Nearly 100 Mila-affiliated scientific papers accepted at NeurIPS 2023

Mila and NeurIPS 2023 logos

From December 10 to December 16, 2023, Mila researchers will attend the thirty-seventh Conference on Neural Information Processing Systems (NeurIPS) in New Orleans. This year, they will share 96 scientific papers pushing the boundaries of artificial intelligence (AI) research with their peers from all around the world.

Here is a list of papers accepted at NeurIPS 2023 that contain at least one Mila-affiliated author :

























































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































Adaptive Resolution Residual NetworksLéa Demeule,Mahtab Sandhu,Glen
Effective Latent Differential Equation Models via Attention and Multiple ShootingGermán Abrevaya,Mahta Ramezanian-Panahi,Jean-Christophe Gagnon-Audet,Pablo Polosecki,Irina Rish,Silvina Ponce Dawson,Guillermo Cecchi,Guillaume
Physics-Informed Transformer NetworksFabricio Dos Santos,Tara Akhound-Sadegh,Siamak
Deep PDE Solvers for Subgrid Modelling and Out-of-Distribution GeneralizationPatrick Chatain,Adam
Causal Inference in Gene Regulatory Networks with GFlowNet: Towards Scalability in Large SystemsTrang Nguyen,Alexander Tong,Kanika Madan,Yoshua Bengio,Dianbo
DGFN: Double Generative Flow NetworksElaine Lau,Nikhil Murali Vemgal,Doina Precup,Emmanuel
Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu SearchAbbas Mehrabian,Ankit Anand,Hyunjik Kim,Nicolas Sonnerat,Tudor Berariu,Matej Balog,Gheorghe Comanici,Andrew Lee,Anian Ruoss,Anna Bulanova,Daniel Toyama,Sam Blackwell,Bernardino Romera Paredes,Laurent Orseau,Petar Veličković,Anurag Murty Naredla,Joonkyung Lee,Adam Zsolt Wagner,Doina
Learning Optimizers for Local SGDCharles-Étienne Joseph,Benjamin Thérien,Abhinav Moudgil,Boris Knyazev,Eugene
Learning Silicon Dopant Transitions in Graphene using Scanning Transmission Electron MicroscopyMax Schwarzer,Jesse Farebrother,Joshua Greaves,Kevin Roccapriore,E. D. Cubuk,Rishabh Agarwal,Aaron Courville,Marc G. Bellemare,Sergei Kalinin,Igor Mordatch,Pablo Samuel
On the importance of catalyst-adsorbate geometric relative information when predicting relaxed energyAlvaro Carbonero,Alexandre Duval,Victor Schmidt,Santiago Miret,Alex Hernandez-Garcia,Yoshua Bengio,David
Towards equilibrium molecular conformation generation with GFlowNetsAlexandra Volokhova,Michał Koziarski,Alex Hernandez-Garcia,Cheng-Hao Liu,Santiago Miret,Pablo Lemos,Luca Thiede,Zichao Yan,Alan Aspuru-Guzik,Yoshua
Piecewise Linear Parametrization of Policies: Towards Interpretable Deep Reinforcement LearningMaxime Wabartha,Joelle
Searching for High-Value Molecules Using Reinforcement Learning and TransformersRaj Ghugare,Santiago Miret,Adriana Hugessen,Mariano Phielipp,Glen
HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials ScienceYu Song,Santiago Miret,Huan Zhang,Bang
Crystal-GFlowNet: sampling materials with desirable properties and constraintsMistal,Alex Hernandez-Garcia,Alexandra Volokhova,Alexandre Duval,Yoshua Bengio,Divya Sharma,Pierre Luc Carrier,Michał Koziarski,Victor
Learning Conditional Policies for Crystal Design Using Offline Reinforcement LearningPrashant Govindarajan,Santiago Miret,Jarrid Rector-Brooks,Mariano Phielipp,Janarthanan Rajendran,Sarath
Detecting Backdoors with Meta-ModelsLauro Langosco,Neel Alex,William Baker,David Quarel,Herbie Bradley,David
Score-Based Likelihood Characterization for Inverse Problems in the Presence of Non-Gaussian NoiseRonan Legin,Alexandre Adam,Yashar Hezaveh,Laurence
Learning to Scale Logits for Temperature-Conditional GFlowNetsMinsu Kim,Joohwan Ko,Dinghuai Zhang,L. Pan,Taeyoung Yun,Woochang Kim,Jinkyoo Park,Yoshua
Baking Symmetry into GFlowNetsGeorge Ma,Emmanuel Bengio,Yoshua Bengio,Dinghuai
Role of Structural and Conformational Diversity for Machine Learning PotentialsNikhil Shenoy,Prudencio Tossou,Emmanuel Noutahi,Hadrien Mary,Dominique Beaini,Jiarui
Latent Space Simulator for Unveiling Molecular Free Energy Landscapes and Predicting Transition DynamicsSimon Dobers,Hannes Stärk,Xiang Fu,Dominique Beaini,Stephan
Evaluating Self-Supervised Learning for Molecular Graph EmbeddingsHanchen Wang,Jean Kaddour,Shengchao Liu,Jian Tang,Matt J. Kusner,Joan Lasenby,Qi
ClimateSet: A Large-Scale Climate Model Dataset for Machine LearningJulia Kaltenborn,Charlotte Emilie Elektra Lange,Venkatesh Ramesh,Philippe Brouillard,Yaniv Gurwicz,Chandni Nagda,Jakob Runge,Peer Nowack,David
GEO-Bench: Toward Foundation Models for Earth MonitoringAlexandre Lacoste,Nils Lehmann,Pau Rodríguez,Evan D. Sherwin,H. Kerner,Bjorn Lutjens,Jeremy Andrew Irvin,J. Irvin,David Dao,H. Alemohammad,Alexandre Drouin,Mehmet Gunturkun,Gabriel Huang,David Vazquez,Dava Newman,Yoshua Bengio,S. Ermon,Xiao Xiang
PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation LearningFlorian Bordes,Shashank Shekhar,Mark Ibrahim,Diane Bouchacourt,Pascal Vincent,Ari S.
Temporal Graph Benchmark for Machine Learning on Temporal GraphsShenyang Huang,Farimah Poursafaei,Jacob Danovitch,Matthias Fey,Weihua Hu,Emanuele Rossi,Jure Leskovec,Michael M. Bronstein,Guillaume Rabusseau,Reihaneh
SatBird: a Dataset for Bird Species Distribution Modeling using Remote Sensing and Citizen Science DataMélisande Teng,Amna Elmustafa,Benjamin Akera,Yoshua Bengio,Hager Radi,Hugo Larochelle,David
Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline MaterialsShengchao Liu,Weitao Du,Yanjing Li,Zhuoxinran Li,Zhiling Zheng,Chenru Duan,Zhi-Ming Ma,O. Yaghi,Anima Anandkumar,Christian Borgs,Jennifer T. Chayes,Hongyu Guo,Jian
Generating QM1B with PySCF$_{\text{IPU}}$Alexander Mathiasen,Hatem Helal,K. Klaser,Paul Balanca,Josef Dean,Carlo Luschi,Dominique Beaini,A. Fitzgibbon,Dominic
Additive Decoders for Latent Variables Identification and Cartesian-Product ExtrapolationSebastien Lachapelle,Divyat Mahajan,Ioannis Mitliagkas,Simon
Prioritizing Samples in Reinforcement Learning with Reducible LossShiva Kanth Sujit,Somjit Nath,Pedro H. M. Braga,Samira E.
The Impact of Positional Encoding on Length Generalization in TransformersAmirhossein Kazemnejad,Inkit Padhi,Karthikeyan Natesan,K. Ramamurthy,Payel Das,Siva
Small batch deep reinforcement learningJohan Samir Obando Ceron,Marc G. Bellemare,Pablo Samuel
A Heat Diffusion Perspective on Geodesic Preserving Dimensionality ReductionGuillaume Huguet,Alexander Tong,Edward De Brouwer,Yanlei Zhang,Guy Wolf,Ian M. Adelstein,Smita
When Do Transformers Shine in RL? Decoupling Memory from Credit AssignmentTianwei Ni,Michel Ma,Benjamin Eysenbach,Pierre-luc
Language Model Alignment with Elastic ResetMichael Noukhovitch,Samuel Lavoie,Florian Strub,Aaron
Prediction and Control in Continual Reinforcement LearningNishanth Anand,Doina
Decision-Aware Actor-Critic with Function Approximation and Theoretical GuaranteesSharan Vaswani,A. Kazemi,Reza Babanezhad Harikandeh,Nicolas
HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide ResolutionEric Q. Nguyen,Michael Poli,Marjan Faizi,A. Thomas,Michael Wornow,C. Birch-sykes,Aman Patel,Stefano Massaroli,Clayton M. Rabideau,Yoshua Bengio,S. Ermon,S. Baccus,Christopher
When Do Graph Neural Networks Help with Node Classification? Investigating the Impact of Homophily Principle on Node DistinguishabilitySitao Luan,Chenqing Hua,Minkai Xu,Qincheng Lu,Jiaqi Zhu,Xiaowen Chang,Jie Fu,Jure Leskovec,Doina
Normalization Layers Are All That Sharpness-Aware Minimization NeedsMaximilian Mueller,Tiffany Joyce Vlaar,David Rolnick,Matthias
DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNetsLazar Atanackovic,Alexander Tong,BO WANG,Leo J Lee,Yoshua Bengio,Jason
Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RLChen Sun,Wannan Yang,Thomas Jiralerspong,Dane Malenfant,Benjamin Alsbury-Nealy,Yoshua Bengio,Blake Aaron
Double Gumbel Q-LearningDavid Yu-Tung Hui,Aaron Courville,Pierre-luc
Reusable Slotwise MechanismsTrang Nguyen,Amin Mansouri,Kanika Madan,Nguyen Duy Khuong,Khuong N. Nguyen,Kartik Ahuja,Dianbo Liu,Yoshua
A Diffusion-Model of Joint Interactive NavigationM. Niedoba,J. Wilder Lavington,Yunpeng Liu,Vasileios Lioutas,Justice Sefas,Xiaoxuan Liang,Dylan Green,Setareh Dabiri,B. Zwartsenberg,Adam Scibior,Frank
For SALE: State-Action Representation Learning for Deep Reinforcement LearningScott Fujimoto,Wei-Di Chang,Edward J. Smith,Shane Gu,Doina Precup,David
GAUCHE: A Library for Gaussian Processes in ChemistryRyan-Rhys Griffiths,Leo Klarner,Henry Moss,Aditya Ravuri,Sang T. Truong,Yuanqi Du,Samuel Don Stanton,Gary Tom,Bojana Rankovic,Arian Rokkum Jamasb,Aryan Deshwal,Julius Schwartz,Austin Tripp,Gregory Kell,Simon Frieder,Anthony Bourached,Alex Chan,Jacob Moss,Chengzhi Guo,Johannes P. Dürholt,Saudamini Chaurasia,Ji Won Park,Felix Strieth-Kalthoff,Alpha Lee,Bingqing Cheng,Alan Aspuru-Guzik,Philippe Schwaller,Jian TangICML 2022 2nd AI for Science Workshop2022-07-21poster
CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive LearningCharles Guille-Escuret,Pau Rodríguez,David Vazquez,Ioannis Mitliagkas,João MonteiroarXiv.org2021-12-31published
$\textbf{A}^2\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep LearningAdel Nabli,Eugene Belilovsky,Edouard OyallonarXiv.org2022-12-31published
Thinker: Learning to Plan and ActStephen Chung,Ivan Anokhin,David
Retrieval-Augmented Multiple Instance LearningYufei CUI,Ziquan Liu,Yixin CHEN,Yuchen Lu,Xinyue Yu,X Liu,Tei-Wei Kuo,Miguel R. D. Rodrigues,Chun Jason Xue,Antoni B.
Optimal Extragradient-Based Algorithms for Stochastic Variational Inequalities with Separable StructureAn Yuan,Chris Junchi Li,Gauthier Gidel,Michael Jordan,Quanquan Gu,Simon Shaolei
Improving Compositional Generalization using Iterated Learning and Simplicial EmbeddingsYi Ren,Samuel Lavoie,Mikhail Galkin,Danica J. Sutherland,Aaron
Lie Point Symmetry and Physics-Informed NetworksTara Akhound-Sadegh,Laurence Perreault-Levasseur,Johannes Brandstetter,Max Welling,Siamak
Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow NetworkTristan Deleu,Mizu Nishikawa-Toomey,Jithendaraa Subramanian,Nikolay Malkin,Laurent Charlin,Yoshua
Maximum State Entropy Exploration using Predecessor and Successor RepresentationsArnav Kumar Jain,Lucas Lehnert,Irina Rish,Glen
Joint Prompt Optimization of Stacked LLMs using Variational InferenceAlessandro Sordoni,Xingdi Yuan,Marc-Alexandre Côté,Matheus Pereira,Adam Trischler,Ziang Xiao,Arian Hosseini,Friederike Niedtner,Nicolas
DiffPack: A Torsional Diffusion Model for Autoregressive Protein Side-Chain PackingYangtian Zhang,Zuobai Zhang,Bozitao Zhong,Sanchit Misra,Jian
Guiding The Last Layer in Federated Learning with Pre-Trained ModelsGwen Legate,Nicolas Bernier,Lucas Caccia,Edouard Oyallon,Eugene
Learning better with Dale’s Law: A Spectral PerspectivePingsheng Li,Jonathan Cornford,Arna Ghosh,Blake Aaron
A Definition of Continual Reinforcement LearningDavid Abel,Andre Barreto,Benjamin Van Roy,Doina Precup,Hado van Hasselt,Satinder P.
Auxiliary Losses for Learning Generalizable Concept-based ModelsIvaxi Sheth,Samira E.
Feature Likelihood Score: Evaluating the Generalization of Generative Models Using SamplesMarco Jiralerspong,Joey Bose,Ian Gemp,Chongli Qin,Yoram Bachrach,Gauthier
Improving *day-ahead* Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal ContextOussama Boussif*,Ghait Boukachab*,Dan Assouline*,Stefano Massaroli,Tianle Yuan,Loubna Benabbou,Yoshua
Group Robust Classification Without Any Group InformationChristos Tsirigotis,João Monteiro,Pau Rodríguez,David Vazquez,Aaron
Equivariant Adaptation of Large Pretrained ModelsArnab Kumar Mondal,Siba Smarak Panigrahi,Oumar Kaba,Sai Rajeswar,Siamak
Formalizing locality for normative synaptic plasticity modelsC. Bredenberg,Ezekiel Williams,Cristina Savin,Blake Aaron Richards,Guillaume
Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised LearningCasey Meehan,Florian Bordes,Pascal Vincent,Kamalika Chaudhuri,Chuan
Are Diffusion Models Vision-And-Language Reasoners?Benno Krojer,Elinor Poole-Dayan,Vikram Voleti,Christopher Joseph Pal,Siva
Towards Hybrid-grained Feature Interaction Selection for Deep Sparse NetworkFuyuan Lyu,Xing Tang,Dugang Liu,Chen Ma,Weihong Luo,Liang Chen,xiuqiang He,X
Block-State TransformersJonathan Pilault,Mahan Fathi,Orhan Firat,Christopher Joseph Pal,Pierre-luc Bacon,Ross
Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNetsDinghuai Zhang,Hanjun Dai,Nikolay Malkin,Aaron Courville,Yoshua Bengio,L.
Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous ControlNate Rahn,Pierluca D'Oro,Harley Wiltzer,Pierre-Luc Bacon,Marc G.
Parallel-mentoring for Offline Model-based OptimizationCan Chen,Christopher Beckham,Zixuan Liu,X Liu,Christopher Joseph
Multi-Head Adapter Routing for Cross-Task GeneralizationLucas Caccia,Edoardo Ponti,Zhan Su,Matheus Pereira,Nicolas Roux,Alessandro
A*Net: A Scalable Path-based Reasoning Approach for Knowledge GraphsZhaocheng Zhu,Xinyu Yuan,Mikhail Galkin,Sophie Xhonneux,Ming Zhang,Maxime Gazeau,Jian
Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory PredictionZuobai Zhang,Minghao Xu,Aurelie Lozano,Vijil Chenthamarakshan,Payel Das,Jian
Learning Reliable Logical Rules with SATNetZhaoyu Li,Jinpei Guo,Yuhe Jiang,Xujie
Importance-aware Co-teaching for Offline Model-based OptimizationYe Yuan,Can Chen,Zixuan Liu,Willie Neiswanger,X
Laughing Hyena Distillery: Extracting Compact Recurrences From ConvolutionsStefano Massaroli,Michael Poli,Daniel Y. Fu,Hermann Kumbong,Rom Nishijima Parnichkun,David W. Romero,Aman Timalsina,Quinn McIntyre,Beidi Chen,Atri Rudra,Ce Zhang,Christopher Re,S. Ermon,Yoshua
Versatile Energy-Based Probabilistic Models for High Energy PhysicsTaoli Cheng,Aaron
A Unified, Scalable Framework for Neural Population DecodingMehdi Azabou,Vinam Arora,Venkataramana Ganesh,Ximeng Mao,Santosh B Nachimuthu,Michael Jacob Mendelson,Blake Aaron Richards,Matthew G Perich,Guillaume Lajoie,Eva L
Statistical Guarantees for Variational Autoencoders using PAC-Bayesian TheorySokhna Diarra Mbacke,Florence Clerc,Pascal
Object-centric architectures enable efficient causal representation learningAmin Mansouri, Jason Hartford, Yan Zhang, Yoshua BengioCausal Representation Learning27 Oct 2023poster
Multi-Domain Causal Representation Learning via Weak Distributional InvariancesKartik Ahuja, Amin Mansouri, Yixin WangCausal Representation Learning27 Oct 2023poster
EDGI: Equivariant Diffusion for Planning with Embodied AgentsJohann Bremer*, Joey Bose*, Pim de Haan, Taco Cohen 
Subtle Misogyny Detection and Mitigation: An Expert-Annotated DatasetAnna Richter*, Brooklyn Sheppard*, Allison Cohen, Elizabeth Smith, Tamara Kneese, Carolyne Pelletier, Ioana Baldini, Yue Dong + oral 
Symmetry Breaking and Equivariant Neural NetworksSékou-Oumar Kaba, Siamak RavanbakhshNeurReps Workshop2023-11-15oral 
From 6235149080811616882909238708 to 29: Vanilla Thompson Sampling RevisitedBingshan Hu, Tianyue H. ZhangNeurips Opt Workshop2023-10-27poster
Climate Variable Downscaling with Conditional Normalizing FlowChristina Winkler, Paula Harder, David Rolnick  
Mitigating Mode Collapse in Sparse Mixture-of-ExpertsNizar Islah, Diganta Misra, Timothy Nest, Matthew Riemer, Irina Rish, Eilif MullerNeurIPS NewInML Workshop2023-11-13poster
Feedback-guided Data Synthesis for Imbalanced ClassificationReyhane Askari Hemmat, Mohammad Pezeshki, Florian Bordes, Michal Drozdzal, Adriana Romero-Sorianosyntheticdata4ml@Neurips20232023-10-27poster
Discovering environments with XRMMohammad Pezeshki, Diane Bouchacourt, Mark Ibrahim, Nicolas Ballas, Pascal Vincent, David Lopez-PazDistShift @NeurIPS20232023-10-27poster
A Computational Framework for Solving Wasserstein Lagrangian FlowsKirill Neklyudov, Rob Brekelmans, Alexander Tong, Lazar Atanackovic, qiang liu, Alireza MakhzaniNeurIPS OTML Workshop poster