🧑‍🔬 Leonid Karlinsky

🏛️ Affiliations

🏢IBMArmonk · United States2017–2025 · 68 papers🎓Massachusetts Institute of TechnologyCambridge · United States2020–2025 · 26 papers🔬IBM Research - HaifaHaifa · Israel2016–2023 · 8 papers🎓Weizmann Institute of ScienceRehovot · Israel2008–2012 · 6 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. NumeroLogic: Number Encoding for Enhanced LLMs' Numerical Reasoning (2024 · 26 citations)
   Causal LLMs read numbers left to right, so a digit's place value only becomes clear once the whole number has been seen.
2. REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark (2025 · 22 citations)
   Existing benchmarks for multi-modal document retrieval in RAG do not reflect how retrieval works in practice.

All works

21 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. RepMet: Representative-Based Metric Learning for Classification and Few-Shot Object Detection ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetLeonid Karlinsky et al.2019 · 387 citations
2. CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJames Seale Smith et al.2023 · 352 citations
3. LaSO: Label-Set Operations Networks for Multi-Label Few-Shot Learning ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetAmit Alfassy et al.2019 · 125 citations
4. Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning ↗arXiv (Cornell University) · no summary yetZhen Wang et al.2023 · 77 citations
5. Fine-Grained Recognition of Thousands of Object Categories with Single-Example Training ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetLeonid Karlinsky et al.2017 · 72 citations
6. Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs ↗Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · no summary yetRoei Herzig et al.2023 · 31 citations
7. Learning to Grow Pretrained Models for Efficient Transformer Training ↗arXiv (Cornell University) · no summary yetPeihao Wang et al.2023 · 28 citations
8. NumeroLogic: Number Encoding for Enhanced LLMs' Numerical ReasoningConference on Empirical Methods in Natural Language Processing (EMNLP)Eli Schwartz, Leshem Choshen, Joseph Shtok, et al.2024 · 26 citations
9. REAL-MM-RAG: A Real-World Multi-Modal Retrieval BenchmarkAnnual Meeting of the Association for Computational Linguistics (ACL)Navve Wasserman, Roi Pony, Oshri Naparstek, et al.2025 · 22 citations
10. ConStruct-VL: Data-Free Continual Structured VL Concepts Learning* ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJames Seale Smith et al.2023 · 18 citations
11. Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning ↗neural information processing systems · no summary yetBrandon Huang et al.2024 · 17 citations
12. Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens ↗arXiv (Cornell University) · no summary yetElad Ben Avraham et al.2022 · 16 citations
13. PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data ↗IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · no summary yetRoei Herzig et al.2022 · 10 citations
14. ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs ↗neural information processing systems · no summary yetIrene Huang et al.2024 · 6 citations
15. Enhancing Few-Shot Vision-Language Classification With Large Multimodal Model Features ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetChancharik Mitra et al.2025 · 5 citations
16. Navigating the Labyrinth: Evaluating LLMs' Ability to Reason About Search Problems ↗arXiv (Cornell University) · no summary yetNasim Borazjanizadeh et al.2024 · 5 citations
17. Activation Reward Models for Few-Shot Model Alignment ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetTianning Chai et al.2026 · 2 citations
18. Visualizing Thought: Conceptual Diagrams Enable Robust Planning in LMMs ↗arXiv (Cornell University) · no summary yetNasim Borazjanizadeh et al.2025 · 1 citation
19. Latent Implicit Visual Reasoning ↗arXiv (Cornell University) · no summary yetKelvin Zhenghao Li et al.2025 · 1 citation
20. Structured Video Tokens @ Ego4D PNR Temporal Localization Challenge 2022 ↗arXiv (Cornell University) · no summary yetElad Ben Avraham et al.2022 · 1 citation
21. Discriminative World Models for Web Agents ↗arXiv (Cornell University) · no summary yetKelvin Li et al.2026

🤝 Co-authors here

2 co-authors with a page, the most papers together first.

• Eli Schwartz ×2
• Leshem Choshen

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 ×5
• Conference on Empirical Methods in Natural Language Processing (EMNLP) ×2: EMNLP 2024
• neural information processing systems ×2
• Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2025
• Findings of the Association for Computational Linguistics: ACL 2026
• IEEE/CVF International Conference on Computer Vision (ICCV)
• IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

🔗 Cited by

Papers of our library cite their works 165 times (of the 149,439 papers whose bibliographies we read); 31 citing papers with a page here →.

Updated 3 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/leonid-karlinsky/