#FlowMatching - Twitter Hashtag

about 5 hours ago

Unsupervised source separation matches supervised models without clean training data. SURF uses flow matching with remixing bootstrap. Handles domain shifts. Demo released. #SourceSeparation #FlowMatching #MIR https://t.co/wQTAXFgmcT

0

4

mikel @mikel_zhobro

4 days ago

What is the sota for training diffusion/flow-matching models without direct supervision? Lets say, diffusion in 3D and supervision in 2D. Is this the best we can do? https://t.co/jVCfpqS6Sm #diffusion #flowmatching #3DGS

0

47

Baran Hashemi @Rythian47

4 months ago

6/ 📄 Paper: https://t.co/uqpsKnfqV8 💻 Code: https://t.co/qs8hngVf3B Built at @AarhusUni and @mpiMathSci, and @TU_Muenchen Happy to discuss methodology, results, or potential applications! #AI4Mathematics #AI4Science #FlowMatching

1

6

1

3

621

Nature Computational Science @NatComputSci

5 months ago

📢Out now! @MingjieLiu_UFL, @SteMartiniani, and colleagues present PropMolFlow, a flow-matching method for property-guided molecule generation. #MoleculeDiscovery #FlowMatching https://t.co/TxQQik18UJ 🔓https://t.co/XPvyvrrLJ5

0

8

2

3

2K

Amir Habibian @amir_habibian

8 months ago

Research internship openings at Qualcomm AI Research - Amsterdam Research on efficient generative modeling of visual and multimodal data: https://t.co/VKgLggtpAV #Diffusion, #FlowMatching, #AutoRegressive , #GaussianSplatting, #VLMs, #MLLMs.

amir_habibian's tweet photo. Research internship openings at Qualcomm AI Research - Amsterdam

Research on efficient generative modeling of visual and multimodal data:
https://t.co/VKgLggtpAV

#Diffusion, #FlowMatching, #AutoRegressive , #GaussianSplatting, #VLMs, #MLLMs. https://t.co/dDg71q2RYA

3

224

25

160

14K

Christian A. Naesseth @canaesseth

9 months ago

I presented our recent work on #SDEMatching, a groundbreaking new way to learn stochastic differential equations that entirely sidesteps numerical simulation and discretisation. Slides: https://t.co/mnBEkvilBS #simulationfree #SDE #Diffusion #FlowMatching #ScoreMatching

1

3

0

2

190

Christian A. Naesseth @canaesseth

11 months ago

At #ICML2025 this week? Come check out our work on controlled generation, simulation-free latent SDEs, and risk monitoring in test-time adaptation, and chat with the awesome students that made it happen! #SDE #Diffusion #FlowMatching #TTA #UncertaintyQuantification

1

17

1

1K

Christian A. Naesseth @canaesseth

11 months ago

🚨🚀 Come hear @GrigoryBartosh talk about SDE Matching! SDE Matching is a highly efficient and scalable training framework for Latent/Neural SDEs. You no longer have to discretize or simulate your SDE models when fitting them to data. #SDE #Diffusion #FlowMatching #ML

MolSS Reading Group @MolSS_Group

11 months ago

On the coming Tuesday (July 1st), we will have @GrigoryBartosh talking about “SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations" (https://t.co/EYPXbrvHoX) 🚀, from 4pm to 5pm (UK time). Join us via Zoom 🔥https://t.co/N1C3UFukxd

0

10

4

6

5K

0

27

4

5

2K

Christian A. Naesseth @canaesseth

12 months ago

I like the resurgence of "old-school" NFs that is happening. Here to distill CNFs for free-energy estimation. RL https://t.co/bVPe9Ta1WI Diffusion models (NFDM) https://t.co/V9B1T8e5AD Latent SDEs (SDE Matching) https://t.co/k8PNxYTYZP #SDE #Diffusion #GenAI #ML #FlowMatching

Danyal Rehman @danyalrehman17

about 1 year ago

Excited to release FORT, a new regression-based approach for training normalizing flows 🔥! 🔗 Paper available here: https://t.co/2dMjkvEwBp New paper w/ @osclsd @jiarlu @tangjianpku @mmbronstein @Yoshua_Bengio @AlexanderTong7 @bose_joey 🧵1/6

danyalrehman17's tweet photo. Excited to release FORT, a new regression-based approach for training normalizing flows 🔥!

🔗 Paper available here: https://t.co/2dMjkvEwBp

New paper w/ @osclsd @jiarlu @tangjianpku @mmbronstein @Yoshua_Bengio @AlexanderTong7 @bose_joey

🧵1/6 https://t.co/ruFLcvHVlt

2

89

23

47

23K

1

44

7

22

4K

Seongsu Kim @seongsukim_ml

about 1 year ago

[7/7] 4⃣Real acceleration of DFT/SCF • 53% time reduction compared to conventional method • 30% time reduction compared to baseline #DFT #AI4science #GenerativeModel #FlowMatching #DensityFunctionalTheory #ComputatioanlPhysics #MachineLearning

1

3

0

103

Eleonora Grassucci @eleonoragrassuc

about 1 year ago

So happy to finally meet @drscotthawley in person at #ICLR2025!! Can't wait for his tutorial on #FlowMatching at #IJCNN2025!! #ICLR #ICLR25 @iclr_conf @dhan90001

eleonoragrassuc's tweet photo. So happy to finally meet @drscotthawley in person at #ICLR2025!! Can't wait for his tutorial on #FlowMatching at #IJCNN2025!!

#ICLR #ICLR25 @iclr_conf @dhan90001 https://t.co/nNyMBHEQwn

0

7

2

0

508

Dominik Klein @Dominik1Klein

over 1 year ago

1/6 Looking for neural estimators of entropic #OptimalTransport or simply cool applications of #FlowMatching? Excited by novel generative modeling tools for #SingleCell data? Check out our #GENOT #NeurIPS paper https://t.co/JCuTihSapT!