Radu Soricut
Artificial Intelligence · 2003–2025
A researcher in the Science corpus: 24 papers; trusts 2,325 researchers and is trusted by 2,924 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 678 citations into it; #1,446 of 36,961 by trust here, #860 by citations
- Computer Vision and Pattern Recognition — 551 citations into it; #989 of 21,973 by trust here, #533 by citations
- Natural Language Processing — 309 citations into it; #1,097 of 5,725 by trust here, #703 by citations
- Multimodal Learning — 222 citations into it; #68 of 1,215 by trust here, #103 by citations
- Evaluation & Benchmarks — 187 citations into it; #238 of 3,155 by trust here, #252 by citations
- Large Language Models — 73 citations into it; #146 of 810 by trust here, #123 by citations
- Representation & Self-Supervised Learning — 73 citations into it
- Model Architectures — 61 citations into it
Whom Radu Soricut trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Geoffrey E. Hinton
- Kaiming He
- Diederik P. Kingma
- Alex Krizhevsky
- Ilya Sutskever
- Tomas Mikolov
- Richard Socher
- Yann LeCun
- Oriol Vinyals
Who trusts Radu Soricut overall
- Soravit Changpinyo
- Zhe Gan
- Regina Barzilay
- Greg Durrett
- Christian Stab
- John Lawrence
- Kim Schouten
- Jianfeng Wang
- Junnan Li
- Anna Rogers
Papers from Radu Soricut's perspective
Ordered by how strongly the researchers Radu Soricut trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning (2018) — 3,041 citations
- ALBERT: A Lite BERT for Self-supervised Learning of Language Representations (2019) — 7,601 citations
- Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts (2021) — 1,502 citations
- PaLI: A Jointly-Scaled Multilingual Language-Image Model (2022) — 1,015 citations
- Findings of the 2014 Workshop on Statistical Machine Translation (2014) — 850 citations
- Connecting Vision and Language with Localized Narratives (2019) — 310 citations
- PaLI-X: On Scaling up a Multilingual Vision and Language Model (2023) — 301 citations
- All You May Need for VQA are Image Captions (2022) — 93 citations
- Findings of the 2012 Workshop on Statistical Machine Translation (2012) — 377 citations
- Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering (2019) — 20 citations
- A Case Study on Combining ASR and Visual Features for Generating Instructional Video Captions (2019) — 40 citations
- Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting (2022) — 295 citations
- Cold-Start Reinforcement Learning with Softmax Policy Gradient (2017) — 47 citations
- Sentence Level Discourse Parsing using Syntactic and Lexical Information (2003) — 488 citations
- Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context (2024) — 3,818 citations
- Beyond Instructional Videos: Probing for More Diverse Visual-Textual Grounding on YouTube (2020) — 4 citations
- Unsupervised Morphology Induction Using Word Embeddings (2015) — 153 citations
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025) — 3,609 citations
- Gemini Robotics: Bringing AI into the Physical World (2025) — 385 citations
- PaliGemma: A versatile 3B VLM for transfer (2024) — 728 citations