دنبال کردن
Vishaal Udandarao
Vishaal Udandarao
PhD Student, University of Tübingen & University of Cambridge
ایمیل تأیید شده در cam.ac.uk - صفحهٔ اصلی
عنوان
نقل شده توسط
نقل شده توسط
سال
Sus-x: Training-free name-only transfer of vision-language models‏
V Udandarao, A Gupta, S Albanie‏
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023‏
1072023
No" zero-shot" without exponential data: Pretraining concept frequency determines multimodal model performance‏
V Udandarao, A Prabhu, A Ghosh, Y Sharma, P Torr, A Bibi, S Albanie, ...‏
The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024‏
442024
Cobra: Contrastive bi-modal representation algorithm‏
V Udandarao, A Maiti, D Srivatsav, SR Vyalla, Y Yin, RR Shah‏
arXiv preprint arXiv:2005.03687, 2020‏
322020
EDUQA: Educational domain question answering system using conceptual network mapping‏
A Agarwal, N Sachdeva, RK Yadav, V Udandarao, V Mittal, A Gupta, ...‏
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019‏
252019
Memeify: A large-scale meme generation system‏
SR Vyalla, V Udandarao‏
Proceedings of the 7th ACM IKDD CoDS and 25th COMAD, 307-311, 2020‏
172020
InPHYNet: Leveraging attention-based multitask recurrent networks for multi-label physics text classification‏
V Udandarao, A Agarwal, A Gupta, T Chakraborty‏
Knowledge-Based Systems 211, 106487, 2021‏
132021
Understanding and Fixing the Modality Gap in Vision-Language Models‏
V Udandarao‏
https://www.mlmi.eng.cam.ac.uk/files/2021-2022_dissertations …, 2022‏
122022
On the inference of soft biometrics from typing patterns collected in a multi-device environment‏
V Udandarao, M Agrawal, R Kumar, RR Shah‏
2020 IEEE Sixth International Conference on Multimedia Big Data (BigMM), 76-85, 2020‏
102020
Changing landscape of technical education pedagogy from traditional to practical e-learning‏
A Gupta, S Motwani, A Agarwal, V Udandarao, T Chakraborty‏
Computer 55 (11), 16-28, 2022‏
82022
Lifelong Benchmarks: Efficient Model Evaluation in an Era of Rapid Progress‏
A Prabhu, V Udandarao, P Torr, M Bethge, A Bibi, S Albanie‏
NeurIPS 2024, 2024‏
62024
Visual data-type understanding does not emerge from scaling vision-language models‏
V Udandarao, MF Burg, S Albanie, M Bethge‏
arXiv preprint arXiv:2310.08577, 2023‏
62023
DisCont: Self-Supervised Visual Attribute Disentanglement using Context Vectors‏
S Bhagat, V Udandarao, S Uppal‏
ICML Workshop on ML Interpretability for Scientific Discovery, 2020‏
62020
A Practitioner's Guide to Continual Multimodal Pretraining‏
K Roth, V Udandarao, S Dziadzio, A Prabhu, M Cherti, O Vinyals, ...‏
NeurIPS 2024, 2024‏
52024
Centaur: a foundation model of human cognition‏
M Binz, E Akata, M Bethge, F Brändle, F Callaway, J Coda-Forno, ...‏
arXiv preprint arXiv:2410.20268, 2024‏
42024
Data contamination report from the 2024 CONDA shared task‏
O Sainz, I García-Ferrero, A Jacovi, JA Campos, Y Elazar, E Agirre, ...‏
arXiv preprint arXiv:2407.21530, 2024‏
42024
CiteME: Can Language Models Accurately Cite Scientific Claims?‏
O Press, A Hochlehnert, A Prabhu, V Udandarao, O Press, M Bethge‏
NeurIPS 2024, 2024‏
42024
Active data curation effectively distills large-scale multimodal models‏
V Udandarao, N Parthasarathy, MF Naeem, T Evans, S Albanie, ...‏
arXiv preprint arXiv:2411.18674, 2024‏
32024
It’s levasa not leviosa! latent encodings for valence-arousal structure alignment‏
SS Nath, V Udandarao, J Shukla‏
Proceedings of the 3rd ACM India Joint International Conference on Data …, 2021‏
22021
ONEBench to test them all: Sample-level benchmarking over open-ended capabilities‏
A Ghosh, S Dziadzio, A Prabhu, V Udandarao, S Albanie, M Bethge‏
arXiv preprint arXiv:2412.06745, 2024‏
12024
ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models‏
J Roberts, MR Taesiri, A Sharma, A Gupta, S Roberts, I Croitoru, ...‏
arXiv preprint arXiv:2502.09696, 2025‏
2025
سیستم در حال حاضر قادر به انجام عملکرد نیست. بعداً دوباره امتحان کنید.
مقاله‌ها 1–20