SwetaMahajan1 Profile Banner
Sweta Mahajan Profile
Sweta Mahajan

@SwetaMahajan1

Followers
92
Following
45
Media
4
Statuses
31

PhD, Max Planck Institute for Informatics, supervised by Prof. Bernt Schiele. Computer Vision @ IIT Delhi, Mathematics and Statistics @ IISER Kolkata.

Saarbrücken, Germany
Joined July 2012
Don't wanna be here? Send us removal request.
@SwetaMahajan1
Sweta Mahajan
7 days
Come on, bring your best work to eXCV workshop at ICCV and see you in Hawaii!. @ICCVConference #ICCV2025.
@robinhesse_
Robin Hesse
7 days
Got a strong XAI paper rejected from ICCV? Submit it to our ICCV eXCV Workshop today—we welcome high-quality work!.🗓️ Submissions open until June 26 AoE. 📄 Got accepted to ICCV? Congrats! Consider our non-proceedings track. #ICCV2025 @ICCVConference
Tweet media one
0
0
4
@SwetaMahajan1
Sweta Mahajan
10 days
Submission Deadline is extended by 6 days. #ICCV2025 @ICCVConference
Tweet media one
@SwetaMahajan1
Sweta Mahajan
19 days
Join us in advancing explainability in the rapidly evolving landscape of AI! We welcome papers on novel explanation methods, scaling existing xAI approaches, innovations for foundational models, and beyond.
Tweet media one
0
6
11
@SwetaMahajan1
Sweta Mahajan
19 days
Organizers:.@sukrutrao, @robinhesse_, @QBouniot, @SwetaMahajan1, @Amin_Prc, Jayneel Parekh, @schaub_simone, Florence d'Alché-Buc, @zeynepakata, @stefanroth, Bernt Schiele.
0
0
2
@SwetaMahajan1
Sweta Mahajan
19 days
Call for papers is out for the 2nd Explainable Computer Vision - Quo Vadis?. (eXCV) workshop in #XAI at #ICCV2025! More details can be found here: Submission Site: Coming Soon!. @ICCVConference @XAI_Research . 1.
1
0
2
@SwetaMahajan1
Sweta Mahajan
19 days
Join us in advancing explainability in the rapidly evolving landscape of AI! We welcome papers on novel explanation methods, scaling existing xAI approaches, innovations for foundational models, and beyond.
Tweet media one
1
1
4
@SwetaMahajan1
Sweta Mahajan
22 days
Day 1 at #CVPR2025 was 🔥. Workshops, posters, ideas — special shoutout to the EVAL-FoMo Workshop!. Talks that stood out:. 📊 @imisra_ on emergent behaviors in FMs. 🧠 @RanjayKrishna on cognitive architectures & scaling with quality data. ⚙️ @sainingxie on benchmarking MLLMs.
0
1
5
@SwetaMahajan1
Sweta Mahajan
4 months
RT @ELLISInst_Tue: 🚜 Polybot, founded by @wielandbr has secured a 220,000€ validation grant from SPRIND to advance its AI-driven agricultur….
0
1
0
@SwetaMahajan1
Sweta Mahajan
7 months
RT @KatharinaP19256: We are excited to hear @SwetaMahajan1 speak about her recent work on XAI, today live at Uni Mannheim. @dwsunima @Keup….
0
1
0
@SwetaMahajan1
Sweta Mahajan
9 months
Amazing opportunity to work in a highly supportive research group. Apply for your PhD to work on Neuro-explicit models :).
@neuroexplicit
Neuroexplicit Models of Language, Vision, Action
9 months
Now hiring: Twelve (!) PhD students to start in fall 2025, for research on combining neural and symbolic/interpretable models of language, vision, and action. Work with world-class advisors at @Saar_Uni, MPI Informatics, @mpi_sws, @CISPA, @DFKI. Details:
0
0
3
@SwetaMahajan1
Sweta Mahajan
10 months
RT @sukrutrao: I am attending @gcpr_by_dagm this week, and will be presenting these two works (with @SwetaMahajan1, @Amin_Prc) in the poste….
0
4
0
@SwetaMahajan1
Sweta Mahajan
10 months
I am attending @gcpr_by_dagm this week, and will be presenting our work with @sukrutrao in the poster session of the Nectar Track. Really excited to see you at our poster and looking forward to interesting discussions in the conference!. #GCPR2024
Tweet media one
0
2
17
@SwetaMahajan1
Sweta Mahajan
10 months
RT @sukrutrao: @eccvconf @mitymight @eccvconf I am having trouble logging in to the website to access this -- it says (1) I have an account….
0
2
0
@SwetaMahajan1
Sweta Mahajan
10 months
Looking forward to attending ECCV in Milan in a month, super excited to catch up with other researchers working in this domain and exchange ideas during the conference :). Please visit the poster if you want to know more.
0
0
3
@SwetaMahajan1
Sweta Mahajan
10 months
We show that sparse autoencoders can help extract and name concepts known to CLIP vision encoders in an automated manner, and find that the extracted concepts can be used to form performant concept bottleneck models on downstream datasets.
Tweet media one
1
0
3
@SwetaMahajan1
Sweta Mahajan
1 year
RT @elonmusk: Congratulations PM @NarendraModi on being the most followed world leader!.
0
45K
0
@SwetaMahajan1
Sweta Mahajan
1 year
RT @cvml_mpiinf: We are pleased to share that we will be presenting exciting new research @CVPR 2024. Please find a thread (with short summ….
0
8
0
@SwetaMahajan1
Sweta Mahajan
1 year
RT @neuroexplicit: Now hiring: Three PhD students and one postdoc, as part of a research team of ~30, combining neural and symbolic/interpr….
0
6
0