Jan Eric Lenssen
@janericlenssen.bsky.social
Senior Researcher at Max Planck Institute for Informatics
Founding Engineer at Kumo.ai
Founding Engineer at Kumo.ai
Can diffusion models solve visual Sudoku?
If you are at #ICML2025, come to our poster in the Wednesday morning poster session (Poster Session 3 East, Poster 3412) and find out!
@chriswewer.bsky.social
If you are at #ICML2025, come to our poster in the Wednesday morning poster session (Poster Session 3 East, Poster 3412) and find out!
@chriswewer.bsky.social
July 14, 2025 at 8:41 PM
Can diffusion models solve visual Sudoku?
If you are at #ICML2025, come to our poster in the Wednesday morning poster session (Poster Session 3 East, Poster 3412) and find out!
@chriswewer.bsky.social
If you are at #ICML2025, come to our poster in the Wednesday morning poster session (Poster Session 3 East, Poster 3412) and find out!
@chriswewer.bsky.social
At #CVPR2025 and working on consistency in video and multi-view generative models?
Come and visit our poster on Friday afternoon, where I present 𝗠𝗘𝘁𝟯𝗥: 𝗠𝗲𝗮𝘀𝘂𝗿𝗶𝗻𝗴 𝗠𝘂𝗹𝘁𝗶-𝗩𝗶𝗲𝘄 𝗖𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝗰𝘆 𝗶𝗻 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝗱 𝗜𝗺𝗮𝗴𝗲𝘀
@mohammadasim98.bsky.social @wimmerthomas.bsky.social @mpi-inf.mpg.de @cvml.mpi-inf.mpg.de
Come and visit our poster on Friday afternoon, where I present 𝗠𝗘𝘁𝟯𝗥: 𝗠𝗲𝗮𝘀𝘂𝗿𝗶𝗻𝗴 𝗠𝘂𝗹𝘁𝗶-𝗩𝗶𝗲𝘄 𝗖𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝗰𝘆 𝗶𝗻 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝗱 𝗜𝗺𝗮𝗴𝗲𝘀
@mohammadasim98.bsky.social @wimmerthomas.bsky.social @mpi-inf.mpg.de @cvml.mpi-inf.mpg.de
June 12, 2025 at 10:38 PM
At #CVPR2025 and working on consistency in video and multi-view generative models?
Come and visit our poster on Friday afternoon, where I present 𝗠𝗘𝘁𝟯𝗥: 𝗠𝗲𝗮𝘀𝘂𝗿𝗶𝗻𝗴 𝗠𝘂𝗹𝘁𝗶-𝗩𝗶𝗲𝘄 𝗖𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝗰𝘆 𝗶𝗻 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝗱 𝗜𝗺𝗮𝗴𝗲𝘀
@mohammadasim98.bsky.social @wimmerthomas.bsky.social @mpi-inf.mpg.de @cvml.mpi-inf.mpg.de
Come and visit our poster on Friday afternoon, where I present 𝗠𝗘𝘁𝟯𝗥: 𝗠𝗲𝗮𝘀𝘂𝗿𝗶𝗻𝗴 𝗠𝘂𝗹𝘁𝗶-𝗩𝗶𝗲𝘄 𝗖𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝗰𝘆 𝗶𝗻 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝗱 𝗜𝗺𝗮𝗴𝗲𝘀
@mohammadasim98.bsky.social @wimmerthomas.bsky.social @mpi-inf.mpg.de @cvml.mpi-inf.mpg.de
Can image generators solve visual Sudoku?
Naively, no, with sequentialization and the correct order, they can!
Check out @chriswewer.bsky.social's and Bart's SRM's for details.
Project: geometric-rl.mpi-inf.mpg.de/srm/
Paper: arxiv.org/abs/2502.21075
Code: github.com/Chrixtar/SRM
Naively, no, with sequentialization and the correct order, they can!
Check out @chriswewer.bsky.social's and Bart's SRM's for details.
Project: geometric-rl.mpi-inf.mpg.de/srm/
Paper: arxiv.org/abs/2502.21075
Code: github.com/Chrixtar/SRM
March 3, 2025 at 2:14 PM
Can image generators solve visual Sudoku?
Naively, no, with sequentialization and the correct order, they can!
Check out @chriswewer.bsky.social's and Bart's SRM's for details.
Project: geometric-rl.mpi-inf.mpg.de/srm/
Paper: arxiv.org/abs/2502.21075
Code: github.com/Chrixtar/SRM
Naively, no, with sequentialization and the correct order, they can!
Check out @chriswewer.bsky.social's and Bart's SRM's for details.
Project: geometric-rl.mpi-inf.mpg.de/srm/
Paper: arxiv.org/abs/2502.21075
Code: github.com/Chrixtar/SRM
Hello bluesky-world :)
Introducing 𝗠𝗘𝘁𝟯𝗥: 𝗠𝗲𝗮𝘀𝘂𝗿𝗶𝗻𝗴 𝗠𝘂𝗹𝘁𝗶-𝗩𝗶𝗲𝘄 𝗖𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝗰𝘆 𝗶𝗻 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝗱 𝗜𝗺𝗮𝗴𝗲𝘀.
Lacking 3D consistency in generated images is a limitation of many current multi-view/video/world generative models. To quantitatively measure these inconsistencies, check out Mohammad Asims new work!
Introducing 𝗠𝗘𝘁𝟯𝗥: 𝗠𝗲𝗮𝘀𝘂𝗿𝗶𝗻𝗴 𝗠𝘂𝗹𝘁𝗶-𝗩𝗶𝗲𝘄 𝗖𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝗰𝘆 𝗶𝗻 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝗱 𝗜𝗺𝗮𝗴𝗲𝘀.
Lacking 3D consistency in generated images is a limitation of many current multi-view/video/world generative models. To quantitatively measure these inconsistencies, check out Mohammad Asims new work!
January 15, 2025 at 6:30 PM
Hello bluesky-world :)
Introducing 𝗠𝗘𝘁𝟯𝗥: 𝗠𝗲𝗮𝘀𝘂𝗿𝗶𝗻𝗴 𝗠𝘂𝗹𝘁𝗶-𝗩𝗶𝗲𝘄 𝗖𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝗰𝘆 𝗶𝗻 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝗱 𝗜𝗺𝗮𝗴𝗲𝘀.
Lacking 3D consistency in generated images is a limitation of many current multi-view/video/world generative models. To quantitatively measure these inconsistencies, check out Mohammad Asims new work!
Introducing 𝗠𝗘𝘁𝟯𝗥: 𝗠𝗲𝗮𝘀𝘂𝗿𝗶𝗻𝗴 𝗠𝘂𝗹𝘁𝗶-𝗩𝗶𝗲𝘄 𝗖𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝗰𝘆 𝗶𝗻 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝗱 𝗜𝗺𝗮𝗴𝗲𝘀.
Lacking 3D consistency in generated images is a limitation of many current multi-view/video/world generative models. To quantitatively measure these inconsistencies, check out Mohammad Asims new work!