LK
Leonid Karlinsky
cs.CVcs.LGcs.AIcs.CLeess.AScs.SDcs.MMstat.MLcs.HCcs.IR
On Valency
published · living versionsW_5sy9upy2·v1 · currentpublished
Discriminative World Models for Web Agents
with Kelvin Li, Dhruv Pendharkar, Anish Pahilajani, Chuyi Shang +4
1 version
Preprints & journals
84 papers in the corpus · 2018–2026Architectural Sampling: Test-Time Scaling via Computational Diversity in Frozen Vision-Language Models2610.01687v1 · Akshit Singh, Shyam Marjit, Wei Lin et al.2026 · 0 citationsarXiv
Discriminative World Models for Web Agents2609.02885v1 · Kelvin Li, Dhruv Pendharkar, Anish Pahilajani et al.2026 · 0 citationsarXivon Valency
Latent Implicit Visual Reasoning2512.21218v2 · Kelvin Li, Chuyi Shang, Leonid Karlinsky et al.2025 · 0 citationsarXiv
Activation Reward Models for Few-Shot Model Alignment2507.01368v1 · Tianning Chai, Chancharik Mitra, Brandon Huang et al.2025 · 0 citationsarXiv
ChartGen: Scaling Chart Understanding Via Code-Guided Synthetic Chart Generation2507.19492v1 · Jovana Kondic, Pengyuan Li, Dhiraj Joshi et al.2025 · 0 citationsarXiv
Instructify: Demystifying Metadata to Visual Instruction Tuning Data Conversion2505.18115v1 · Jacob Hansen, Wei Lin, Junmo Kang et al.2025 · 0 citationsarXiv
Overflow Prevention Enhances Long-Context Recurrent LLMs2505.07793v2 · Assaf Ben-Kish, Itamar Zimerman, M. Jehanzeb Mirza et al.2025 · 0 citationsarXiv
CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment2505.01237v2 · Edson Araujo, Andrew Rouditchenko, Yuan Gong et al.2025 · 8 citationsarXiv
Visualizing Thought: Conceptual Diagrams Enable Robust Planning in LMMs2503.11790v3 · Nasim Borazjanizadeh, Roei Herzig, Eduard Oks et al.2025 · 0 citationsarXiv
REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark2502.12342v1 · Navve Wasserman, Roi Pony, Oshri Naparstek et al.2025 · 5 citationsarXiv
3VL: Using Trees to Improve Vision-Language Models' Interpretability.40030875 · Yellinek, Nir, Karlinsky, Leonid, Giryes, Raja2025 · 4 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2025;PP
: Bimodal Online Test-Time Adaptation for CLIP2412.02837v3 · Sarthak Kumar Maharana, Baoming Zhang, Leonid Karlinsky et al.2024 · 1 citationarXiv
Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features2412.00142v3 · Chancharik Mitra, Brandon Huang, Tianning Chai et al.2024 · 2 citationsarXiv
State-Space Large Audio Language Models2411.15685v1 · Saurabhchand Bhati, Yuan Gong, Leonid Karlinsky et al.2024 · 1 citationarXiv
Sample- and Parameter-Efficient Auto-Regressive Image Models2411.15648v2 · Elad Amrani, Leonid Karlinsky, Alex Bronstein2024 · 0 citationsarXiv
Teaching VLMs to Localize Specific Objects from In-context Examples2411.13317v2 · Sivan Doveh, Nimrod Shabtay, Wei Lin et al.2024 · 3 citationsarXiv
LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content2410.10783v4 · Nimrod Shabtay, Felipe Maia Polo, Sivan Doveh et al.2024 · 0 citationsarXiv
GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models2410.06154v6 · M. Jehanzeb Mirza, Mengjie Zhao, Zhuoyuan Mao et al.2024 · 1 citationarXiv
Scaling Granite Code Models to 128K Context2407.13739v1 · Matt Stallone, Vaibhav Saxena, Leonid Karlinsky et al.2024 · 1 citationarXiv
DASS: Distilled Audio State Space Models Are Stronger and More Duration-Scalable Learners2407.04082v2 · Saurabhchand Bhati, Yuan Gong, Leonid Karlinsky et al.2024 · 6 citationsarXiv
Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning2406.15334v3 · Brandon Huang, Chancharik Mitra, Assaf Arbelle et al.2024 · 6 citationsarXiv
Navigating the Labyrinth: Evaluating LLMs' Ability to Reason About Search Problems2406.12172v3 · Nasim Borazjanizadeh, Roei Herzig, Trevor Darrell et al.2024 · 1 citationarXiv
Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts2406.12034v2 · Junmo Kang, Leonid Karlinsky, Hongyin Luo et al.2024 · 3 citationsarXiv
Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation2406.10082v3 · Andrew Rouditchenko, Yuan Gong, Samuel Thomas et al.2024 · 29 citationsarXiv
Comparison Visual Instruction Tuning2406.09240v1 · Wei Lin, Muhammad Jehanzeb Mirza, Sivan Doveh et al.2024 · 1 citationarXiv
ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs2406.08164v3 · Irene Huang, Wei Lin, M. Jehanzeb Mirza et al.2024 · 4 citationsarXiv
: towards data-free Transferable Parameter Efficient Finetuning2405.17258v1 · Runqian Wang, Soumya Ghosh, David Cox et al.2024 · 0 citationsarXiv
Adaptive Memory Replay for Continual Learning2404.12526v1 · James Seale Smith, Lazar Valkov, Shaunak Halbe et al.2024 · 27 citationsarXiv
NumeroLogic: Number Encoding for Enhanced LLMs' Numerical Reasoning2404.00459v2 · Eli Schwartz, Leshem Choshen, Joseph Shtok et al.2024 · 14 citationsarXiv
Towards Multimodal In-Context Learning for Vision & Language Models2403.12736v2 · Sivan Doveh, Shaked Perek, M. Jehanzeb Mirza et al.2024 · 2 citationsarXiv
Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs2403.11755v3 · M. Jehanzeb Mirza, Leonid Karlinsky, Wei Lin et al.2024 · 15 citationsarXiv
CAMELoT: Towards Large Language Models with Training-Free Consolidated Associative Memory2402.13449v1 · Zexue He, Leonid Karlinsky, Donghyun Kim et al.2024 · 0 citationsarXiv
Large Scale Generative AI Text Applied to Sports and Music2402.15514v2 · Aaron Baughman, Stephen Hammer, Rahul Agarwal et al.2024 · 13 citationsarXiv
Learning Human Action Recognition Representations Without Real Humans2311.06231v1 · Howard Zhong, Samarth Mishra, Donghyun Kim et al.2023 · 1 citationarXiv
GeRA: Label-Efficient Geometrically Regularized Alignment2310.00672v2 · Dustin Klebe, Tal Shnitzer, Mikhail Yurochkin et al.2023 · 0 citationsarXiv
Self-Specialization: Uncovering Latent Expertise within Large Language Models2310.00160v2 · Junmo Kang, Hongyin Luo, Yada Zhu et al.2023 · 2 citationsarXiv
Joint Audio and Speech Understanding2309.14405v3 · Yuan Gong, Alexander H. Liu, Hongyin Luo et al.2023 · 48 citationsarXiv
TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification2309.06809v1 · M. Jehanzeb Mirza, Leonid Karlinsky, Wei Lin et al.2023 · 0 citationsarXiv
Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers2307.03183v1 · Yuan Gong, Sameer Khurana, Leonid Karlinsky et al.2023 · 65 citationsProceedings of Interspeech 2023
Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models2305.19595v2 · Sivan Doveh, Assaf Arbelle, Sivan Harary et al.2023 · 20 citationsarXiv
LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections2305.18287v2 · M. Jehanzeb Mirza, Leonid Karlinsky, Wei Lin et al.2023 · 17 citationsarXiv
Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languages2305.12606v2 · Andrew Rouditchenko, Sameer Khurana, Samuel Thomas et al.2023 · 14 citationsarXiv
Listen, Think, and Understand2305.10790v3 · Yuan Gong, Hongyin Luo, Alexander H. Liu et al.2023 · 43 citationsarXiv
Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs2305.06343v2 · Roei Herzig, Alon Mendelson, Leonid Karlinsky et al.2023 · 20 citationsarXiv
Constructive Assimilation: Boosting Contrastive Learning Performance through View Generation Strategies2304.00601v2 · Ligong Han, Seungwook Han, Shivchander Sudalairaj et al.2023 · 1 citationarXiv
Going Beyond Nouns With Vision & Language Models Using Synthetic Data2303.17590v2 · Paola Cascante-Bonilla, Khaled Shehada, James Seale Smith et al.2023 · 33 citationsarXiv
MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge2303.08914v2 · Wei Lin, Leonid Karlinsky, Nina Shvetsova et al.2023 · 37 citationsarXiv
Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning2303.02861v1 · Zhen Wang, Rameswar Panda, Leonid Karlinsky et al.2023 · 42 citationsarXiv
Learning to Grow Pretrained Models for Efficient Transformer Training2303.00980v1 · Peihao Wang, Rameswar Panda, Lucas Torroba Hennigen et al.2023 · 18 citationsarXiv
PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data2212.04821v3 · Roei Herzig, Ofir Abramovich, Elad Ben-Avraham et al.2022 · 10 citationsarXiv
Career total: 118 works. 84 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.