Dim Papadopoulos
@dim_p_papa
Followers
181
Following
644
Media
11
Statuses
54
Associate Professor at @DTU_Compute | Previously PostDoc at @MIT_CSAIL
Joined March 2022
Looking forward to talking about Efficient Test-Time Scaling for Small Vision-Language Models at the University of Waterloo in the Davis Center 3301 at 4:30pm today. This is joint work with @monurcan55 and @dim_p_papa
https://t.co/Zx0YJ3HAtY
0
8
31
Excited to share our latest work!🎉 We propose an efficient test-time scaling framework for small vision-language models via Test-Time Augmentation and Test-Time Adaptation. https://t.co/uQMnoUvgCA
@delliott @dim_p_papa
#TestTimeScaling #VLM #Multimodal #LLM #DeepLearning #AI
monurcan.github.io
We propose two efficient and effective methods improving multimodal small language models at test-time: TTAug (input augmentation + token-level aggregation) and TTAdapt (parameter adaptation via...
1
2
6
Congratulations to everyone who got their @NeurIPSConf papers accepted 🎉🎉🎉 At #EurIPS we are looking forward to welcoming presentations of all accepted NeurIPS papers, including a new “Salon des Refusés” track for papers which were rejected due to space constraints!
4
25
240
EurIPS is coming! 📣 Mark your calendar for Dec. 2-7, 2025 in Copenhagen 📅 EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @NeurIPSConf and #NordicAIR and is co-developed by @ELLISforEurope
https://t.co/RSAvf9lcZm
1
27
79
🚨 Recruiting PhD students to join my team at @DTU_VisualComp & @AiCentreDK on 3D Vision! 🇩🇰 🚲🌊🏰 Copenhagen is an emerging hub for computer vision with a thriving community—and it’s an amazing city! 📢 Apply now: https://t.co/W6vtAuTDZY & please reach out with any questions!
1
17
38
Thomas Moeslund from @aaucreate is kicking of the @AiCentreDK Computer Vision workshop, with presentations from @dim_p_papa , @christian_igel , and Thomas, and their research groups #ComputerVision
1
2
5
Our computer vision textbook is released! Foundations of Computer Vision with Antonio Torralba and Bill Freeman https://t.co/We0ZSJzkle It’s been in the works for >10 years. Covers everything from linear filters and camera optics to diffusion models and radiance fields. 1/4
45
408
2K
📢 We have an open PostDoc position at @DTU_Compute in Copenhagen in the area of computer vision with deep learning for material and computational design in collaboration with the Royal Danish Academy @kglakademi: https://t.co/oeOTrCexZj Deadline: 15 May 2024
efzu.fa.em2.oraclecloud.com
Do you want to advance the state-of-the-art research in computer vision for material and computational design?
0
8
20
Jens @JParslov is now on stage at the synthetic data generation workshop of #D3A 1.0 presenting our work on damage assessment #CrashCar101
@DataScienceDK @AiCentreDK Project page: https://t.co/k0pluEWWvX
0
1
6
Great start for D3A 1.0!🤩500+ professionals unite for two days of inspiration on AI, data science and digitalization at Hotel Nyborg Strand. Keynote by prof. Mor Naaman highlights AI’s impact on human communication. Stay tuned for more insights! #D3A
0
5
18
Postdoc opportunity @DIKU_Institut @AiCentreDK with start date in September, application deadline February 1. Please help us spread the word! 🙏
Postdoc Opportunity in Multimodal Narrative Analysis 📣 Think @tvtropes /Periodic Table of Storytelling, but for real life 🗣️ (1/10)
0
6
12
DTU team 🇩🇰 @DTU_Compute @DTUtweet at #WACV2024 🏝️ Kudos to the organizers for an amazing and very well-organized event @wacv_official
1
3
15
If you are interested in image labeling or video segmentation, Thanos @thanosdel_ is presenting his EVA-VOS work at poster #73 #WACV2024 @wacv_official
Two papers accepted to #WACV2024 @wacv_official 1/2 Learning the What and How of Annotation in Video Object Segmentation https://t.co/4HjTC78mts
https://t.co/nK3aMDeX7M with @thanosdel_ and @VickyKalogeiton
1
3
31
Jens @JParslov and Erik @erikriise98 are ready to explain you how we deal with damage assessment in images by synthetically damaging cars #WACV2024 @wacv_official
Two papers accepted to #WACV2024 @wacv_official 2/2 CrashCar101: Procedural Generation for Damage Assessment https://t.co/91nlLKWRh3
https://t.co/k0pluEWoGp with @JParslov and @erikriise98
0
3
10
Two papers accepted to #WACV2024 @wacv_official 2/2 CrashCar101: Procedural Generation for Damage Assessment https://t.co/91nlLKWRh3
https://t.co/k0pluEWoGp with @JParslov and @erikriise98
0
8
19
Two papers accepted to #WACV2024 @wacv_official 1/2 Learning the What and How of Annotation in Video Object Segmentation https://t.co/4HjTC78mts
https://t.co/nK3aMDeX7M with @thanosdel_ and @VickyKalogeiton
0
6
25
📢 We have a fully-funded PhD position at @DTU_Compute, @DTU_VisualComp in Copenhagen in the area of computer vision with deep learning for human-machine collaboration: https://t.co/dM2UwzrcZE Deadline: 2 January 2024 @AiCentreDK @DFF_raad [Please RT]
efzu.fa.em2.oraclecloud.com
Do you want to advance the state-of-the-art research in computer vision systems using human-machine collaboration? The Technical University of Denmark (DTU) invites you to apply for a fully funded...
2
11
25
Our project MATTERS received a @VILLUMFONDEN Synergy grant! I am looking forward to this collaboration with Isak Worre Foged and the Royal Danish Academy to analyze the properties of biogenic materials using computer vision and multimodal learning. @DTU_Compute @AiCentreDK
How about harvesting solar energy using coral-inspired microgeometry? Or use af AI for ethical surveillance? 15 projects receive grants in DK’s largest programme for data-driven interdisciplinary research #VillumSynergy #dkforsk #dkscience
https://t.co/ZMcArjh80L
0
2
15
You can find @thanosdel_ at E08 right now to learn more about our work @cveu_workshop @ICCVConference
@AiCentreDK @DTU_VisualComp
Excited to present tomorrow our work with @VickyKalogeiton and @dim_p_papa on efficient video annotation📽️ at @cveu_workshop @ICCVConference! Join to check the poster and discuss! Project page:
1
0
12