![Nitesh Kumar](https://profiles-cardiff.imgix.net/attachments/4597?w=200&h=200&auto=format&crop=faces&fit=crop&q=90")
Dr Nitesh Kumar
- Ar gael fel goruchwyliwr ôl-raddedig
Timau a rolau for Nitesh Kumar
Darlithydd
Trosolwyg
Mae fy ymchwil yn canolbwyntio ar ddeallusrwydd artiffisial esboniadwy a dibynadwy. Mae gen i ddiddordeb mewn sut y gellir gwneud systemau AI, yn enwedig modelau iaith mawr a systemau AI asegol, yn fwy dibynadwy, dehongladwy a defnyddiol mewn lleoliadau lle mae rhesymu, ansicrwydd ac esboniadau yn bwysig. Mae fy ngwaith yn tynnu ar syniadau o AI niwrosymbolaidd, rhaglennu rhesymeg tebygol, darganfod achosol, prosesu iaith naturiol, a dysgu cynrychiolaeth.
Darpar Fyfyrwyr MPhil/PhD
Rwy'n croesawu ymholiadau gan ddarpar fyfyrwyr MPhil a PhD sydd â diddordeb mewn prosiectau ymchwil ar AI esboniadwy a dibynadwy.
Wrth gysylltu â mi, disgrifiwch yn fyr eich diddordebau ymchwil, sut maen nhw'n cyd-fynd â'm gwaith, ac a oes gennych gyllid eisoes neu'n bwriadu gwneud cais am ysgoloriaethau. Cynhwyswch hefyd dystiolaeth eich bod yn bodloni gofynion mynediad y Brifysgol, gan gynnwys gofynion iaith Saesneg lle bo'n berthnasol.
Mae ymgeiswyr sy'n hunan-ariannu neu sydd eisoes â chyllid o ffynonellau eraill, megis ysgoloriaethau'r llywodraeth, nawdd cyflogwyr, neu ysgoloriaethau allanol, yn cael eu hannog yn arbennig i gysylltu â ni. Rwyf hefyd yn hapus i gefnogi ymgeiswyr cryf sy'n dymuno gwneud cais am ysgoloriaethau PhD cystadleuol, gan gynnwys cynllun Cyngor Ysgoloriaethau Prifysgol Caerdydd-Tsieina.
Cyhoeddiad
2025
- Kumar, N. , Chatterjee, U. and Schockaert, S. 2025. Extracting conceptual spaces from LLMs using prototype embeddings. Presented at: Findings of EMNLP Suzhou, China 4-9 November 2025. Published in: Christodoulopoulos, C. et al., Findings of the Association for Computational Linguistics: EMNLP 2025. Suzhou, China: Association for Computational Linguistics. , pp.9275-9298. (10.18653/v1/2025.findings-emnlp.493)
2024
- Kumar, N. , Chatterjee, U. and Schockaert, S. 2024. Ranking entities along conceptual space dimensions with LLMs: An analysis of fine-tuning strategies. Presented at: The 62nd Annual Meeting of the Association for Computational Linguistics Bangkok, Thailand 11-16 August 2024. Published in: Ku, L. , Martins, A. and Srikumar, V. eds. Findings of the Association for Computational Linguistics ACL 2024. Association for Computational Linguistics. , pp.7974-7989. (10.18653/v1/2024.findings-acl.474)
2023
- Kumar, N. , Kuzelka, O. and De Raedt, L. 2023. First-order context-specific likelihood weighting in hybrid probabilistic logic programs. Journal of Artificial Intelligence Research 77 , pp.683-735. (10.1613/jair.1.13657)
- Kumar, N. and Schockaert, S. 2023. Solving hard analogy questions with relation embedding chains. Presented at: Conference on Empirical Methods in Natural Language Processing, EMNLP Singapore 6-10 December 2023. Published in: Bouamor, H. , Pino, J. and Bali, K. eds. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. , pp.6224–6236. (10.18653/v1/2023.emnlp-main.382)
2022
- Kumar, N. , Kuželka, O. and De Raedt, L. 2022. Learning distributional programs for relational autocompletion. Theory and Practice of Logic Programming 22 (1), pp.81-114. (10.1017/S1471068421000144)
2021
- Kumar, N. and Kuželka, O. 2021. Context-specific likelihood weighting. Presented at: The 24th International Conference on Artificial Intelligence and Statistics Virtual 13 -15 April 2021. Published in: Banerjee, A. and Fukumizu, K. eds. Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS) 2021. Vol. 130.ML Research Press. , pp.2125-2133.
2020
- Zuidberg Dos Martires, P. et al., 2020. Symbolic learning and reasoning with noisy data for probabilistic anchoring. Frontiers in Robotics and AI 7 100. (10.3389/frobt.2020.00100)
Cynadleddau
- Kumar, N. , Chatterjee, U. and Schockaert, S. 2025. Extracting conceptual spaces from LLMs using prototype embeddings. Presented at: Findings of EMNLP Suzhou, China 4-9 November 2025. Published in: Christodoulopoulos, C. et al., Findings of the Association for Computational Linguistics: EMNLP 2025. Suzhou, China: Association for Computational Linguistics. , pp.9275-9298. (10.18653/v1/2025.findings-emnlp.493)
- Kumar, N. , Chatterjee, U. and Schockaert, S. 2024. Ranking entities along conceptual space dimensions with LLMs: An analysis of fine-tuning strategies. Presented at: The 62nd Annual Meeting of the Association for Computational Linguistics Bangkok, Thailand 11-16 August 2024. Published in: Ku, L. , Martins, A. and Srikumar, V. eds. Findings of the Association for Computational Linguistics ACL 2024. Association for Computational Linguistics. , pp.7974-7989. (10.18653/v1/2024.findings-acl.474)
- Kumar, N. and Schockaert, S. 2023. Solving hard analogy questions with relation embedding chains. Presented at: Conference on Empirical Methods in Natural Language Processing, EMNLP Singapore 6-10 December 2023. Published in: Bouamor, H. , Pino, J. and Bali, K. eds. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. , pp.6224–6236. (10.18653/v1/2023.emnlp-main.382)
- Kumar, N. and Kuželka, O. 2021. Context-specific likelihood weighting. Presented at: The 24th International Conference on Artificial Intelligence and Statistics Virtual 13 -15 April 2021. Published in: Banerjee, A. and Fukumizu, K. eds. Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS) 2021. Vol. 130.ML Research Press. , pp.2125-2133.
Erthyglau
- Kumar, N. , Kuzelka, O. and De Raedt, L. 2023. First-order context-specific likelihood weighting in hybrid probabilistic logic programs. Journal of Artificial Intelligence Research 77 , pp.683-735. (10.1613/jair.1.13657)
- Kumar, N. , Kuželka, O. and De Raedt, L. 2022. Learning distributional programs for relational autocompletion. Theory and Practice of Logic Programming 22 (1), pp.81-114. (10.1017/S1471068421000144)
- Zuidberg Dos Martires, P. et al., 2020. Symbolic learning and reasoning with noisy data for probabilistic anchoring. Frontiers in Robotics and AI 7 100. (10.3389/frobt.2020.00100)
Addysgu
CMT651 - Datblygu Meddalwedd Hyblyg (Sem Hydref 2024/25, 2025/26)
CM6113 - Sgiliau Datblygu Meddalwedd 1 (Sem Hydref 2025/26)
Bywgraffiad
Rwy'n Ddarlithydd mewn Deallusrwydd Artiffisial yn yr Ysgol Cyfrifiadureg a Gwybodeg ym Mhrifysgol Caerdydd. Ymunais â'r Ysgol yn 2022 fel Cydymaith Ymchwil a deuthum yn Ddarlithydd yn 2024.
Cyn ymuno â Chaerdydd, cwblheais fy PhD yn yr Adran Gyfrifiadureg yn KU Leuven, Gwlad Belg, lle roeddwn yn gysylltiedig â'r grŵp Ieithoedd Datganiadol a Deallusrwydd Artiffisial (DTAI) a Leuven.AI. Fy ngoruchwylwyr oedd yr Athro Luc De Raedt a'r Athro Ondřej Kuželka.
Derbyniais fy B.Tech mewn Cyfrifiadureg a Pheirianneg o'r Sefydliad Technoleg Cenedlaethol (NIT) Rourkela, a fy MSR mewn Peirianneg Drydanol (Technoleg Gyfrifiadurol) o Sefydliad Technoleg India Delhi (IIT Delhi). Cyn fy PhD, roeddwn i'n gweithio fel peiriannydd meddalwedd yn Samsung R&D Institute India - Delhi (SRID).
Anrhydeddau a dyfarniadau
Cymrodoriaeth, Academi Addysg Uwch (2026)
Contact Details
Themâu ymchwil
Arbenigeddau
- Deallusrwydd artiffisial
- Prosesu iaith naturiol
- Cynrychiolaeth a rhesymu gwybodaeth