Conference
Autoregressive Language Models are Secretly Energy-Based Models
Mathieu Blondel, Michaël E. Sander, Germain Vivier-Ardisson, Tianlin Liu, Vincent Roulet
International Conference on Machine Learning (ICML) 2026
Joint Learning of Energy-based Models and their Partition Function
Michaël E. Sander, Vincent Roulet, Tianlin Liu, Mathieu Blondel
International Conference on Machine Learning (ICML) 2025
Loss Functions and Operators Generated by f-Divergences
Vincent Roulet, Tianlin Liu, Nino Vieillard, Michaël E. Sander, Mathieu Blondel
International Conference on Machine Learning (ICML) 2025
Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise
Enea Monzio Compagnoni, Tianlin Liu, Rustem Islamov, Frank Norbert Proske, Antonio Orvieto, Aurélien Lucchi
International Conference on Learning Representations (ICLR) 2025
Decoding-time Realignment of Language Models
Tianlin Liu, Shangmin Guo, Leonardo Bianco, Daniele Calandriello, Quentin Berthet, Felipe Llinares, Jessica Hoffmann, Lucas Dixon, Michal Valko, Mathieu Blondel
International Conference on Machine Learning (ICML) 2024
Spotlight presentation
The N Implementation Details of RLHF with PPO
Shengyi Huang, Tianlin Liu, Leandro Von Werra
The Blogpost Track at International Conference on Learning Representations (ICLR) 2024
Spotlight presentation
Sparsity-constrained optimal transport
Tianlin Liu, Joan Puigcerver, Mathieu Blondel
International Conference on Learning Representations (ICLR) 2023
Spotlight presentation
Universal approximation under constraints is possible with transformers
Anastasis Kratsios, Behnoosh Zamanlooy, Tianlin Liu, and Ivan Dokmanić
International Conference on Learning Representations (ICLR) 2022
Spotlight presentation
Finding trainable sparse networks through neural tangent transfer
Tianlin Liu and Friedemann Zenke
International Conference on Machine Learning (ICML) 2020
Causally denoise word embeddings using half-sibling regression
Zekun Yang*, Tianlin Liu* (*Equal contribution)
AAAI Conference on Artificial Intelligence 2020
Continual learning for sentence representations using conceptors
Tianlin Liu, Lyle Ungar and João Sedoc
Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT) 2019
Reservoir transfer on analog neuromorphic hardware
Xu He, Tianlin Liu, Fatemeh Hadaeghi, and Herbert Jaeger
International IEEE EMBS Conference on Neural Engineering (NER) 2019
Best paper finalist award (3rd place out of 467 accepted papers)
Unsupervised post-processing of word vectors via conceptor negation
Tianlin Liu, Lyle Ungar, and João Sedoc
AAAI Conference on Artificial Intelligence 2019
Journal
LoFi: Neural Local Fields for Scalable Image Reconstruction
AmirEhsan Khorashadizadeh, Tobías I. Liaudat, Tianlin Liu, Jason D. McEwen, Ivan Dokmanić
IEEE Transactions on Computational Imaging, 2025
GLIMPSE: Generalized Local Imaging with MLPs
AmirEhsan Khorashadizadeh, Valentin Debarnot, Tianlin Liu, Ivan Dokmanić
IEEE Transactions on Medical Imaging, 2025
Routers in Vision Mixture of Experts: An Empirical Study
Tianlin Liu, Mathieu Blondel, Carlos Riquelme, Joan Puigcerver
Transactions on Machine Learning Research (TMLR), 2024
WaveBench: Benchmarking Data-driven Solvers for Linear Wave Propagation PDEs
Tianlin Liu*, Jose Antonio Lara Benitez*, Amirehsan Khorashadizadeh, Florian Faucher, Maarten V de Hoop, Ivan Dokmanić
Learning multiscale convolutional dictionaries for image reconstruction
Tianlin Liu, Anadi Chaman, David Belius, and Ivan Dokmanić
IEEE Transactions on Computational Imaging, 2022
Workshop
SeisLM: A Foundation Model for Seismic Waveforms
Tianlin Liu, Jannes Münchmeyer, Laura Laurenti, Chris Marone, Maarten V. de Hoop, Ivan Dokmanić
Foundation Models for Science Workshop, 38th Conference on Neural Information Processing Systems (NeurIPS) 2024
Fast binary compressive sensing via smoothed l0 gradient descent
Tianlin Liu and Dae Gwan Lee
International Workshop on Compressed Sensing Theory and its Applications to Radar, Sonar, and Remote Sensing (CoSeRa) 2018
Correcting the common discourse bias in linear representation of sentences using conceptors
Tianlin Liu, João Sedoc, and Lyle Ungar
Biocreative/OHNLP workshop at ACM-BCB 2018
Predicting engagement breakdown in HRI using thin-slices of facial expressions
Tianlin Liu and Arvid Kappas
AAAI Workshop on Affective Content Analysis 2018
Preprints & Technical Reports
DiffusionGemma Technical Report
DiffusionGemma Team, Google DeepMind
Technical report, 2026
Gemma 4 Technical Report
Gemma Team, Google DeepMind
Technical report, 2026
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gemini Team, Google DeepMind
Technical report, 2025
Direct Language Model Alignment from Online AI Feedback
Shangmin Guo, Biao Zhang, Tianlin Liu, Tianqi Liu, Misha Khalman, Felipe Llinares-López, Alexandre Ramé, Thomas Mesnard, Yao Zhao, Bilal Piot, Johan Ferret, Mathieu Blondel
arXiv preprint, 2024
A consistent method for learning OOMs from asymptotically stationary time series data containing missing values
Tianlin Liu
Technical report, 2018