--- title: "Manish Kumar — author profile and papers · Reasoning" description: "Manish Kumar, Indian Institute of Information Technology Allahabad: 3 papers on Elamur Research (2023–2026), h-index 36 — affiliations, topics…" canonical: "https://research.elamur.ai/free/en/authors/manish-kumar/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/manish-kumar/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Manish Kumar # Manish Kumar Manish Kumar has 3 papers in our library, in 2023–2026, most of them on [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/), [Code & programming languages](https://md.research.elamur.ai/free/en/topics/code-and-programming/); often with [Alexander Novikov](https://md.research.elamur.ai/free/en/authors/alexander-novikov/), [Emilien Dupont](https://md.research.elamur.ai/free/en/authors/emilien-dupont/), [Francisco J. R. Ruiz](https://md.research.elamur.ai/free/en/authors/francisco-j-r-ruiz/). 3 papers in our library · 2023–2026 [OpenAlex](https://openalex.org/A5018728658) · [ORCID](https://orcid.org/0000-0002-1311-0976) · [**h-index 36**](https://openalex.org/authors/A5018728658) · [439 works](https://openalex.org/works?filter=author.id:A5018728658) · [6,832 citations](https://openalex.org/works?filter=author.id:A5018728658&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 3 works in our library](https://md.research.elamur.ai/free/en/authors/manish-kumar/#papers) · [🔗 Cited 408 times in our library](https://md.research.elamur.ai/free/en/authors/manish-kumar/cited-by/) · [12 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #4352](https://md.research.elamur.ai/free/en/paper-stars/page/44/#star-4352) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Manish+Kumar) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Manish+Kumar) · [dblp](https://dblp.org/search?q=Manish+Kumar) · [ACL Anthology](https://aclanthology.org/search/?q=Manish+Kumar) ## Affiliations [🎓**Indian Institute of Information Technology Allahabad** Prayagraj · India 2005–2011Education 2007–2011 · Ph.D, ITEmployment since 2005 · Associate Professor, Information Technology*current*](https://md.research.elamur.ai/free/en/universities/indian-institute-of-information-technology-allahabad/) · [🎓**University of Oxford** Oxford · United Kingdom 2008–2023 · 36 papers](https://md.research.elamur.ai/free/en/universities/university-of-oxford/) · [🎓**École Centrale Paris** Châtenay-Malabry · France 2012–2016 · 12 papers](https://ror.org/00v0y5771) · [🎓**Stanford University** Stanford · United States 2008–2012 · 8 papers](https://md.research.elamur.ai/free/en/universities/stanford-university/) · [🔬**The Alan Turing Institute** London · United Kingdom 2016–2019 · 7 papers](https://md.research.elamur.ai/free/en/labs/the-alan-turing-institute/) · [🔬**CentraleSupélec** Gif-sur-Yvette · France 2014–2016 · 7 papers](https://md.research.elamur.ai/free/en/labs/centralesupelec/) · [🎓**Oxford Brookes University** Oxford · United Kingdom 2005–2007 · 7 papers](https://ror.org/04v2twj65) · [🔬**Centre de Vision Numérique** Gif-sur-Yvette · France 2014–2016 · 6 papers](https://ror.org/043k3s342) · [🔬**Institut national de recherche en sciences et technologies du numérique** Le Chesnay-Rocquencourt · France 2013–2015 · 6 papers](https://md.research.elamur.ai/free/en/labs/institut-national-de-recherche-en-sciences-et-technologies-du-numerique/) · [🔬**Centre Inria de Saclay** Palaiseau · France 2013–2015 · 4 papers](https://md.research.elamur.ai/free/en/labs/centre-inria-de-saclay/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 7 more institutions on single bylines are not listed. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 5 The field of science this work belongs to (OpenAlex fields).[Computer Science · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Information Systems · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · [Arts and Humanities · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) 🧭 Topics 2 Research subjects and languages the work is about.[Code & programming languages · 1 work](https://md.research.elamur.ai/free/en/topics/code-and-programming/) · [Reasoning · 1 work](https://md.research.elamur.ai/free/en/topics/reasoning/) ## Works by year ### 2020s [**2026** 1 paper](https://md.research.elamur.ai/free/en/authors/manish-kumar/year/2026/) · [**2025** 1 paper](https://md.research.elamur.ai/free/en/authors/manish-kumar/year/2025/) · [**2023** 1 paper](https://md.research.elamur.ai/free/en/authors/manish-kumar/year/2023/) ## Papers The most cited first (OpenAlex and our library). 1. **[AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://md.research.elamur.ai/free/en/papers/novikov-2025-alphaevolve-coding-agent-scientific-algorithmic/)** *(2025 · 202 citations)* AlphaEvolve is a coding agent from Google DeepMind. It tests whether large language models can produce new discoveries, not just strong benchmark scores, on problems where a machine can check candidate answers. The user supplies three things: a working starting program with sections flagged for evolution, an… 2. **[Mathematical Discoveries from Program Search with Large Language Models](https://md.research.elamur.ai/free/en/papers/paredes-2023-mathematical-discoveries-program-search-large/)** *(2023 · 200 citations)* Large language models can write code, but they often produce answers that sound right and are wrong. That makes them hard to trust for new scientific results. The authors present FunSearch, an evolutionary loop that combines a frozen code LLM (Codey, built on PaLM2) with an automatic evaluator that scores each… 3. **[NIT-Agartala-NLP-Team at SemEval-2026 Task 9: A Weighted Soft-Voting Ensemble Framework of Fine-Tuned LLMs for Binary and Multi-Label Polarization Detection](https://md.research.elamur.ai/free/en/papers/shivam-2026-nit-agartala-nlp-team-semeval/)** *(2026)* The paper describes a system for SemEval-2026 Task 9, which targets polarization in online text. The task has two parts: deciding whether a post is polarized, and labeling polarized posts with one or more types (Political, Racial/Ethnic, Religious, Gender/Sexual, Others). The task corpus covers 22 languages, but the… ## All works 15 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them. 1. **[OBJ CUT ↗](https://doi.org/10.1109/cvpr.2005.249) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Manish Kumar, Philip H. S. Torr, Andrew Zisserman*2005 · 329 citations* 2. [**AlphaEvolve: A coding agent for scientific and algorithmic discovery arXiv:2506.13131**Alexander Novikov, Ngân Vũ, Marvin Eisenberger, et al.*2025 · 202 citations*](https://md.research.elamur.ai/free/en/papers/novikov-2025-alphaevolve-coding-agent-scientific-algorithmic/) 3. [**Mathematical Discoveries from Program Search with Large Language Models Nature 625**Bernardino Romera-Paredes, Mohammadamin Barekatain, Alexander Novikov, et al.*2023 · 200 citations*](https://md.research.elamur.ai/free/en/papers/paredes-2023-mathematical-discoveries-program-search-large/) 4. **[Efficient discriminative learning of parts-based models ↗](https://doi.org/10.1109/iccv.2009.5459192) IEEE International Conference on Computer Vision (ICCV) · no summary yet**Manish Kumar, Andrew Zisserman, Philip H. S. Torr*2009 · 84 citations* 5. **[OBJCUT: Efficient Segmentation Using Top-Down and Bottom-Up Cues ↗](https://doi.org/10.1109/tpami.2009.16) IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yet**Manish Kumar, P. Torr, Andrew Zisserman*82 citations* 6. **[Smooth Loss Functions for Deep Top-k Classification ↗](https://arxiv.org/abs/1802.07595) arXiv:1802.07595 · no summary yet**Leonard Berrada, Andrew Zisserman, M. Pawan Kumar*2018 · 73 citations* 7. **[An Invariant Large Margin Nearest Neighbour Classifier ↗](https://doi.org/10.1109/iccv.2007.4409041) IEEE International Conference on Computer Vision (ICCV) · no summary yet**Manish Kumar, Philip H. S. Torr, Andrew Zisserman*2007 · 45 citations* 8. **[Solving Markov Random Fields using Second Order Cone Programming Relaxations ↗](https://doi.org/10.1109/cvpr.2006.283) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Manish Kumar, Philip H. S. Torr, Andrew Zisserman*2006 · 37 citations* 9. **[Deep Frank-Wolfe For Neural Network Optimization ↗](https://arxiv.org/abs/1811.07591) arXiv (Cornell University) · no summary yet**Leonard Berrada, Andrew Zisserman, Manish Kumar*2018 · 22 citations* 10. **[Training Neural Networks for and by Interpolation ↗](https://openalex.org/W3035303608) International Conference on Machine Learning · no summary yet**Leonard Berrada, Manish Kumar, Andrew Zisserman*2020 · 11 citations* 11. **[Trusting SVM for Piecewise Linear CNNs ↗](https://arxiv.org/abs/1611.02185) arXiv (Cornell University) · no summary yet**Leonard Berrada, Andrew Zisserman, Manish Kumar*2016 · 10 citations* 12. **[Learning from M/EEG Data with Variable Brain Activation Delays ↗](https://doi.org/10.1007/978-3-642-38868-2_35) Lecture notes in computer science · no summary yet**Wojciech Zaremba et al.*2013 · 6 citations* 13. **[An Object Category Specific mrf for Segmentation ↗](https://doi.org/10.1007/11957959_30) Lecture notes in computer science · no summary yet**Manish Kumar, Philip H. S. Torr, Andrew Zisserman*2006 · 2 citations* 14. **[NIT-Agartala-NLP-Team at SemEval-2026 Task 9: A Weighted Soft-Voting Ensemble Framework of Fine-Tuned LLMs for Binary and Multi-Label Polarization Detection](https://md.research.elamur.ai/free/en/papers/shivam-2026-nit-agartala-nlp-team-semeval/) [International Workshop on Semantic Evaluation (SemEval)](https://md.research.elamur.ai/free/en/venues/semeval/)**Shivam, Manish Kumar, Anupam Jamatia*2026* 15. **[Comment on Stochastic Polyak Step-Size: Performance of ALI-G ↗](https://arxiv.org/abs/2105.10011) arXiv (Cornell University) · no summary yet**Leonard Berrada, Andrew Zisserman, Manish Kumar*2021* ## Co-authors here 6 co-authors with a page, the most papers together first. - [Alexander Novikov](https://md.research.elamur.ai/free/en/authors/alexander-novikov/) ×2 - [Emilien Dupont](https://md.research.elamur.ai/free/en/authors/emilien-dupont/) ×2 - [Francisco J. R. Ruiz](https://md.research.elamur.ai/free/en/authors/francisco-j-r-ruiz/) ×2 - [Abigail See](https://md.research.elamur.ai/free/en/authors/abigail-see/) - [Po-Sen Huang](https://md.research.elamur.ai/free/en/authors/po-sen-huang/) - [Pushmeet Kohli](https://md.research.elamur.ai/free/en/authors/pushmeet-kohli/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings ×2 - IEEE International Conference on Computer Vision (ICCV) ×2 - Lecture notes in computer science ×2 - [International Workshop on Semantic Evaluation (SemEval)](https://md.research.elamur.ai/free/en/venues/semeval/): [SemEval 2026](https://md.research.elamur.ai/free/en/venues/semeval/2026/) - IEEE Transactions on Pattern Analysis and Machine Intelligence - International Conference on Machine Learning - Nature 625 ## Cited by Papers of our library cite their works 408 times (of the 149,439 papers whose bibliographies we read); [36 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/manish-kumar/cited-by/). Updated 1 November 2026