able to submit when *work is ready* is going to be great for the community.
Today,
@RaiaHadsell
,
@kchonyc
and I are happy to announce the creation of a new journal: Transaction on Machine Learning Research (TMLR)
Learn more in our post:
54
691
3K
0
0
17
Check out our new work on learning generative models of functions on graphs for molecular conformer generation, led by the amazing
@YuyangW95
! A few things that I found really exciting about this work:
1/n New preprint alert! Introducing Generative Molecular Conformer Fields (MCF) a generative model for molecular conformer generation that obtains state-of-the-art results without using any domain specific inductive biases!
4
33
247
1
3
16
Always fun to go back to the origins! More so if its to talk about generative models! Thanks for hosting me
@SergioEscalera_
!
0
1
14
Check out this new work lead by
@bogdan_mazoure
and
@waltertalbott
using diffusion models to capture the distribution of the value function! IMO this is a very interesting way to think about how do we leverage large probabilistic models in RL settings.
Latest preprint from
@Apple
MLR - we use conditional diffusion models + Perceiver I/O to learn the policy's state visitation and the value function on hard offline robotic tasks . Work with
@waltertalbott
,
@itsbautistam
, Devon, Alex and
@jsusskin
.
0
15
103
0
1
13
Want to take generative modeling of the 3D world to the next level? Check out and come help us take it to the next level.
Only by going through this path will we be able to point the camera back at simple internet images and not just see the "Egyptian cat" class, but condition on the image to instantiate full generative 3D reconstructions of worlds consistent with that observation.
17
20
510
0
1
14
We just released code for Equivariant Neural Rendering! Give it a shot!
1
3
14
We decompose the generative model in two stages, we first learn latent representations that encode the 3D radiance fields and corresponding camera poses for thousands of trajectories. This task is formulated as optimization problem over latents and network parameters.
1
2
14
The fundamental problem of unsupervised correspondence learning is oftentimes formulated using this framework. Things become trickier when f^{-1} is not defined and needs to be approximated, a couple of cool papers dealing with it:
A powerful idea in math (that nobody teaches you directly…):
If you don't know how to map between two "things," you can often map each of them to the same "canonical thing."
Then you can just go from the 1st thing to the canonical thing, and back to the 2nd thing. [1/n]
18
141
757
1
1
13
We will be presenting GSN at
#ICCV2021
, session 11A (today at 3pm PDT). Join
@DevriesTerrance
and myself if you want to chat about generative models for 3D scenes and what the future holds for these types of models.
#apple
#generativemodels
#computervision
Introducing Generative Scene Networks (GSN), a generative model for learning radiance fields for realistic scenes. With GSN we can sample scenes from the learned prior and move through them with a freely moving camera.
Arxiv:
Scenes sampled from the prior:
5
46
230
0
3
13
How about an open source framework for ML development on Apple silicon? :)
Just in time for the holidays, we are releasing some new software today from Apple machine learning research.
MLX is an efficient machine learning framework specifically designed for Apple silicon (i.e. your laptop!)
Code:
Docs:
100
718
4K
0
1
12
Catch me and
@YuyangW95
at
@NeurIPSConf
next week! Happy to chat about anything from generative models, geometric deep learning, applications in scientific domains, as well as in vision and 3D. Also happy to chat about internship and FTE opportunities! Come join Apple MLR!
I’ll be attending
#NeurIPS2023
next week. Please feel free to reach out if you want to chat about generative models, AI4Science, geometric deep learning, and more!
2
0
18
0
1
12
Run AIM models locally on your M-powered MacBook! :)
New autoregressive image models (AIM) from Apple run out of the box on your laptop with MLX!
Code and models:
Example:
2
42
310
0
0
11
Excited to participate in the
@_LXAI
mentorship hour at
#NeurIPS2021
alongside incredible mentors. Join and say hi!
Let's all welcome the Mentor Representatives from the
@_LXAI
Sponsors for the workshop this year co-locating with
#NeurIPS2021
!! Today at 4:30 PM PST during the mentoring hour! Join here 👉
#LXAI
#MentoringHour
#NeurIPS2021
0
2
8
0
3
12
In GAUDI we don’t rely on a pre-trained text-to-image model and design a generative model for 3D indoor scenes from the ground up . It’s only a matter of time until similar models can be trained on internet scale 3D datasets.
0
0
10
Pixels are discrete points in a continuous function/field. The true universal interface is the wave function.
1
0
11
This is an interesting time+light extension of implicit representations used neural rendering!
X-Fields: Implicit Neural View-, Light- and Time-Image Interpolation
pdf:
demo:
project page:
4
209
961
0
1
10
The DFN-2B dataset used to train AIM is also available on HF (by the great
@Vaishaal
)
0
2
11
Learning latents for radiance fields and camera poses is critical. As opposed to single objects (which can always be rendered from cameras on the sphere), the set of valid camera poses depends on each scene. Therefore, we need to encode which camera poses are valid for each scene
1
2
10
Text-to-3D from amazing colleagues at
@Apple
!! Congratulations
@pengsheng_guo
🔥🔥🔥
StableDreamer: Taming Noisy Score Distillation Sampling for Text-to-3D
paper page:
In the realm of text-to-3D generation, utilizing 2D diffusion models through score distillation sampling (SDS) frequently leads to issues such as blurred appearances and
0
27
90
0
1
10
Check out the fantastic video explanation by
@artsiom_s
of a couple of papers on self-supervised learning that we worked together on a few years ago before CPC was cool. Those were good times
@artsiom_s
!
My new video on self-supervised representation learning (also easy to understand for beginners). I explain CliqueCNN which builds compact cliques for classification as a pretext task and I discuss other self-supervised learning approaches.
@itsbautistam
3
19
95
0
3
10
I love seeing more papers on scene generative models. I believe that to make substantial progress in RL we need very powerful world models. We are just seeing the beginning of what these models are capable of!
Pathdreamer: A World Model for Indoor Navigation,
@kohjingyu
et al. ()
A neural network hallucinating indoor scenes from a single given observation in a previously unseen building.
Possibilities are endless:
5
72
347
0
0
10
0
0
9
Check out this opening if you are interested in foundation models and embodied AI!
@alexttoshev
’s team is going cool stuff!
I wanted to advertise that we have opportunities in my team at Apple MLR in scalable/distributed ML for multimodal foundational models, embodied AI, planning and reasoning. More info below but feel free to send me a note.
1
6
21
0
1
10
"The company is publishing regularly, it's doing academic sponsorships, it has fellowships, it sponsors labs, it goes to AI/ML conferences. It recently relaunched a machine learning blog where it shares some of its research"
0
1
10
@karpathy
How about "These violent delights have violent ends - Geoff Hinton". I bursted into laughter :D
0
1
9
Neat idea! I’ve been waiting for lightfields to strike back in 3D and compete with radiance fields, I think we are going to see more work in this direction.
Ray Conditioning: Trading Photo-consistency for Photo-realism in Multi-view Image Generation
abs:
project page:
2
51
211
1
0
9
Nice! I feel fast geodesic distance extraction could be useful as GT for learning-based approaches for correspondence modeling.
Point cloud code releases in
#geometrycentral
C++, with Python bindings on pip!
Fast computation of geodesic distance, nearest-geodesic-neighbor interpolation, parallel transport, and the logarithmic map.
(C++)
(Python)
(1/4)
8
118
530
0
2
9
In order to model radiance fields for unconstrained scenes we decompose them into many small locally conditioned radiance fields which are conditioned on a latent spatial representation of a scene W.
1
0
9
The prior learned by GSN can be used for view synthesis: by inverting GSNs generator we can complete unobserved parts of a scene (T) conditioned on a sparse set of views (S).
1
0
9
On Gemini day you can also learn how to scale your EMA! From great colleagues at Apple MLR
Excited to be at NeurIPS in New Orleans next week and hope to see many of you there! On Wednesday, my co-authors (
@jramapuram
,
@PierreAblin
, Tatiana Likhomanenko, Xavier Suau, Russ Webb) and I will present our🥳spotlight-awarded🎉work “How to Scale Your EMA”.
1
14
49
0
0
8
Thanks for having me
@ml_collective
and
@savvyRL
, I hope folks enjoyed as much as I did. All questions and comments were really insightful!
2
1
9
On my way the Silicon Valley tomorrow! Really exciting times ahead!!!
1
0
9
Cool work using text-to-image models to generate 3D scenes. The next nut to crack here is to be able to have spatially aware text prompts.
Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models
abs:
project page:
4
184
813
0
0
9
This is what we are doing to loss landscapes when we use inductive biases in our neural nets😅
Awesome real time geomorphology. This Augmented-Reality sandbox is one of the coolest things I've seen
324
12K
40K
0
2
9
Sharing this because I believe this work deserves more attention! I really enjoyed the clean and elegant formulation of the problem from the lens of interpolating densities.
Our paper on a general framework for efficiently building continuous normalizing flows between any distributions has been accepted
@ICLR
2023! Here are some flow-flowers. of interest:
@DaniloJRezende
@KyleCranmer
@FrankNoeBerlin
@ylecun
@wgrathwohl
Paper:
5
39
281
1
0
9
