[Google Scholar] [dblp]
Temporal straightening for latent planning. Ying Wang, Oumayma Bounou, Gaoyue Zhou, Randall Balestriero, Tim G. J. Rudner, Yann LeCun, Mengye Ren. arXiv preprint arXiv:2603.12231, 2026. [webpage] [arxiv] [html]
MA-EgoQA: Question answering over egocentric videos from multiple embodied agents. Kangsan Kim, Yanlai Yang, Suji Kim, Woongyeong Yeo, Youngwan Lee, Mengye Ren, Sung Ju Hwang. arXiv preprint arXiv:2603.09827, 2026. [arxiv] [html]
When does verification pay off? A closer look at LLMs as solution verifiers. Jack Lu*, Ryan Teehan*, Jinran Jin, Mengye Ren. arXiv preprint arXiv:2512.02304, 2025. [arxiv] [html]
In-context clustering with large language models. Ying Wang, Mengye Ren, Andrew Gordon Wilson. arXiv preprint arXiv:2510.08466, 2025. [webpage] [arxiv] [html]
StreamMem: Query-agnostic KV cache memory for streaming video understanding. Yanlai Yang, Zhuokai Zhao, Satya Narayan Shukla, Aashu Singh, Shlok Kumar Mishra, Lizhu Zhang, Mengye Ren. arXiv preprint arXiv:2508.15717, 2025. [webpage] [arxiv] [html]
Context tuning for in-context optimization. Jack Lu, Ryan Teehan, Zhenbang Yang, Mengye Ren. arXiv preprint arXiv:2507.04221, 2025. [webpage] [arxiv] [html]
LifelongMemory: Leveraging LLMs for answering queries in long-form egocentric videos. Ying Wang, Yanlai Yang, Mengye Ren. arXiv preprint arXiv:2312.05269, 2023. [webpage] [arxiv] [pdf] [html]
BIM: block-wise self-supervised learning with masked image modeling. Yixuan Luo, Mengye Ren, Sai Qian Zhang. arXiv preprint arXiv:2311.17218, 2023. [arxiv]
Gaussian-Bernoulli RBMs without tears. Renjie Liao, Simon Kornblith, Mengye Ren, David J. Fleet, Geoffrey Hinton. arXiv preprint arXiv:2210.10318, 2022. [arxiv]
Learning to reason with relational abstractions. Andrew J. Nam*, Mengye Ren*, Chelsea Finn, James L. McClelland. arXiv preprint arXiv:2210.02615, 2022. [arxiv] [dataset] [pdf]
Online unsupervised learning of visual representations and categories. Mengye Ren, Tyler R. Scott, Michael L. Iuzzolino, Michael C. Mozer, Richard Zemel. arXiv preprint arXiv:2109.05675, 2021. [arxiv] [code] [pdf] [html]
Flexible few-shot learning of contextual similarity. Mengye Ren*, Eleni Triantafillou*, Kuan-Chieh Wang*, James Lucas*, Jake Snell, Xaq Pitkow, Andreas S. Tolias, Richard S. Zemel. arXiv preprint arXiv:2012.05895, 2020. [pdf] [video]
Learning to remember from a multi-task teacher. Yuwen Xiong*, Mengye Ren*, Raquel Urtasun. arXiv preprint arXiv:1910.04650, 2019. [arxiv]
Temporal straightening for latent planning. Ying Wang, Oumayma Bounou, Gaoyue Zhou, Randall Balestriero, Tim G. J. Rudner, Yann LeCun, Mengye Ren. World Modeling Workshop, 2026. [webpage] [arxiv] [html]
SkillFactory: Self-distillation for learning cognitive behaviors. Zayne Sprague, Jack Lu, Manya Wadhwa, Sedrick Keh, Mengye Ren, Greg Durrett. ICLR, 2026. [arxiv]
When does verification pay off? A closer look at LLMs as solution verifiers. Jack Lu*, Ryan Teehan*, Jinran Jin, Mengye Ren. ICLR 2026 Workshop on AI with Recursive Self-Improvement, 2026. [arxiv] [html]
Local reinforcement learning with action-conditioned root mean squared Q-functions. Frank (Zequan) Wu, Mengye Ren. ICLR, 2026. [webpage] [arxiv] [html]
Midway Network: Learning representations for recognition and motion from latent dynamics. Christopher Hoang, Mengye Ren. ICLR, 2026. [webpage] [arxiv] [html]
LaMo: A latent motion world model for long-horizon prediction. Azwar Abdulsalam, Christopher Hoang, Mengye Ren. ICLR 2026 the 2nd Workshop on World Models: Understanding, Modelling and Scaling, 2026.
Opinion: Learning Intuitive Physics Requires More Than Visual Data. Ellen Su*, Solim LeGris*, Todd M. Gureckis, Mengye Ren. NeurIPS 2025 Workshop on Embodied World Models for Decision Making, 2025. [arxiv]
Context tuning for in-context optimization. Jack Lu, Ryan Teehan, Zhenbang Yang, Mengye Ren. Second Workshop on Test-Time Adaptation: Putting Updates to the Test! at ICML 2025, 2025. [webpage] [arxiv] [html]
Discrete JEPA: Learning discrete token representations without reconstruction. Junyeob Baek, Hosung Lee, Christopher Hoang, Mengye Ren, Sungjin Ahn. WoTok: Workshop on Tokenization at ICML 2025, 2025. [arxiv] [html]
Replay can provably increase forgetting. Yasaman Mahdaviyeh, James Lucas, Mengye Ren, Andreas S. Tolias, Richard Zemel, Toniann Pitassi. CoLLAs, 2025. [arxiv] [html]
Memory Storyboard: Leveraging temporal segmentation for streaming self-supervised learning from egocentric videos. Yanlai Yang, Mengye Ren. CoLLAs, 2025. [webpage] [arxiv] [code] [html]
A general framework for inference-time scaling and steering of diffusion models. Raghav Singhal*, Zachary Horvitz*, Ryan Teehan*, Mengye Ren, Zhou Yu, Kathleen McKeown, Rajesh Ranganath. ICML, 2025. [arxiv]
Are LLMs prescient? A continuous evaluation using daily news as the oracle. Hui Dai, Ryan Teehan, Mengye Ren. ICML, 2025. [webpage] [arxiv] [code] [dataset] [html]
PooDLe: Pooled and dense self-supervised learning from naturalistic videos. Alex N. Wang*, Christopher Hoang*, Yuwen Xiong, Yann LeCun, Mengye Ren. ICLR, 2025. [webpage] [arxiv] [code] [dataset] [pdf] [html]
Are LLMs prescient? A continuous evaluation using daily news as the oracle. Hui Dai, Ryan Teehan, Mengye Ren. AFM, 2024. [webpage] [arxiv] [code] [dataset] [html]
ProCreate, don’t reproduce! Propulsive energy diffusion for creative generation. Jack Lu, Ryan Teehan, Mengye Ren. ECCV, 2024. [webpage] [arxiv] [code] [pdf] [html]
Integrating present and past in unsupervised continual learning. Yipeng Zhang, Laurent Charlin, Richard Zemel, Mengye Ren. CoLLAs, 2024. [arxiv] [pdf] [html]
Integrating present and past in unsupervised continual learning. Yipeng Zhang, Laurent Charlin, Richard Zemel, Mengye Ren. CLVision, 2024. [arxiv] [pdf] [html]
CoLLEGe: Concept embedding generation for large language models. Ryan Teehan, Brenden M. Lake, Mengye Ren. COLM, 2024. [webpage] [arxiv] [code] [pdf] [html]
Reawakening knowledge: Anticipatory recovery from catastrophic interference via structured training. Yanlai Yang, Matt Jones, Michael C. Mozer, Mengye Ren. NeurIPS, 2024. [webpage] [arxiv] [code] [pdf] [html]
Self-supervised learning of video representations from a child’s perspective. Emin Orhan, Wentao Wang, Alex N. Wang, Mengye Ren, Brenden M. Lake. CogSci, 2024. [arxiv] [pdf] [html]
Learning and forgetting unsafe examples in large language models. Jiachen Zhao, Zhun Deng, David Madras, James Zou, Mengye Ren. ICML, 2024. [arxiv] [pdf] [html]
Towards unsupervised object detection from LiDAR point clouds. Lunjun Zhang, Anqi Joyce Yang, Yuwen Xiong, Sergio Casas, Bin Yang, Mengye Ren, Raquel Urtasun. CVPR, 2023. [webpage] [arxiv] [pdf] [video]
Scaling forward gradient with local losses. Mengye Ren, Simon Kornblith, Renjie Liao, Geoffrey Hinton. ICLR, 2023. [arxiv] [code] [pdf] [html]
Learning in temporally structured environments. Matt Jones, Tyler R. Scott, Mengye Ren, Gamaleldin F. Elsayed, Katherine Hermann, David Mayo, Michael C. Mozer. ICLR, 2023. [pdf]
Multitask learning via interleaving: A neural network investigation. David Mayo, Tyler R Scott, Mengye Ren, Gamaledin Elsayed, Katherine Hermann, Matt Jones, Michael Mozer. CogSci, 2023. [pdf]
Egocentric video comprehension via large language model inner speech. Ying Wang, Dongdong Sun, Rui Chen, Yanlai Yang, Mengye Ren. 3rd International Ego4D Workshop at CVPR, 2023. [pdf]
Rethinking closed-loop training for autonomous driving. Chris Zhang*, Runsheng Guo*, Wenyuan Zeng*, Yuwen Xiong, Binbin Dai, Rui Hu, Mengye Ren, Raquel Urtasun. ECCV, 2022. [arxiv] [pdf]
Learning to reason with relational abstractions. Andrew J. Nam*, Mengye Ren*, Chelsea Finn, James L. McClelland. 2nd Workshop on MATH-AI at NeurIPS, 2022. [arxiv] [dataset] [pdf]
Neural network online training with sensitivity to multiscale temporal structure. Matt Jones, Tyler R. Scott, Gamaleldin F. Elsayed, Mengye Ren, Katherine Hermann, David Mayo, Michael C. Mozer. Memory in Artificial and Real Intelligence Workshop at NeurIPS, 2022. [pdf]
Open-world machine learning with limited labeled data. Mengye Ren. Ph.D. Thesis, University of Toronto, 2022. [pdf]
Just label what you need: Fine-grained active selection for perception and prediction through partially labeled scenes. Sean Segal*, Nishanth Kumar*, Sergio Casas, Wenyuan Zeng, Mengye Ren, Jingkang Wang, Raquel Urtasun. CoRL, 2021. [arxiv]
Exploring adversarial robustness of multi-sensor perception systems in self driving. James Tu, Huichen Li, Xinchen Yan, Mengye Ren, Yun Chen, Ming Liang, Eilyan Bitar, Ersin Yumer, Raquel Urtasun. CoRL, 2021. [arxiv]
Adversarial attacks on multi-agent communication. James Tu*, Tsun-Hsuan Wang*, Jingkang Wang, Sivabalan Manivasagam, Mengye Ren, Raquel Urtasun. ICCV, 2021. [arxiv]
Self-supervised representation learning from flow equivariance. Yuwen Xiong, Mengye Ren, Wenyuan Zeng, Raquel Urtasun. ICCV, 2021. [arxiv] [pdf] [html]
AdvSim: Generating safety-critical scenarios for self-driving vehicles. Jingkang Wang, Ava Pun, James Tu, Abbas Sadat, Sergio Casas, Sivabalan Manivasagam, Mengye Ren, Raquel Urtasun. CVPR, 2021. [arxiv] [pdf]
SceneGen: Learning to simulate realistic traffic scenes. Shuhan Tan*, Kelvin Wong*, Shenlong Wang, Sivabalan Manivasagam, Mengye Ren, Raquel Urtasun. CVPR, 2021. [arxiv] [pdf]
Perceive, attend and drive: Learning spatial attention for safe self-driving. Bob Wei*, Mengye Ren*, Wenyuan Zeng, Ming Liang, Bin Yang, Raquel Urtasun. ICRA, 2021. [arxiv] [pdf] [html] [video]
Theoretical bounds on estimation error for meta learning. James Lucas, Mengye Ren, Irene Kameni, Toniann Pitassi, Richard S. Zemel. ICLR, 2021. [arxiv] [pdf] [html] [video]
SketchEmbedNet: Learning novel concepts by imitating drawings. Alexander Wang*, Mengye Ren*, Richard S. Zemel. ICML, 2021. [arxiv] [pdf] [html]
Wandering within a world: Online contextualized few-shot learning. Mengye Ren, Michael L. Iuzzolino, Michael C. Mozer, Richard S. Zemel. ICLR, 2021. [arxiv] [code] [pdf] [html] [video]
Cost-efficient online hyperparameter optimization. Jingkang Wang*, Mengye Ren*, Ilija Bogunovic, Yuwen Xiong, Raquel Urtasun. ICML RealML Workshop, 2020. [arxiv] [pdf] [slides]
Learning to communicate and correct pose errors. Nicholas Vadivelu, Mengye Ren, James Tu, Jingkang Wang, Raquel Urtasun. CoRL, 2020. [arxiv] [video]
Perceive, predict, and plan: Safe motion planning through interpretable semantic representations. Abbas Sadat*, Sergio Casas Romero*, Mengye Ren, Xinyu Wu, Pranaab Dhawan, Raquel Urtasun. ECCV, 2020. [arxiv]
End-to-end contextual perception and prediction with interaction transformer. Lingyun (Luke) Li, Bin Yang, Ming Liang, Wenyuan Zeng, Mengye Ren, Sean Segal, Raquel Urtasun. IROS, 2020. [arxiv]
LoCo: Local contrastive representation learning. Yuwen Xiong, Mengye Ren, Raquel Urtasun. NeurIPS, 2020. [arxiv] [pdf] [html] [video]
Multi-agent routing value iteration network. Quinlan Sykora*, Mengye Ren*, Raquel Urtasun. ICML, 2020. [arxiv] [code] [pdf] [html] [video]
Wandering within a world: Online contextualized few-shot learning. Mengye Ren, Michael L. Iuzzolino, Michael C. Mozer, Richard S. Zemel. ICML Continual Learning Workshop & Lifelong Learning Workshop & Workshop on Learning in Artificial Open Worlds, 2020. [arxiv] [code] [pdf] [html] [video]
Physically realizable adversarial examples for LiDAR object detection. James Tu, Mengye Ren, Sivabalan Manivasagam, Ming Liang, Bin Yang, Richard Du, Frank Cheng, Raquel Urtasun. CVPR, 2020. [arxiv] [video]
Flexible few-shot learning of contextual similarity. Mengye Ren*, Eleni Triantafillou*, Kuan-Chieh Wang*, James Lucas*, Jake Snell, Xaq Pitkow, Andreas S. Tolias, Richard S. Zemel. NeurIPS Meta-Learning Workshop, 2020. [pdf] [video]
Multi-label incremental few-shot learning for medical image pathology classifiers. Laleh Seyyed-Kalantari, Karsten Roth, Mengye Ren, Parsa Torabian, Joseph P. Cohen, Marzyeh Ghassemi. Medical Imaging Meets NeurIPS Workshop, 2020. [video]
Identifying unknown instances for autonomous driving. Kelvin Wong, Shenlong Wang, Mengye Ren, Ming Liang, Raquel Urtasun. CoRL, 2019. [arxiv]
Jointly learnable behavior and trajectory planner for self-driving vehicles. Abbas Sadat*, Mengye Ren*, Andrei Pokrovsky, Yen-Chen Lin, Ersin Yumer, Raquel Urtasun. IROS, 2019. [arxiv]
Deformable filter convolution for point cloud reasoning. Yuwen Xiong*, Mengye Ren*, Renjie Liao, Kelvin Wong, Raquel Urtasun. arXiv preprint arXiv:1907.13079, 2019. [arxiv]
Incremental few-shot learning with attention attractor networks. Mengye Ren, Renjie Liao, Ethan Fetaya, Richard S. Zemel. NeurIPS, 2019. [arxiv] [code] [html]
Graph hypernetworks for neural architecture search. Chris Zhang, Mengye Ren, Raquel Urtasun. ICLR, 2019. [arxiv] [html]
Information-theoretic limitations on novel task generalization. James Lucas, Mengye Ren, Richard S. Zemel. NeurIPS Workshop on Machine Learning with Guarantees, 2019. [pdf]
Incremental few-shot learning with attention attractor networks. Mengye Ren, Renjie Liao, Ethan Fetaya, Richard S. Zemel. NeurIPS Meta-Learning Workshop, 2018. [arxiv] [code] [html]
Graph hypernetworks for neural architecture search. Chris Zhang, Mengye Ren, Raquel Urtasun. NeurIPS Meta-Learning Workshop, 2018. [arxiv] [html]
Learning to reweight examples for robust deep learning. Mengye Ren, Wenyuan Zeng, Bin Yang, Raquel Urtasun. ICML, 2018. [arxiv] [code] [html]
Understanding short-horizon bias in meta optimization. Yuhuai Wu*, Mengye Ren*, Renjie Liao, Roger B. Grosse. ICLR, 2018. [webpage] [arxiv] [code] [html]
Meta-learning for semi-supervised few-shot classification. Mengye Ren, Eleni Triantafillou*, Sachin Ravi*, Jake Snell, Kevin Swersky, Joshua B. Tenenbaum, Hugo Larochelle, Richard S. Zemel. ICLR, 2018. [webpage] [arxiv] [code] [html]
SBNet: Sparse blocks network for fast inference. Mengye Ren*, Andrei Pokrovsky*, Bin Yang*, Raquel Urtasun. CVPR, 2018. [webpage] [arxiv] [code] [html]
Understanding short-horizon bias in meta optimization. Yuhuai Wu*, Mengye Ren*, Renjie Liao, Roger B. Grosse. NIPS, 2017. [webpage] [arxiv] [code] [html]
Meta-learning for semi-supervised few-shot classification. Mengye Ren, Eleni Triantafillou*, Sachin Ravi*, Jake Snell, Kevin Swersky, Joshua B. Tenenbaum, Hugo Larochelle, Richard S. Zemel. NIPS, 2017. [webpage] [arxiv] [code] [html]
The reversible residual network: Backpropagation without storing activations. Aidan N. Gomez*, Mengye Ren*, Raquel Urtasun, Roger B. Grosse. NeurIPS, 2017. [webpage] [arxiv] [code]
Normalizing the normalizers: Comparing and extending network normalization schemes. Mengye Ren*, Renjie Liao*, Raquel Urtasun, Fabian H. Sinz, Richard S. Zemel. ICLR, 2017. [webpage] [arxiv] [code]
End-to-end instance segmentation with recurrent attention. Mengye Ren, Richard S. Zemel. CVPR, 2017. [webpage] [arxiv] [code] [video]
Exploring models and data for image question answering. Mengye Ren, Ryan Kiros, Richard S. Zemel. NeurIPS, 2015. [webpage] [arxiv] [code] [dataset] [results] [question generation]
Exploring models and data for image question answering. Mengye Ren, Ryan Kiros, Richard Zemel. ICML Deep Learning Workshop, 2015. [webpage] [arxiv] [code] [dataset] [results] [question generation]