Hannes Stärk
@HannesStaerk
Followers
8,645
Following
331
Media
321
Statuses
1,945
@MIT PhD student • ML for molecular biology and generative models
Cambridge, MA
Joined June 2019
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
namjoon
• 436087 Tweets
Kabosu
• 97336 Tweets
新時代の扉
• 87087 Tweets
#뜨거운_5월의불꽃_도은호
• 74655 Tweets
FB MADE YOU BLUSH
• 70740 Tweets
#ハマダ歌謡祭
• 48677 Tweets
メラルバ
• 33368 Tweets
ビッグビッグラン
• 29616 Tweets
#原神予告番組
• 28452 Tweets
#それスノ
• 22344 Tweets
新人バニーガールのニケ
• 13295 Tweets
#薬屋のひとりごとSimeji
• 11618 Tweets
Pinned Tweet
New paper :)
"Dirichlet Flow Matching with Applications to DNA Sequence Design"
TLDR
1. try linear flow matching on simplex
2. oh problem: explain
3. fix it with Dirichlet flow matching
4. Try on DNA, nice, better than language model
1/4
9
49
332
Oke, the AlphaFlow paper is awesome: AlphaFold Meets Flow Matching for Generating Protein Ensembles
Just watch how AlphaFlow's ensemble reproduces details of MD.
Weights + code
We have it in the reading group on Mon 11am EST!
1/2
15
152
760
Intested in KAN: Kolmogorov-Arnold Networks?
Fair, I guess everyone is 🙃
Good that
@ZimingLiu11
will join us on Mon May 13th 11am EDT, to discuss it in our Zoom reading group.
Sign up for reminders or join our slack here:
7
80
566
I am starting my PhD
@MIT
this summer! ☺️
Me = beyond happy :D
I can't wait to work there 👇 in the groups of Profs
@BarzilayRegina
and Jaakkola!
A thousand thanks to my collaborators and friends - I'm looking forward to enjoying even more research and time together! Let's go🤗
36
8
545
Our paper "EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction" was accepted to
@icmlconf
!
My first ICML paper🤗
With
@octavianEganea
(joint first)
@lucky_pattanaik
@BarzilayRegina
and Tommi Jaakkola!
8
80
441
This Tuesday Jinwoo Kim presents his recent "Pure Transformers are Powerful Graph Learners"!
Just tokenize the edges as well and throw everything in a "pure" transformer.
Join the discussion on Zoom at 11am EST / 3pm UTC tomorrow:
8
82
443
How to get a paper accepted at ICLR?
Easy: be male, don't live in Asia, submit to RL, have many coauthors, work at FAIR/Google or similar, and write "Theorem" in your paper.
In more seriousness, this paper compiles some interesting ICLR statistics:
1/9👇
6
82
419
New Video with Professor
@nimatabari
explaining his Lie-Conv Neural Nets!
The amazing added bonuses to automatic symmetry discovery are exciting connections to physics!
Paper Link:
Join the reading group:
4
94
388
Reading group Monday:
The better perspective on flow matching? 🙃
@msalbergo
will present everything about their clean stochastic interpolants framework:
Join on Zoom at 11am EDT / 3pm UTC / 5pm CEST:
1
65
378
New paper!
DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
1. Diffusion over molecule position, rotation, and torsion angles
2. From 23% accuracy to 38% on a time-split 🤗
3. Confidence estimates with high selective accuracy
1/3
3
61
356
Our new paper is out!🧬
EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction
Fast 3D structure predictions in which molecules bind to proteins!
With the lovely team
@octavianEganea
@lucky_pattanaik
@BarzilayRegina
Tommi Jaakkola 🤗
1/2
11
64
349
Coming Monday
@ZimingLiu11
will present his "KAN: Kolmogorov-Arnold Networks" :)
Clearly this one is popular, but come hear more about what the author thinks to be the most relevant KAN uses and what they can do. On Zoom 11am EDT:
3
67
356
Tomorrow in the reading group:
@geisler_si
will present his "Transformers Meet Directed Graphs" 👌
Excellent for understanding Graph Transofmers better (and GT for DAGs :3)
Join on zoom at 11am EDT / 3pm UTC:
0
65
347
Diffusion models are dead - long live joint conditional flow matching! 🙃
Tomorrow
@AlexanderTong7
presents his "Improving and generalizing flow-based generative models with minibatch optimal transport"
On Zoom 11am EDT / 3pm UTC:
4
56
343
New paper!🤗
"Harmonic Self-Conditioned Flow Matching for Multi-Ligand Docking and Binding Site Design"
Generating pockets to bind small molecules has applications like designing antidotes that sequester toxins or as a first step toward Enzyme design
1/11
2
64
329
This Tuesday Professor
@Nimatabari
presents his paper "Automatic Symmetry Discovery with Lie Algebra
CNN"!
Join tomorrow via Zoom at 3pm UTC or sign up for a reminder here:
With
@RobinSFWalters
@YanchenLiu13
@dashunwang
@yuqirose
2
63
284
This Tuesday in the
#Graph
ML reading group
@matej_zecevic
will present his paper "Relating Graph Neural Networks to Structural Causal Models"
None less than
@yudapearl
said that this paper deserves attention!
So join on Zoom!
1/2
4
52
257
In next Tuesday's Graph ML reading group session, Professor
@PanLi90769257
presents his paper "Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning"!
How to link prediction!
Join on Zoom at 11am EST / 5pm CEST:
1
35
248
Reading group session with
@k_neklyudov
again!
"A Computational Framework for Solving Wasserstein Lagrangian Flows":
Join on Zoom on Monday at 11am EST / 4pm UTC / 5pm CET:
1
32
243
"Bayesian Flow Networks" has 47 pages of main text with over 200 equations 🙃
Maybe this summary is a simpler resource if you want to understand the new generative modeling paradigm: :)
2
42
245
In tomorrow's reading group session, we discuss "On the Ability of Graph Neural Networks to Model Interactions Between Vertices" with
@noamrazin
!
Join us on zoom at 11am EST / 5pm CET on Monday via this link:
1
39
241
Monday in the reading group!
"Bayesian Flow Networks" with Alex Graves from
@nnaisense
:
I really hope we can avoid any Alice and Bob analogies 🙃
Join on Zoom at 11am EST / 5pm CET / 4pm UTC:
0
23
239
"A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems"
Tomorrow in the reading group with
@chaitjo
@SimMat20
and
@ADuvalinho
🤗
Join us at 11am EDT / 5pm CEST on zoom:
4
41
230
This Tuesday in the GraphML reading group we discuss GNN theory based on Prof. Stefanie Jegelka's new survey "Theory of Graph Neural Networks: Representation and Learning" with
@dereklim_lzh
!
Join us tomorrow!🤗
At 3pm UTC/11am EST
4
34
219
Tomorrow (Monday) Zian Li will present his paper "Is Distance Matrix Enough for Geometric Deep Learning?" !
Some interesting discussions can be had about parts of that question.
Join us on zoom at 11am EDT / 3pm UTC / 5pm CEST:
1
39
214
A bit late but our "3D Infomax improves GNNs for Molecular Property Prediction" was also accepted to
@icmlconf
🤗
Second ICML paper☺️
Helps especially for quantum properties!
With
@dom_beaini
@GabriCorso
@TOSSOUPrudencio
@sacdallago
@guennemann
Pietro Lió
7
36
214
Tomorrow we cover a very hot topic!
@jo_brandstetter
presents his
#ICLR2022
spotlight paper "Message Passing Neural PDE Solvers"!
Join us this Tuesday on Zoom at 3pm UTC:
Co-authors:
@danielewworrall
@wellingmax
2
34
204
Diffusion models strike back! Tomorrow
@xuyilun2
presents his PFGM++: Unlocking the Potential of Physics-Inspired Generative Models
Join us on zoom at 11am EDT / 3pm UTC:
0
37
204
Today we discuss "Unsupervised Learning of Group Invariant and Equivariant Representations" in the reading group with the authors
@jrobin_winter
and Marco Bertolini.
Join us on Zoom in 1h 20min at 11am EDT / 3pm UTC!
3
37
192
Tomorrow (Monday)
@ZimingLiu11
will present his paper "GenPhys: From Physical Processes to Generative Models"!
Diffusion models, PFGM and ?!
On zoom 11am EDT / 5pm CEST:
Co-authors:
@xuyilun2
, Di Luo, Tommi Jaakkola,
@tegmark
1
54
193
Tomorrow (Monday) we discuss "Fine-Tuning GNNs via Graph Topology induced Optimal Transport" in the reading group!
Optimal Transport = nice.
Zoom link for 11am EST / 4pm UTC / 5pm CET:
3
34
193
Monday reading group session!
@leonklein26
presents his Equivariant Flow Matching paper!
Simple and effective :)
Join us at 11am EDT / 3pm UTC on Zoom:
1
20
188
Alright 2023 let's go - tomorrow we have our first paper presentation with "Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions" !
Join us on zoom at 11am EST / 5pm CET on Monday via this link:
2
35
187
Monday in the reading group - flow matching? neigh: "Action Matching: Learning Stochastic Dynamics from Samples" with
@k_neklyudov
and
@AliMakhzani
! One of the most interesting ICML papers. 👌
On Zoom at 11am EDT / 3pm UTC:
0
21
185
Okay, okay, here it is:
The highly demanded recording of our reading group session about "AlphaFold Meets Flow Matching for Generating Protein Ensembles" with Bowen Jing:
Many more of these awesome Alphaflow reproduces MD gifs :)
5
27
182
This paper on generalization in diffusion models is very nice
@ZKadkhodaie
gave a talk about it, and the whole audience, including me, loved it. So tomorrow we'll discuss it with her in the reading group!
On Zoom 11am ET:
8
29
180
Our new paper is out!⚛️
3D Infomax improves GNNs for Molecular Property Prediction:
With
@GabriCorso
@sacdallago
@guennemann
@pl219_Cambridge
and
@dom_beaini
@TOSSOUPrudencio
from
@valence_ai
🤗
Use 3D to improve for molecules with unknown 3D! 👇
1/4
4
23
175
Excited for this Tuesday when
@vijaypradwi
presents his new "GNNs with Learnable Structural and Positional Representations" in the graphML reading group 🤗
A neat technique to simply improve any GNN?
Sign up and join on Zoom!
1/2
2
38
175
Soo, this is a big one :)
On Nov 20 we will have RosettaFold all-atom in the reading group with
@r_krishna3
!
Quite amazing protein design capabilities. But that is my naive evaluation - join us and let's discuss and hear your insights! Sign up here:
1
35
176
Super happy that MIT News covered our
@icmlconf
paper "EquiBind" today! 🤗
Thanks to the lovely team
@octavianEganea
@lucky_pattanaik
@BarzilayRegina
Tommi Jaakkola and all others who contributed to this project!
1/2
6
31
170
This Tuesday,
@emaros96
will discuss his paper "On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features" () in the LoGaG reading group!
Join the discussion on Zoom at 4pm GMT:
1/2
2
33
161
New GNNs? On Tuesday in the
#GraphML
reading group James Rowbottom and
@b_p_chamberlain
present their "GRAND: Graph Neural Diffusion" + their
#NeurIPS2021
paper "Beltrami Flow and Neural Diffusion on Graphs" out of
@mmbronstein
's group
@Twitter
!
Zoom:
1/2
1
35
156
Monday reading group session: SE(3)-Stochastic Flow Matching for Protein Backbone Generation
Presented by Tara Akhound-Sadegh!
Join us on zoom at 11am ET / 5pm CET / 4pm UTC:
0
24
155
Beyond excited to have professor
@ZhongingAlong
presenting her work and vision at
#MoML
!
P.S.: She is looking for PhD students for her freshly minted lab at Princeton University - reach out!
1
18
153
We have a new little review on GNNs in life sciences in "Nature Reviews Methods Primers"!
We try to keep it focused and provide some interesting considerations instead of just listing papers. I hope that makes it useful - let me know what you think!
1/2
3
31
155
This Monday,
@julberner
presents his paper "An optimal control perspective on diffusion-based generative modeling" in our reading group!
Join us on zoom at 11am EST / 5pm CET tomorrow:
Co-authors:
@lorenz_richter
@karen_ullrich
2
24
152
Next Tuesday, I am giving a talk at the
@Cambridge_CL
AI Seminar titled "3D Pre-training improves GNNs for Molecular Property Prediction" ⚛️🤗
Join the Zoom call on Oct 12th at 2:15pm CEST / 8:15 EST here:
1/2
8
29
152
Tomorrow in the reading group, we have
@chaitjo
presenting his paper "On the Expressive Power of Geometric Graph Neural Networks"
Pretty interesting if you care about point clouds/molecules.
Join on Zoom at 11am EST / 5pm CET:
3
26
151
This Monday, we discuss "Ewald-based Long-Range Message Passing for Molecular Graphs" with author Arthur Kosmala!
Fascinating molecular dynamics ideas from 1921 making their way into ML!
On Zoom at 11am EDT / 5pm CEST:
2
26
145
Help 🫠
Scenario: you train a model and run into NaNs after some epochs.
My primitive debugging is putting NaN checks and prints everywhere. Seemingly, for every project it is a different reason.
If you run into NaNs, what are the most common causes or causes of overflows?
50
12
144
Tomorrow in the reading group, we discuss GFlowNets and "Biological Sequence Design with GFlowNets." 🤗👌
GFlowNets:
Bio Sequence Design with GFlowNets:
Zoom link etc. for Monday 11am ET / 5pm CET:
4
22
143
This Monday in the reading group, we have the two beautiful👌Clifford Algebra Net papers presented by the authors
@jo_brandstetter
@djjruhe
@rejuvyesh
!
Join us on Zoom at 11am EST / 5pm CET 🤗
0
28
139
Monday 11am Reading group: RosettaFold all-atom!
Let us discuss with
@r_krishna3
what protein design niceties we can achieve with this. And also the AlphaFold all-atom "glimpse" :)
Join on Zoom at 11am ET / 4pm UTC / 5pm CET:
1
22
139
Tomorrow at 11am EST we discuss "On Recoverability of Graph Neural Network Representations" with Maxim Fishman!
Join if you are interested in unsupervised learning on graphs or GNNs in general!
Zoom for Tue 11am EST / 3pm UTC:
1/2
1
26
138
Tomorrow in the reading group we will have Bingxin Zhou and Kai Yi presenting their "Graph Denoising Diffusion for Inverse Protein Folding"
Join us at 11am EDT on zoom:
1
20
134
Coming Tuesday
@haiyangyu14
will present his paper "On Explainability of Graph Neural Networks via Subgraph Explorations"
from
@ShuiwangJi
's lab!
Such lovely explanation examples! 👌🤗
Join the Zoom reading group at 3pm UTC:
1/2
4
28
129
We wrote a little review on diffusion models for protein structure generation and docking.
Again, we tried to not just make it a list of papers, and instead to give some interesting framings and takes.
You judge if it worked :)
Our review on diffusion models for protein structures and docking is out
@HannesStaerk
@GabriCorso
Bowen Jing
@BarzilayRegina
Tommi Jaakkola. This summarize the advancements up to 2023. There have been lots of exciting new works since!
1
78
301
1
16
132
Tomorrow we discuss the paper "Recipe for a General, Powerful, Scalable Graph Transformer" with the authors! 🔥
Find out most of the current state of graph transformers by joining us on Zoom on Tue at 11am EST / 3pm UTC:
1/2
2
24
130
This Tuesday,
@stevenygd
will join our Graph and Geometry reading group discussion about his paper "Geometry Processing with Neural Fields"!
Join the Zoom at 4pm UTC:
Co-authors:
@SergeBelongie
@BharathHarihar2
Vladen Koltun
1
22
129
Look at these most beautiful slides from
@SoledadVillar5
's keynote
@LogConference
happening right now!
About her new work on "Random Graph Models and Graph Neural Networks" 🤗
Find the Zoom link here:
Or watch the stream:
0
25
127
The GraphML reading group recording of
@andreeadeac22
's and Louis-Pascal's explanation of their NeurIPS papers on neural algorithmic reasoning is online!
0
22
127
This Tuesday in the reading group,
@WengongJin
will present his "Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design":
Awesome and impactful if I may make that judgment!
Join on Zoom at 4pm GMT
1/2
2
28
126
This Tuesday in the GraphML reading group we witness the solution to Graph Transformers?
@dereklim_lzh
and
@Josh_d_robinson
explain their Sign and Basis Invariant spectral encodings for GNNs!
On Zoom at 11am EST/5pm CEST:
Paper
1/2
5
25
124
Tomorrow (Monday)
@HajijMustafa
will summarize his survey "Topological Deep Learning: Going Beyond Graph Data" in the LoGG reading group!
Join us on Zoom at 11am EDT / 3pm UTC:
0
23
125
This Tuesday in the GraphML reading group,
@zhu_zhaocheng
will present his fantastic paper "Neural Bellman-Ford Networks: A General Graph
Neural Network Framework for Link Prediction":
Join on Zoom at 4pm UTC:
1/2
3
16
116
Tomorrow
@HoldijkLars
presents his paper "Path Integral Stochastic Optimal Control for Sampling Transition Paths" ()
I think the SOC ideas might have even more applicability in this field!
Join on Zoom at 11am EDT / 5pm CET:
1
19
106
Tomorrow in the reading group we discuss "Smooth, exact rotational symmetrization for deep learning on point clouds"!
Join us at 11am EDT / 5pm CEST on zoom:
1
21
112
Tomorrow (Monday) reading group session:
@michael_galkin
presents "Towards Foundation Models for Knowledge Graph Reasoning" !
I predict there will be at least 1 meme slide🙃
Join us on Zoom at 11am ET / 5pm CET / 4pm UTC:
2
22
110
For ICML submissions, remember that they require an impact statement
(I may be among those who did not realize until now 🙃)
3
11
110
Is anyone interested in faster FID calculation for high-dim embeddings?
I first used .
For 2k dim: 6 sec
For 16k dim: 1h 32min
Then use "Newton-Schulz iteration" for matrix sqrt
For 16k dim: 16 sec (and lower sqrt error)
Let me know if anyone wants this
4
15
109
Tomorrow's paper in our Zoom reading group: "Clifford Group Equivariant Neural Networks" with the author
@djjruhe
! Another piece in
@jo_brandstetter
's line :D
Join us on Zoom at 11am EDT / 3pm UTC / 5pm CEST:
2
13
109
On Monday we are joined by
@HoldijkLars
and
@priyankjaini
to discuss their paper "Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient Descent"!
Join on Zoom at 11am ETD / 3pm UTC:
0
19
106
Reading group session tomorrow:
@chinwei_h
and
@MAghajohari
present their "Riemannian Diffusion Models"!
On Zoom at 11am EDT / 5pm CEST:
1
31
108
Reading group tomorrow:
"Generative Modeling with Phase Stochastic Bridges" with Tianrong Chen
Join on zoom at 11am EST / 5pm CET / 4pm UTC:
0
17
105
Tomorrow in the GraphML reading group we have
@Francesco_dgv
@_JRowbottom
and
@b_p_chamberlain
presenting their "GNNs as Gradient Flows"
Join us on Zoom at 11am EDT / 3pm UTC:
Co-authors:
Thomas Markovich
@mmbronstein
4
12
103
"Flow Annealed Importance Sampling Bootstrap" is what we discuss tomorrow with the authors
@SilkyDogfish
and
@VStimper
! Paper:
Join the discussion at 11am EST / 5pm CET on zoom:
Co-authors:
@gncsimm
@bschoelkopf
@jmhernandez233
3
17
102
How to GNN for your atom point cloud. I am quite impressed by this presentation:
"Smooth, exact rotational symmetrization for deep learning on point clouds"
1
19
99
Today
@ffabffrasca
and
@beabevi_
discuss their "Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries"
It is a nice paper. Join us at 11am EST / 5pm CET on zoom:
Co-authors:
@mmbronstein
@HaggaiMaron
1
17
97
This Monday, we discuss a new 3D GNN framework with the authors Weitao Du,
@YuanqiD
, and
@limei69990587
:
Come discuss with the authors what is new about this one more 3D GNN
Join us at 11am EDT / 5pm CEST on Zoom:
2
19
96
Please spread the word that the
@LogConference
abstract submission deadline is on Sept 9th!
Submit your papers!
We ensure excellent reviewers for both the 9 page full paper track (in PMLR proceedings if accepted) and the 4 page extended abstract track 👌
0
47
95
Tomorrow in the reading group: "Designing losses for data-free training of normalizing flows on Boltzmann distributions" with the authors Loris Felardos and Jérôme Hénin!
Join us on Zoom at 11am EDT / 3pm UTC / 5pm CEST:
0
11
95
New updates on DiffDock + accepted to
#ICLR
!
Knowing how small molecules bind to proteins is important for drug discovery: in the crucial scenario where the bound protein structure is unknown DiffDock also outperforms the baselines (10.4% success vs 21.7%)
7
10
94
Tomorrow 3pm UTC in the GraphML reading group
@CristianBodnar
and
@ffabffrasca
present their Weisfeiler and Lehman Go Cellular: CW Networks!
GNNs + topology => 🚀
@kneppkatt
@guidomontufar
@pl219_Cambridge
@mmbronstein
@Cambridge_CL
@TwitterResearch
1/2
3
18
92
"Stability-Aware Training of Neural Network Interatomic Potentials with Differentiable Boltzmann Estimators"
the paper we discuss tomorrow in the reading group with Sanjeev Raja.
On zoom, anyone can join, 11am EDT, link here:
1
17
91
A new GraphML reading group recording is up!
@chaitjo
gives a great overview of the world of GNNs for solving routing problems and other combinatorial optimization problems!
Very interesting discussion points and future ideas!
0
21
89
The best mentor
14
2
90
In today's reading group session in 15 minutes
@ClementVignac
will discuss his paper "DiGress: Discrete Denoising diffusion for graph generation" with us!
Join us on Zoom at 11am EDT / 3pm UTC:
Recordings will also be available!
0
12
90
In 24h the legends
@Francesco_dgv
@tk_rusch
return to present their "How does over-squashing affect the power of GNNs?"
😮
Do not miss this n-th appearance tomorrow at 11am EDT / 3pm UTC / 5pm CEST on zoom:
0
15
87
New Graph ML paper explanation video!
Professors
@jo_brandstetter
and
@erikjbekkers
present their paper "Geometric and Physical Quantities Improve E(3) Equivariant Message Passing"
Fantastic insights 👌
Co-authors:
@robdhess
@ElisevanderPol
@wellingmax
1
19
87
It is almost frequently happening now that attendees of our Graph ML reading group ask me if we could set up a Slack or Discord 😅
We DO have a Slack since ~day 1:
I am not sure how to advertise it better, but here is an attempt ^^
2
13
84
Just started at
@LogConference
: a fantastic tutorial on "Exploring the Practical and Theoretical Landscape of Expressive Graph Neural Networks" by
@ffabffrasca
@beabevi_
and
@HaggaiMaron
!
Find all information to join in our Slack:
0
19
83
If you train a flow matching model, try self-conditioning!
It is a very simple tweak, and I think it is almost always worth a try.
Explanation in the HarmonicFlow paper:
Section 3.1 "structure self-conditioning" or in Algorithm 3.
2
6
85
This Tuesday in the
#GraphML
reading group
@WujieWang
and
@MinkaiX
present their paper "Generative Coarse-Graining of Molecular Conformations"!
Join us on Zoom tomorrow at 11am EST / 3pm UTC here:
1/2
3
7
82
Reading group tomorrow (1h earlier for Europe than usual).
"Mirror Diffusion Models" with
@guanhorng_liu
:
Join on Zoom at 11am EDT / 3pm UTC / 4pm CET:
1
12
83
This Tuesday in the reading group
@xiangfu_ml
will present his paper Simulate Time-integrated Coarse-grained Molecular Dynamics with Geometric Machine Learning!
Join us at 11am EST / 3pm UTC on Zoom or sign up for a reminder:
1/2
1
10
81
Great to see that MIT News covered our DiffDock paper for docking molecules to Proteins! 🤗
Code (and hugging face demo, thanks
@simonduerr
):
The article:
Authors:
@GabriCorso
, Bowen Jing,
@BarzilayRegina
, and Tommi Jaakkola.
0
16
81
This is another very neat paper 👌
"MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation"
I think this framework has applications way beyond their examples - join us to discuss it on Zoom tomorrow at 11am ET:
2
18
81
This Tuesday in LoGaG
@Francesco_dgv
@jctopping
and
@b_p_chamberlain
present their "Understanding over-squashing and bottlenecks on graphs via curvature" - an absolute super-star paper from
#iclr2022
!🚀
Join the meeting here:
1/2
3
21
80