Leonid Karlinsky

IBM (United States) — United States

Computer Science · Physical Sciences

28h-index3.2kcitations146works2.72yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Domain Adaptation and Few-Shot Learning(61), Multimodal Machine Learning Applications(53), Advanced Neural Network Applications(28), Advanced Image and Video Retrieval Techniques(20), Topic Modeling(18)

Publications146 total

Latent Implicit Visual Reasoning
arXiv (Cornell University)·2025Open Access
Latent Implicit Visual Reasoning
ArXiv.org·2025Open Access
Activation Reward Models for Few-Shot Model Alignment
arXiv (Cornell University)·2025Open Access
Comparison Visual Instruction Tuning
2025
Sample- and Parameter-Efficient Auto-Regressive Image Models
2025
CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment
2025· 1 cited
Overflow Prevention Enhances Long-Context Recurrent LLMs
arXiv (Cornell University)·2025Open Access
CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment
arXiv (Cornell University)·2025Open Access
Visualizing Thought: Conceptual Diagrams Enable Robust Planning in LMMs
arXiv (Cornell University)·2025Open Access
REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark
arXiv (Cornell University)·2025Open Access
Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence
arXiv (Cornell University)·2025· 1 citedOpen Access
Towards Multimodal In-context Learning for Vision and Language Models
Lecture notes in computer science·2025· 4 cited
3VL: Using Trees to Improve Vision-Language Models’ Interpretability
IEEE Transactions on Image Processing·2025· 1 cited
REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark
2025· 1 citedOpen Access
$\texttt{BATCLIP}$: Bimodal Online Test-Time Adaptation for CLIP
arXiv (Cornell University)·2024· 1 citedOpen Access
DASS: Distilled Audio State Space Models are Stronger and More Duration-Scalable Learners
2024· 2 cited
Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features
arXiv (Cornell University)·2024Open Access
State-Space Large Audio Language Models
arXiv (Cornell University)·2024Open Access
Sample- and Parameter-Efficient Auto-Regressive Image Models
arXiv (Cornell University)·2024Open Access
Teaching VLMs to Localize Specific Objects from In-context Examples
arXiv (Cornell University)·2024Open Access
page 1 of 8Next →

Frequent Co-authors

Rogério Feris(32), Rameswar Panda(15), Raja Giryes(12), Eli Schwartz(11), Sivan Harary(10), Joseph Shtok(8), Assaf Arbelle(8), Alex Bronstein(7), Kate Saenko(7), Prasanna Sattigeri(6), James Glass(6), Sivan Doveh(6), Shimon Ullman(5), Hilde Kuehne(5), James Smith(4), Paola Cascante-Bonilla(4), Donghyun Kim(4), Aude Oliva(4), Ayelet Akselrod-Ballin(4), Amit Alfassy(4)