Issam H. Laradji
Research Manager
AI Frontier Research
Issam Laradji is a research scientist at ServiceNow Research who focuses on methods that minimize the amount of labels required to efficiently train machine learning models. He completed his postdoc at McGill’s Graphics lab and completed his PhD at the Machine Learning lab of University of British Columbia. His current topics of interest are natural language processing, computer vision (both 2D and 3D), and optimization. On the side, he continuously works on Haven-AI, a toolkit to help people build end-to-end deep learning methods and manage large-scale experiments.
Intérêts
- Low Supervision
- Summarization
- Text Classification
- Optimization
Publications
AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery.
Workshop at the Annual Meeting of the Association for Computational Linguistics (ACL),
2025.
StarVector: Generating Scalable Vector Graphics Code from Images and Text.
Computer Vision and Pattern Recognition (CVPR),
2025.
Fast Convergence of Softmax Policy Mirror Ascent.
International Conference on Artificial Intelligence and Statistics (AISTATS),
2025.
A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches.
North American Chapter of the Association for Computational Linguistics (NAACL),
2025.
AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding.
Workshop at the International Conference of Learning Representation (ICLR),
2025.
BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks.
International Conference of Learning Representations (ICLR),
2025.
InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation.
International Conference of Learning Representations (ICLR),
2025.
LitLLMs, LLMs for Literature Review: Are We There Yet?.
Transactions on Machine Learning Research (TMLR),
2025.
StarVector: Generating Scalable Vector Graphics Code from Images and Text.
AAAI Demos,
2025.
BigDocs: A Permissively-Licensed Dataset for Training Vision-Language Models on Document and Code Tasks.
Workshop at the Neural Information Processing Systems (NeurIPS),
2024.
BlockLLM: Memory-Efficient Adaptation of LLMs by Selecting and Optimizing the Right Coordinate Blocks.
Workshop at the Neural Information Processing Systems (NeurIPS),
2024.
Fast Convergence of Softmax Policy Mirror Ascent for Bandits & Tabular MDPs.
Workshop at the Neural Information Processing Systems (NeurIPS),
2024.
WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?.
International Conference on Machine Learning (ICML),
2024.
IntentGPT: Few-shot Intent Discovery with Large Language Models.
Workshop at the International Conference of Learning Representation (ICLR),
2024.
WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?.
Workshop at the International Conference of Learning Representation (ICLR),
2024.
Workflow discovery in low data regimes.
International Conference of Learning Representations (ICLR),
2024.
Automatic Data Augmentation Learning using Bilevel Optimization for Histopathological Images.
ArXiv,
2024.
FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering.
ArXiv,
2024.
Language Decision Transformers with Exponential Tilt for Interactive Text Environments.
ArXiv,
2024.
LitLLM: A Toolkit for Scientific Literature Review.
ArXiv,
2024.
MixSumm: Topic-based Data Augmentation using LLMs for Low-resource Extractive Text Summarization.
ArXiv,
2024.
Capture the Flag: Uncovering Data Insights with Large Language Models.
Workshop at the Neural Information Processing Systems (NeurIPS),
2023.
Surrogate Minimization: An Optimization Algorithm for Training Large Neural Networks with Model Parallelism.
Workshop at the Neural Information Processing Systems (NeurIPS),
2023.
The Unsolved Challenges of LLMs in Open-Ended Web Tasks: A Case Study.
Workshop at the Neural Information Processing Systems (NeurIPS),
2023.
LLM aided semi-supervision for efficient Extractive Dialog Summarization.
Conference on Empirical Methods in Natural Language Processing (EMNLP),
2023.
PromptMix: A Class Boundary Augmentation Method for Large Language Model Distillation.
Conference on Empirical Methods in Natural Language Processing (EMNLP),
2023.
TK-KNN: A Balanced Distance-Based Pseudo Labeling Approach for Semi-Supervised Intent Classification.
Conference on Empirical Methods in Natural Language Processing (EMNLP),
2023.
On Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants.
Transactions on Machine Learning Research (TMLR),
2023.
Workflow discovery in low data regimes.
Workshop at the International Conference on Machine Learning (ICML),
2023.
Let's Make Block Coordinate Descent Converge Faster: Faster Greedy Rules, Message-Passing, Active-Set Complexity, and Superlinear Convergence.
International Conference on Machine Learning (ICML),
2023.
Affinity Learning With Blind-spot Self-supervision for Image Denoising.
International Conference on Acoustics, Speech and Signal Processing (ICASSP),
2023.
Constraining Representations Yields Models That Know What They Don't Know.
International Conference of Learning Representations (ICLR),
2023.
FigGen: Text to Scientific Figure Generation.
International Conference of Learning Representations (ICLR),
2023.
Workflow discovery in low data regimes.
Transactions on Machine Learning Research,
2023.
OCR-VQGAN: Taming Text-within-Image Generation.
Winter Conference on Applications of Computer Vision (WACV),
2023.
Constraining Low-level Representations to Define Effective Confidence Scores.
Workshop at the Neural Information Processing Systems (NeurIPS),
2022.
Consistency-CAM: Towards Improved Weakly Supervised Semantic Segmentation.
British Machine Vision Conference (BMVC),
2022.
OSM: An Open Set Matting Framework with OOD Detection and Few-Shot Learning.
British Machine Vision Conference (BMVC),
2022.
Countering Language Drift with KL Regularization.
Workshop on Interactive Learning for Natural Language Processing (NeurIPS Workshop),
2022.
Data Augmentation for Intent Classification with Off-the-shelf Large Language Models.
Montreal AI Symposium (MAIS),
2022.
Leveraging Activation Patterns to Define Classifiers Able to Detect and Reject Anomalies.
Montreal AI Symposium (MAIS),
2022.
S-LLM: Semi-Supervised Large Language Model for Chat Summarization.
Montreal AI Symposium (MAIS),
2022.
Competition exacerbates Language Drift.
Machine Learning and the Evolution of Language (JCoLE Workshop),
2022.
Overcoming challenges in leveraging GANs for few-shot data augmentation.
Workshop at the Conference on Lifelong Learning Agents (CoLLAs),
2022.
Kubric: A scalable dataset generator.
Computer Vision and Pattern Recognition (CVPR),
2022.
Neural Point Light Fields.
Computer Vision and Pattern Recognition (CVPR),
2022.
Data Augmentation for Intent Classification with Off-the-shelf Large Language Models.
Workshop at the Annual Meetings of the Association for Computational Linguistics (ACL),
2022.
Let's Make Block Coordinate Descent Converge Faster: Faster Greedy Rules, Message-Passing, Active-Set Complexity, and Superlinear Convergence.
Journal of Machine Learning Research (JMLR),
2022.
A Soft Labeling Approach to Develop Automated Algorithms that Incorporate Uncertainty in Pulmonary Opacification on Chest CT using COVID-19 Pneumonia.
Academic Radiology,
2022.
A Survey of Self-Supervised and Few-Shot Object Detection.
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI),
2021.
A Deep Learning Localization Method for Measuring Abdominal Muscle Dimensions in Ultrasound Images.
IEEE Journal of Biomedical and Health Informatics,
2021.
Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations.
International Conference on Computer Vision (ICCV),
2021.
SSR: Semi-supervised Soft Rasterizer for single-view 2D to 3D Reconstruction.
Workshop at the International Conference on Computer Vision (ICCV),
2021.
Weakly Supervised Underwater Fish Segmentation Using Affinity LCFCN.
Nature Scientific Reports,
2021.
Stochastic polyak step-size for sgd: An adaptive learning rate for fast convergence.
International Conference on Artificial Intelligence and Statistics (AISTATS),
2021.
A Weakly Supervised Consistency-based Learning Method for COVID-19 Segmentation in CT Images.
Winter Conference on Applications of Computer Vision (WACV),
2021.
Learning Data Augmentation with Online Bilevel Optimization for Image Classification.
Winter Conference on Applications of Computer Vision (WACV),
2021.
Counting Cows: Tracking Illegal Cattle Ranching From High-Resolution Satellite Imagery.
Workshop at the Neural Information Processing Systems (NeurIPS),
2020.
Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning.
Conference on Neural Information Processing Systems (NeurIPS),
2020.
Synbols: Probing Learning Algorithms with Synthetic Datasets.
Conference on Neural Information Processing Systems (NeurIPS),
2020.
LOOC: Localize Overlapping Objects with Count Supervision.
International Conference on Image Processing (ICIP),
2020.
Proposal-based Instance Segmentation with Point Supervision.
International Conference on Image Processing (ICIP),
2020.
CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions.
Artificial Intelligence Journal,
2020.
Embedding Propagation: Smoother Manifold for Few-Shot Classification.
European Conference on Computer Vision (ECCV),
2020.
Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning.
Workshop at the Conference on Computer Vision and Pattern Recognition (CVPR),
2020.
Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation.
International Conference on Artificial Intelligence and Statistics (AISTATS),
2020.
A realistic fish-habitat dataset to evaluate algorithms for underwater visual analysis.
Nature Scientific Reports,
2020.
Class-Based Styling: Real-time Localized Style Transfer with Semantic Segmentation.
Women in Machine Learning (WiML),
2019.
Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates.
Conference on Neural Information Processing Systems (NeurIPS),
2019.
Class-Based Styling: Real-time Localized Style Transfer with Semantic Segmentation.
Workshop at the International Conference on Computer Vision (ICCV),
2019.
Where are the Masks: Instance Segmentation with Image-level Supervision.
Britsh Machine Vision Conference (BMVC),
2019.
Efficient Deep Gaussian Process Models for Variable-Sized Inputs.
International Joint Conference on Neural Networks (IJCNN),
2019.
Where are the Blobs: Counting by Localization with Point Supervision.
European Conference on Computer Vision (ECCV),
2018.
Synbols: Probing Learning Algorithms with Synthetic Datasets.
Montreal AI Symposium (MAIS),
2018.
Class-Based Styling: Real-time Localized Style Transfer with Semantic Segmentation.
Workshop at the International Conference on Learning Representations (ICLR),
2018.