Portrait of Laurent Charlin

Laurent Charlin

Core Academic Member
Canada CIFAR AI Chair
Associate Professor, HEC Montréal
Associate Professor, Université de Montréal, Department of Computer Science and Operations Research
Research Topics
AI for Science
Data Mining
Deep Learning
Generative Models
Graph Neural Networks
Information Retrieval
Natural Language Processing
Probabilistic Models
Recommender Systems
Reinforcement Learning
Representation Learning

Biography

Laurent Charlin is a Canada CIFAR AI Chair at Mila and an associate professor at HEC, the business school affiliated with the University de Montréal. He is also a core member of Mila—Quebec Institute for Artificial Intelligence.

Charlin’s research focuses on developing novel machine learning models to aid in decision-making. Recent work has focused on learning from data that changes over time, and on applications in fields such as recommender systems and optimization.

He has a number of highly cited publications on dialogue systems (chatbots). He co-developed the Toronto Paper Matching System (TPMS), which has been widely used by computer science conferences for matching reviewers to papers. He has also given MOOCs, introductory talks and media interviews to contribute to knowledge transfer and improve AI literacy.

Current Students

Master's Research - HEC Montréal
PhD - Université de Montréal
Co-supervisor :
Master's Research - HEC Montréal
PhD - HEC Montréal
Principal supervisor :
PhD - Université Laval
Principal supervisor :
PhD - Université de Montréal
Co-supervisor :
Master's Research - Université de Montréal
PhD - Concordia University
Principal supervisor :
Collaborating Alumni - Université de Montréal
Postdoctorate - HEC Montréal
Co-supervisor :
PhD - Université de Montréal
PhD - Université de Montréal

Publications

Active Learning of Robust Models
In many domains from species identification to cancer diagnosis, labelling data to train predictive models remains costly. In these settings… (see more), it is advantageous to intelligently select data points to label to achieve the maximum information gain, this is the motivation behind the study of active learning. In addition to the high costs of acquiring data in such domains, there is the added complexity of data distribution shifts that can occur between training and deployment. For example, the features of cancerous skin cells taken in one country may be different in another region of the world. These two challenges - efficient labelling of data, and learning models robust to distribution shifts have been studied separately but not together, even though these challenges often co-occur in real-life settings. We identify failure modes of standard active learning approaches when the distribution of data at deployment is different from the distribution in which the data is sampled for labelling. We propose a new strategy for efficiently learning classifiers that generalise under specific forms of distribution shift, namely subpopulation shift. Drawing on work in learning from heterogeneous data, we aim to train models that perform well across subpopulations of the data, through active learning. To handle this challenging setting, we exploit the fact that many datasets include metadata about data collection that can serve as a noisy proxy for each sample's underlying subpopulation. We demonstrate how to leverage these noisy labels during active learning selection, and demonstrate empirically that our approach improves classifier accuracy across subpopulations.
On the Limits of Test-Time Compute for Self-Evaluation
Self-verification and aggregation have emerged as popular approaches for bridging the gap between pass@1 and pass@N. However, increasing the… (see more) number of candidates does not consistently narrow the gap between final-answer accuracy and pass@N. To understand this limitation, we use ranking error to measure how reliably models distinguish their correct generations from incorrect ones. We show that ranking error admits a bias-variance decomposition, with both components shaped by algorithmic design choices and inference compute. Across our experiments, additional compute reduces variance, while bias initially decreases before approaching a plateau. Guided by this analysis, we introduce Scorpio, a simple and general method that jointly scores randomly grouped candidates. Across math, code, and puzzle benchmarks, Scorpio improves verification, tree search, and aggregation. For verification, Scorpio improves accuracy over the strongest baseline by up to 7 percentage points while matching or exceeding that baseline's peak accuracy with 17-42% lower inference cost. For tree search, using Scorpio to score partial solutions and select the final answer improves accuracy by up to 10 percentage points over prior methods. Finally, Scorpio improves the scaling of aggregation-based methods by 11 percentage points on coding tasks.
KV-streams for Efficient Compaction in Agentic Reinforcement Learning
Roger Creus Castanyer
Jonathan Light
Matthew J. Sargent
Augustine N. Mavor-Parker
M. Caccia
Lucas Caccia
Esmeralda S. Whitammer
Minseon Kim
Scaling the horizon of agentic LLMs is bottlenecked by the need to fit ever longer context traces in GPU memory. Context compaction has been… (see more) the most popular mechanism to alleviate this issue, keeping GPU memory constant for a given trace. Unfortunately, most compaction strategies rely on prefilling the LLM context many times over, hindering training throughput. To alleviate this bottleneck and enable efficient trainable compaction, we propose KV-streams, a plug-and-play strategy compatible with any compaction strategy that substantially increases throughput while showing no evidence of hindering performance. KV-streams enable scalable compaction by streaming the KV cache forward rather than flushing it after each compaction. We show that KV-streams enable three different compaction strategies, achieving a 2.6 to 5x wall-clock speedup in training. Beyond efficiency, we find that the streamed KV cache can act as a recurrent state, carrying forward information that has long since disappeared from the context. Specifically, in a controlled setting we show that, contrary to prior work, RL alone is all that is needed for this behavior to emerge. Overall, we show KV-streams to be an efficient and lightweight plug-and-play addition to any post-training pipeline.
KV-streams for Efficient Compaction in Agentic Reinforcement Learning
Roger Creus Castanyer
Jonathan Light
Matthew J. Sargent
Augustine N. Mavor-Parker
M. Caccia
Lucas Caccia
Esmeralda S. Whitammer
Minseon Kim
Scaling the horizon of agentic LLMs is bottlenecked by the need to fit ever longer context traces in GPU memory. Context compaction has been… (see more) the most popular mechanism to alleviate this issue, keeping GPU memory constant for a given trace. Unfortunately, most compaction strategies rely on prefilling the LLM context many times over, hindering training throughput. To alleviate this bottleneck and enable efficient trainable compaction, we propose KV-streams, a plug-and-play strategy compatible with any compaction strategy that substantially increases throughput while showing no evidence of hindering performance. KV-streams enable scalable compaction by streaming the KV cache forward rather than flushing it after each compaction. We show that KV-streams enable three different compaction strategies, achieving a 2.6 to 5x wall-clock speedup in training. Beyond efficiency, we find that the streamed KV cache can act as a recurrent state, carrying forward information that has long since disappeared from the context. Specifically, in a controlled setting we show that, contrary to prior work, RL alone is all that is needed for this behavior to emerge. Overall, we show KV-streams to be an efficient and lightweight plug-and-play addition to any post-training pipeline.
Controllable and Content-Based Recommendations
Traditional recommendation systems rely on latent (dense) representations, making them difficult to interpret and control. We propose the Co… (see more)ntrollable and Content-Based Recommendations (CCBR) framework, which builds its recommendations from textual user profile representations. CCBR plugs into collaborative filtering models and introduces controllability via text bottlenecks. We show that CCBR enables text-based and multimodal interventions, allowing users to steer the model towards the directions they prefer. Different from existing controllable recommendation systems, CCBR infers the text summaries directly from item contents (images, audio or video). Across image-, audio-, and video-based datasets, we demonstrate that the proposed framework obtains competitive model performance with standard (latent-representation) models while providing controllable model summaries via text. The model also outperforms TEARS, a recent baseline for controllable recommendation systems. Through systematic interventions, we demonstrate the efficacy of the user steering mechanism.
Rethinking Literature Search Evaluation: Deep Research Helps, and Human Citation Lists Are Not a Ground Truth
Christopher Pal
We study large-scale literature search from two complementary angles: improving the retrieval pipeline, and stress-testing the human referen… (see more)ce list as an evaluation target. First, we implement a Deep Research pipeline that processes the full query paper and expands the retrieved results breadth-first along their bibliographies, and show that it substantially outperforms vanilla API-only search, raising recall on RollingEval-Jun25 (a 250-paper literature-search benchmark) from below 20% to above 80%. Second, we use a neutral LLM-as-a-judge to determine if human references are sound ground truth for the task. We find significant limitations: only 51% of human citations are judged moderately relevant or higher, against 86--88% for the strongest AI-based re-rankers. We study this gap on the OpenAlex co-authorship graph, finding that humans are 2.5x more likely than the best AI re-rankers to cite a direct collaborator. Together, our results argue against single-axis literature-search evaluation: recall, topical-relevance scoring, ranked-list diversity, and a co-authorship-distance diagnostic each measure complementary properties of citation quality and should be reported jointly.
Privileged Information Distillation for Language Models
Nicolas Gontier
Alexandre Lacoste
Massimo Caccia
Training-time privileged information (PI) can enable language models to succeed on tasks they would otherwise fail, making it a powerful too… (see more)l for reinforcement learning in hard, long-horizon settings. However, transferring capabilities learned with PI to policies that must act without it at inference time remains a fundamental challenge. We study this problem in the context of distilling frontier models for multi-turn agentic environments, which typically hide their internal reasoning and expose only action trajectories. This breaks standard distillation pipelines, since successful behavior is observable, but the reasoning process is not. For this, we introduce {\pi}-Distill, a joint teacher-student objective that trains a PI-conditioned teacher and an unconditioned student simultaneously using the same model. Additionally, we also introduce On-Policy Self-Distillation (OPSD), an alternative approach that trains using Reinforcement Learning (RL) with a reverse KL-penalty between the student and the PI-conditioned teacher. We show that both of these algorithms effectively distill frontier agents using action-only PI. Specifically, we find that {\pi}-Distill and, in some cases, OPSD, outperform industry standard practices (Supervised finetuning followed by RL) that assume access to full Chain-of-Thought supervision across multiple agentic benchmarks, models, and forms of PI. We complement our results with extensive analysis that characterizes the factors enabling effective learning with PI, focusing primarily on {\pi}-Distill and characterizing when OPSD is competitive.
Contextual Preference Distribution Learning
Decision-making problems often feature uncertainty stemming from heterogeneous and context-dependent human preferences. To address this, we … (see more)propose a sequential learning-and-optimization pipeline to learn preference distributions and leverage them to solve downstream problems, for example risk-averse formulations. We focus on human choice settings that can be formulated as (integer) linear programs. In such settings, existing inverse optimization and choice modelling methods infer preferences from observed choices but typically produce point estimates or fail to capture contextual shifts, making them unsuitable for risk-averse decision-making. Using a bounded-variance score function gradient estimator, we train a predictive model mapping contextual features to a rich class of parameterizable distributions. This approach yields a maximum likelihood estimate. The model generates scenarios for unseen contexts in the subsequent optimization phase. In a synthetic ridesharing environment, our approach reduces average post-decision surprise by up to 114
Modular Memory is the Key to Continual Learning Agents
Vaggelis Dorovatas
Malte Schwerin
Andrew D. Bagdanov
Lucas Caccia
Antonio Carta
Barbara Hammer
Tyler L. Hayes
Timm Hess
Christopher Kanan
Dhireesha Kudithipudi
Xialei Liu
Vincenzo Lomonaco
Jorge Mendez-Mendez
Ameya Prabhu
Elisa Ricci
Tinne Tuytelaars
Gido M. van de Ven
Liyuan Wang … (see 4 more)
Joost van de Weijer
Jonghyun Choi
Martin Mundt
Foundation models have transformed machine learning through large-scale pretraining and increased test-time compute. Despite surpassing huma… (see more)n performance in several domains, these models remain fundamentally limited in continuous operation, experience accumulation, and personalization, capabilities that are central to adaptive intelligence. While continual learning research has long targeted these goals, its historical focus on in-weight learning (IWL), i.e., updating a single model's parameters to absorb new knowledge, has rendered catastrophic forgetting a persistent challenge. Our position is that combining the strengths of In-Weight Learning (IWL) and the newly emerged capabilities of In-Context Learning (ICL) through the design of modular memory is the missing piece for continual adaptation at scale. We outline a conceptual framework for modular memory-centric architectures that leverage ICL for rapid adaptation and knowledge accumulation, and IWL for stable updates to model capabilities, charting a practical roadmap toward continually learning agents.
Self-Supervised Learning from Structural Invariance
Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization
Zichen Zhao
Fuyuan Lyu
Xiuying Chen
Jikun Kang
Xue Liu
Large Language Models (LLMs) excel at general-purpose tasks, yet adapting their responses to individual users remains challenging. Retrieval… (see more) augmentation provides a lightweight alternative to fine-tuning by conditioning LLMs on user history records, and existing approaches typically select these records based on semantic relevance. We argue that relevance serves as an unreliable proxy for utility: a record may be semantically similar to a query yet fail to improve generation quality or even degrade it due to redundancy or conflicting information. To bridge this gap, we propose PURPLE, a contextual bandit framework that oPtimizes UseR Profiles for Llm pErsonalization. In contrast to a greedy selection of the most relevant records, PURPLE treats profile construction as a set generation process and utilizes a Plackett-Luce ranking model to capture complex inter-record dependencies. By training with dense feedback provided by the likelihood of the reference response, our method aligns retrieval directly with generation quality. Extensive experiments on nine personalization tasks demonstrate that PURPLE consistently outperforms strong heuristic and retrieval-augmented baselines in both effectiveness and efficiency, establishing a principled and scalable solution for optimizing user profiles.
Position: Modular Memory is the Key to Continual Learning Agents
Vaggelis Dorovatas
Malte Schwerin
Andrew Bagdanov
Lucas Caccia
Antonio Carta
CITEC Barbara Hammer
Tyler Hayes
Timm Hess
Christopher Kanan
Dhireesha Kudithipudi
Xialei Liu
Vincenzo Lomonaco
Jorge Mendez-Mendez
Ameya Pandurang Prabhu
Elisa Ricci
Tinne Tuytelaars
Gido van de Ven
Liyuan Wang … (see 4 more)
Joost van de Weijer
Jonghyun Choi
Martin Mundt
Foundation models have transformed machine learning through large-scale pretraining, massive parameterization, and increased test-time compu… (see more)te. Despite surpassing human performance in several domains, these models remain fundamentally limited in continuous operation, experience accumulation, and personalization, capabilities that are central to adaptive intelligence. While continual learning research has long targeted these goals, its historical focus on in-weight learning, i.e., updating a single model’s parameters to absorb new knowledge, has rendered catastrophic forgetting a persistent challenge. **Our position is that combining the strengths of In-Weight Learning (IWL) and the newly emerged capabilities of In-Context Learning (ICL) through the design of modular memory is the missing piece for continual adaptation at scale.** We outline a conceptual framework for modular memory-centric architectures that leverage ICL for rapid adaptation and knowledge accumulation, and IWL for stable updates to model capabilities, thereby mitigating catastrophic forgetting and charting a practical roadmap toward continually learning agents.