Manish Kumar
Manish Kumar has 3 papers in our library, in 2023–2026, most of them on Reasoning, Code & programming languages; often with Alexander Novikov, Emilien Dupont, Francisco J. R. Ruiz.
OpenAlex · ORCID · h-index 36 · 439 works · 6,832 citations OpenAlex, 2026-10-14
📄 3 works in our library · 🔗 Cited 408 times in our library · 12 more in our library without a page yet · ⭐ Paper Stars ranking: #4352
Affiliations
Fields, topics and concepts
📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 3 worksArtificial Intelligence · 2 worksInformation Systems · 1 workArts and Humanities · 1 workLanguage and Linguistics · 1 work
🧭 Topics 2Research subjects and languages the work is about.Code & programming languages · 1 workReasoning · 1 work
Works by year
2020s
Papers
- AlphaEvolve: A coding agent for scientific and algorithmic discovery (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… - Mathematical Discoveries from Program Search with Large Language Models (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… - 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 (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
- OBJ CUT ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetManish Kumar, Philip H. S. Torr, Andrew Zisserman2005 · 329 citations
- AlphaEvolve: A coding agent for scientific and algorithmic discoveryarXiv:2506.13131Alexander Novikov, Ngân Vũ, Marvin Eisenberger, et al.2025 · 202 citations
- Mathematical Discoveries from Program Search with Large Language ModelsNature 625Bernardino Romera-Paredes, Mohammadamin Barekatain, Alexander Novikov, et al.2023 · 200 citations
- Efficient discriminative learning of parts-based models ↗IEEE International Conference on Computer Vision (ICCV) · no summary yetManish Kumar, Andrew Zisserman, Philip H. S. Torr2009 · 84 citations
- OBJCUT: Efficient Segmentation Using Top-Down and Bottom-Up Cues ↗IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yetManish Kumar, P. Torr, Andrew Zisserman82 citations
- Smooth Loss Functions for Deep Top-k Classification ↗arXiv:1802.07595 · no summary yetLeonard Berrada, Andrew Zisserman, M. Pawan Kumar2018 · 73 citations
- An Invariant Large Margin Nearest Neighbour Classifier ↗IEEE International Conference on Computer Vision (ICCV) · no summary yetManish Kumar, Philip H. S. Torr, Andrew Zisserman2007 · 45 citations
- Solving Markov Random Fields using Second Order Cone Programming Relaxations ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetManish Kumar, Philip H. S. Torr, Andrew Zisserman2006 · 37 citations
- Deep Frank-Wolfe For Neural Network Optimization ↗arXiv (Cornell University) · no summary yetLeonard Berrada, Andrew Zisserman, Manish Kumar2018 · 22 citations
- Training Neural Networks for and by Interpolation ↗International Conference on Machine Learning · no summary yetLeonard Berrada, Manish Kumar, Andrew Zisserman2020 · 11 citations
- Trusting SVM for Piecewise Linear CNNs ↗arXiv (Cornell University) · no summary yetLeonard Berrada, Andrew Zisserman, Manish Kumar2016 · 10 citations
- Learning from M/EEG Data with Variable Brain Activation Delays ↗Lecture notes in computer science · no summary yetWojciech Zaremba et al.2013 · 6 citations
- An Object Category Specific mrf for Segmentation ↗Lecture notes in computer science · no summary yetManish Kumar, Philip H. S. Torr, Andrew Zisserman2006 · 2 citations
- Comment on Stochastic Polyak Step-Size: Performance of ALI-G ↗arXiv (Cornell University) · no summary yetLeonard Berrada, Andrew Zisserman, Manish Kumar2021
Co-authors here
Venues
- 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): SemEval 2026
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- International Conference on Machine Learning
- Nature 625
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/manish-kumar/