@KatharinaP19256 @margret_keuper @IsaacBr45419303 @SteWalter @dwsunima Amazing work! Very interesting 😄

I spy with my little eye... a WACV paper. We investigate visual frame detection using Minimum Cost Multicut clustering. Check out the paper to see which foundation model embedding space works best: @IsaacBr45419303 @margret_keuper @SteWalter @dwsunima

Paper: (Camera-Ready coming soon) Code & Data: Work by me, @jovita_lukasik, @jung_vision, Robert Geirhos, @jmie_mirza, @margret_keuper, @JanisKeuper. @dwsunima, @cvml_mpiinf, @MIT_CSAIL, @UniSiegen, @GoogleDeepMind

We're hiring! Want to join @dwsunima for a one-year PostDoc in an exciting project on the crossroads of #knowledgegraph research and #medical applications? Apply now:

💪We train NaSE on 2 curated massively #multilingual news datasets, perfect for #NLProc tasks!🔥 👉 Explore on @huggingface🤗: 📁PolyNews: 📁PolyNewsParallel: Joint work w/ @fdschmidt @gg42554 @heikopaulheim @dwsunima

We are excited to hear @SwetaMahajan1 speak about her recent work on XAI, today live at Uni Mannheim. @dwsunima @KeuperLabs @margret_keuper

Huu Tan Mai presenting joint work of @dwsunima and @BoschGlobal research at #iswc2024, exploring the question whether #LLMs can adapt to unseen domains. Paper:

@dwsunima's @svenhertling presenting amazing work on #KnowledgeGraph construction w/ #LLMs and function calls at @lm_kbc #iswc2024. Joint work w/ @lysander07 from @fiziseka. Paper:

Interesting new work by @PaulGavrikov in collaboration with @margret_keuper @JanisKeuper @KeuperLabs @cvml_mpiinf @dwsunima @shashankska that opens new possibilities for future work towards interpretable Deep Learning!

🚀 Introducing MANNeR, our modular news recommendation 🤖📰 framework that uses ⚖️ metric-based learning to support on-the-fly customization over multiple aspects at inference time. #emnlp2024 findings: w/ @gg42554 @heikopaulheim @dwsunima (1/⏳️)

@heikopaulheim @dwsunima I gotta get used to that new name now 😄

Congrats to our latest @dwsunima alumnus, Dr. Michael Schlechtinger, who defended his thesis collusive behavior of deep reinforcement learning based pricing AIs today! Well done, Dr. @BlooomMusic :-)

Thank you very much to Ines Rehbein (@dwsunima) for using pizza to raise our awareness for the pitfalls (and the potentials) of using transformer-based text classification for the social sciences. Take-home message: Never trust a model that you haven't validated on your own data!

@RitaTorresSousa introduces her project on "Serving up-to-date Dynamic #KnowledgeGraph #Embeddings" at the university's #OpenScience day. @dwsunima

Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Context, Accepted at @eccvconf 2024, a joint work with @JuliaGrabinski and @margret_keuper. Affiliations: @dwsunima @FraunhoferITWM @cvml_mpiinf @KeuperLabs

CosPGD: An efficient white-box adversarial attack for pixel-wise prediction tasks, Accepted at @icmlconf 2024, a joint work with @jung_vision and @margret_keuper. Affiliations: @dwsunima, @cvml_mpiinf, @KeuperLabs.

Joint work with @cvml_mpiinf and @dwsunima !

"MultiMax: Sparse and Multi-Modal Attention Learning" by Yuxuan Zhou, @mariojfritz, and @margret_keuper, in collaboration with @dwsunima and  @CISPA.

"Implicit Representations for Constrained Image Segmentation" by Jan Philipp Schneider, @_Mishal_Fatima, @jovita_lukasik, Andreas Kolb, @margret_keuper, and Michael Moeller, in collaboration with @UniSiegen and @dwsunima.