PhD from @Yale, Distinguished Research Scientist at @SiemensDE, AI Professor @LMU_Muenchen, Fellow @ELLISmunichunit
München, Bayern
Joined June 2011
- Tweets59
- Following221
- Followers297
- Likes155
Thanks to the organizers! Very relevant workshop! Unfortunately, I can only join online
Join us at the #CVPR2024 Workshop on Scene Graphs and Graph Representation Learning (@sg2rl)!
We have an amazing set of speakers talking about #3D Scene Graphs, #Semantics, and #LLMs.
@_krishna_murthy @vtresp @phanein
@ir0armeni @eadeli @fedassa @NassirNavab @CVPR
Volker Tresp retweeted
Join us at the #CVPR2024 Workshop on Scene Graphs and Graph Representation Learning (@sg2rl)!
We have an amazing set of speakers talking about #3D Scene Graphs, #Semantics, and #LLMs.
@_krishna_murthy @vtresp @phanein
@ir0armeni @eadeli @fedassa @NassirNavab @CVPR
On a historical note: During the Golden Decade of the Conference on Neural Information Processing Systems (then NIPS, now, NeurIPS) from 1990-2000, I had 16 papers published in its proceedings, more than any researcher working in Europe.
We got a lot of positive feedback during the workshop. Thanks to everyone attending and also to ELLIS for providing the opportunity to realize this event in Oberwolfach.
Three days of intense discussions & expert talks: Our #ELLISProgram ‘Semantic, Symbolic and Interpretable #MachineLearning’ gathered a group of international researchers for a workshop at the Oberwolfach Research Institute for Mathematics in Germany!
👉 ellis-ssiml.github.io
Great program! Please join. -V
Registration for general attendance now open for this year's mathematics of neuroscience conference:
neuromonster.org
We've got a full schedule of great talks, and would love to have you join us!
Also accepting physical/virtual poster submissions until Sept 20th.
Volker Tresp retweeted
Registration for general attendance now open for this year's mathematics of neuroscience conference:
neuromonster.org
We've got a full schedule of great talks, and would love to have you join us!
Also accepting physical/virtual poster submissions until Sept 20th.
If one agent sees an image and utters: "A yellow and black bird is on tree branch" how do we know that another agent understands this correctly? This is studied in our ICCV paper (1/3) "Do DALL-E and Flamingo Understand Each Other?" arxiv.org/pdf/2212.12249.pdf
Without memories we have no understanding of the world, or as Goethe put it: “We only see what we know.“ My student Hang Li presented our work on the tensor brain arxiv.org/abs/2109.13392 at this for2812.rub.de/gem2023/remar… workshop on generative episodic memories.
Volker Tresp retweeted
Von A wie #AIAct bis Z wie Zero-Shot-Learning: Das war die #PLSKonferenz2023! Unser Souvenir à 40 Sekunden 👇🎬 @BMBF_Bund @acatech_de @csmoderatorin @janwoerner @sabinedoering @DeepLcom
Volker Tresp retweeted
Nicht nur auf Risiken von generativer #KI schauen, sondern Chancen in Deutschland nutzen, mit Rechenleistung und Innovationsgeist, so Nicolas Flores-Herr @FraunhoferIAIS und @vtresp auf der #PLSKonferenz2023
Volker Tresp retweeted
Honored and happy to (re-)join my alma mater
@LMU_Muenchen as honorary professor for #MachineLearning in the #LifeSciences, 16 years after completing my doctoral studies in Munich
Volker Tresp retweeted
🗓️14.3. bei @acatech_de am Dienstag: Was ändern #ChatGPT & Co.? Zu Auswirkungen auf #Bildung und Arbeit diskutieren unsere Mitglieder @vtresp @LMU_Muenchen , Ute Schmid @uni_bamberg_of und @johanneshoffart @SAP mit dem virtuellen Publikum.
Hier anmelden 👉acatech.de/termin/acatech-am…
Volker Tresp retweeted
If you are visiting @RealAAAI, check out our work "InstanceFormer". Great job @rajatkoner and @hannan_tanveer!
If you are in Washington D.C. or attending @RealAAAI , check out our poster on 12th December named InstanceFormer, it is a simplified, tracker-free, single-stage video instance segmentation framework for long and occluded videos.@hannan_tanveer @sahandsharif
Pleased to share our #AAAI23 paper Instanceformer. Kudos to @rajatkoner and @hannan_tanveer
Arxiv: arxiv.org/abs/2208.10547
Code: github.com/rajatkoner08/Inst…
TL/DR: We present a tracking-free online VIS with novel temporal propagation and a concise but effective memory mechanism.(1/4)
Second, we propose a contrastively learned compact memory module to replace the cumbersome Spatiotemporal attention. Memory attention allows an instance query to look into its past, rectify possible mistakes, and anticipate future deviations.
(3/4)
