Voici le programme des chercheuses et chercheurs affilié·e·s à Mila présentant leur travail à NeurIPS 2024. Toutes les heures sont exprimées en heure normale pacifique (PST).
Une version PDF est également disponible ici
Mila @ NeurIPS 2024, 12/10/ 2024
Présentations au kiosque de Mila #104 - 12 PM - 5 PM PST
- 12:15 PM Akshatha Arodi - CableInspect-AD: An Expert-Annotated Anomaly Detection Dataset
- 2:30 PM Raymond Chua - Learning Successor Features the Simple Way
- 3:15 PM Oscar Mañas - Controlling Multimodal LLMs via Reward-guided Decoding
4:15 PM - Le Zhang - Assessing and Learning Alignment of Unimodal Vision and Language Models
Mila @ NeurIPS 2024, 12/11/ 2024
Présentations au kiosque de Mila #104 - 10 AM - 5 PM PST
10:15 AM Moksh Jain - Amortizing intractable inference in diffusion models for vision, language, and control
11:15 AM Aniket Didolkar - Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
12:15 PM Shahrad Mohammadzadeh, Juan David Guerra - Hallucination Detox: Sensitive Neuron Dropout (SeND) for Large Language Model Training and Epistemic Integrity of Large Language Models
2:00 PM Francesco Paissan - Listenable Maps for Zero-Shot Audio Classifiers
3:15 PM Benno Krojer - Learning Action and Reasoning-Centric Image Editing from Videos and Simulation
4:15 PM Daniel Levy - SymmCD: Symmetry-Preserving Crystal Generation with Diffusion Models
Poster Session 1 - 11 AM - 2 PM (PST)
#1110 How Molecules Impact Cells: Unlocking Contrastive PhenoMolecular Retrieval: Philip Fradkin, Puria Azadi Moghadam, Karush Suri, Frederik Wenkel, Ali Bashashati, Maciej Sypetkowski, Dominique Beaini
#1606 Learning Action and Reasoning-Centric Image Editing from Videos and Simulation: Benno Krojer, Dheeraj Vattikonda, Luis Lara, Varun Jampani, Eva Portelance, Christopher Pal, Siva Reddy
#2403 Stress-Testing Capability Elicitation With Password-Locked Models: Ryan Greenblatt, Fabien Roger, Dmitrii Krasheninnikov, David Krueger
#2510 Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences: Damien Ferbach, Quentin Bertrand, Joey Bose, Gauthier Gidel
#2509 ET-Flow: Equivariant Flow-Matching for Molecular Conformer Generation: Majdi Hassan, Nikhil Shenoy, Jungyoon Lee, Hannes Stärk, Stephan Thaler, Dominique Beaini
#3506 Density-based User Representation using Gaussian Process Regression for Multi-interest Personalized Retrieval: Haolun Wu, Ofer Meshi, Masrour Zoghi, Fernando Diaz, Xue Liu, Craig Boutilier, Maryam Karimzadehgan
#4939 The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms: Elizabeth Collins-Woodfin, Inbar Seroussi, Begoña García Malaxechebarría, Andrew Mackenzie, Elliot Paquette, Courtney Paquette
#5210 CableInspect-AD: An Expert-Annotated Anomaly Detection Dataset: Akshatha Arodi, Margaux Luck, Jean-Luc Bedwani, Aldo Zaimi, Ge Li, Nicolas Pouliot, Julien Beaudry, Gaetan Marceau Caron
#6805 Offline Multitask Representation Learning for Reinforcement Learning: Haque Ishfaq, Thanh Nguyen-Tang, Songtao Feng, Raman Arora, Mengdi Wang, Ming Yin, Doina Precup
Poster Session 2 - 4:30 - 7:30 PM (PST)
#1104 Reactzyme: A Benchmark for Enzyme-Reaction Prediction: Chenqing Hua, Bozitao Zhong, Sitao Luan, Liang Hong, Guy Wolf, Doina Precup, Shuangjia Zheng
#1107 MSA Generation with Seqs2Seqs Pretraining: Advancing Protein Structure Predictions: Le Zhang, Jiayang Chen, Tao Shen, Yu Li, Siqi Sun
#1211 Multi-Scale Representation Learning for Protein Fitness Prediction: Zuobai Zhang, Pascal Notin, Yining Huang, Aurelie Lozano, Vijil Chenthamarakshan, Debora Susan Marks, Payel Das, Jian Tang
#2008 Efficient Leverage Score Sampling for Tensor Train Decomposition: Vivek Bharadwaj, Beheshteh T. Rakhshan, Osman Asif Malik, Guillaume Rabusseau
#2606 Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling: Yuanqi Du, Michael Plainer, Rob Brekelmans, Chenru Duan, Frank Noé, Carla P. Gomes, Alán Aspuru-Guzik, Kirill Neklyudov
#2705 On improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models: Tariq Berrada, Pietro Astolfi, Melissa Hall, Reyhane Askari Hemmat, Yohann Benchetrit, Marton Havasi, Matthew J. Muckley, Karteek Alahari, Adriana Romero-Soriano, Jakob Verbeek, Michal Drozdzal
#4801 Normalization and effective learning rates in reinforcement learning: Clare Lyle, Zeyu Zheng, Khimya Khetarpal, James Martens, Hado van Hasselt, Razvan Pascanu, Will Dabney
#5101 RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content: Joao Monteiro, Pierre-Andre Noel, Étienne Marcotte, Sai Rajeswar, Valentina Zantedeschi, David Vazquez, Nicolas Chapados, Christopher Pal, Perouz Taslakian
#5308 WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks: Léo Boisvert, Megh Thakkar, Maxime Gasse, Massimo Caccia, Thibault Le Sellier De Chezelles, Quentin Cappart, Nicolas Chapados, Alexandre Lacoste, Alexandre Drouin
#5708 4+3 Phases of Compute-Optimal Neural Scaling Laws: Elliot Paquette, Courtney Paquette, Lechao Xiao, Jeffrey Pennington
#6109 Conformal Inverse Optimization: Bo Lin, Érick Delage, Timothy Chan
#6401 Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn: Hongyao Tang, Glen Berseth
#6910 Balancing Context Length and Mixing Times for Reinforcement Learning at Scale: Matthew D Riemer, Khimya Khetarpal, Janarthanan Rajendran, Sarath Chandar
#7210 Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Generation: Guillaume Huguet, James Vuckovic, Kilian FATRAS, Eric Thibodeau-Laufer, Pablo Lemos, Riashat Islam, Cheng-Hao Liu, Jarrid Rector-Brooks, Tara Akhound-Sadegh, Michael M. Bronstein, Alexander Tong, Joey Bose
Mila @ NeurIPS 2024, 12/12/ 2024
Présentations au kiosque de Mila #104 - 10 AM - 4 PM (PST)
10:15 AM Jonas Ngnawé - Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers
11:15 AM Prakhar Ganesh - Different Horses for Different Courses: Comparing Bias Mitigation Algorithms in ML
12:15 PM Bonaventure F. P. Dossou - From Preservation to Progress: Expanding Language AI Frontiers for Low-Resource Communities
2:30 PM Arthur Ouaknine - Tackling Climate Change with Machine Learning
3:15 PM Saba Ahmadi - VisMin: Visual Minimal-Change Understanding
Poster Session 3 - 11 AM - 2 PM (PST)
#1100 RGFN: Synthesizable Molecular Generation Using GFlowNets: Michał Koziarski, Andrei Rekesh, Dmytro Shevchuk, Almer M. van der Sloot, Piotr Gaiński, Yoshua Bengio, Cheng-Hao Liu, Mike Tyers, Robert A. Batey
#2104 Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers: Fatemeh Nourilenjan Nokabadi, Jean-Francois Lalonde, Christian Gagné
#2109 On the Scalability of Certified Adversarial Robustness with Generated Data: Thomas Altstidl, David Dobre, Arthur Kosmala, Bjoern Eskofier, Gauthier Gidel, Leo Schwinn
#2411 Metric Flow Matching for Smooth Interpolations on the Data Manifold: Kacper Kapusniak, Peter Potaptchik, Teodora Reu, Leo Zhang, Alexander Tong, Michael M. Bronstein, Joey Bose, Francesco Di Giovanni
#2704 Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving: Aniket Rajiv Didolkar, Anirudh Goyal, Nan Rosemary Ke, Siyuan Guo, Michal Valko, Timothy P Lillicrap, Danilo Jimenez Rezende, Yoshua Bengio, Michael Curtis Mozer, Sanjeev Arora
#2911 What Is Missing For Graph Homophily? Disentangling Graph Homophily For Graph Neural Networks: Yilun Zheng, Sitao Luan, Lihui Chen
#3011 A Foundation Model for Zero-shot Logical Query Reasoning: Mikhail Galkin, Jincheng Zhou, Bruno Ribeiro, Jian Tang, Zhaocheng Zhu
#3204 The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More: Ouail Kitouni, Niklas Nolte, Adina Williams, Michael Rabbat, Diane Bouchacourt, Mark Ibrahim
#3800 Towards a "Universal Translator" for Neural Dynamics at Single-Cell: Yizi Zhang, Yanchen Wang, Donato M. Jiménez-Benetó, Zixuan Wang, Mehdi Azabou, Blake Aaron Richards, Renee Tung, Olivier Winter, International Brain Laboratory, Eva L Dyer, Liam Paninski, Cole Lincoln Hurwitz
#4702 Efficient Adversarial Training in LLMs with Continuous Attacks: Sophie Xhonneux, Alessandro Sordoni, Stephan Günnemann, Gauthier Gidel, Leo Schwinn
#6001 HardCore Generation: Generating Hard UNSAT Problems for Data Augmentation: Joseph Cotnareanu, Zhanguang Zhang, Hui-Ling Zhen, Yingxue Zhang, Mark Coates
#6402 QGFN: Controllable Greediness with Action Values: Elaine Lau, Stephen Zhewen Lu, Ling Pan, Doina Precup, Emmanuel Bengio
#6510 Predicting Future Actions of Reinforcement Learning Agents: Stephen Chung, Scott Niekum, David Krueger
#6704 Foundations of Multivariate Distributional Reinforcement Learning: Harley Wiltzer, Jesse Farebrother, Arthur Gretton, Mark Rowland
#6706 Periodic agent-state based Q-learning for POMDPs: Amit Sinha, Matthieu Geist, Aditya Mahajan
Poster Session 4 - 4:30 PM - 7:30 PM (PST)
#2008 Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers: Jonas Ngnawe, Sabyasachi Sahoo, Yann Batiste Pequignot, Frederic Precioso, Christian Gagne
#2010 Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space: Leo Schwinn, David Dobre, Sophie Xhonneux, Gauthier Gidel, Stephan Günnemann
#3607 VisMin: Visual Minimal-Change Understanding: Rabiul Awal, Saba Ahmadi, Le Zhang, Aishwarya Agrawal
#3705 Geometry of naturalistic object representations in recurrent neural network models of working memory: Xiaoxuan Lei, Takuya Ito, Pouya Bashivan
#3803 Towards training digitally-tied analog blocks via hybrid gradient computation: Timothy Nest, Maxence Ernoult
#4600 Slight Corruption in Pre-training Data Makes Better Diffusion Models: Hao Chen, Yujin Han, Diganta Misra, Xiang Li, Kai Hu, Difan Zou, Masashi Sugiyama, Jindong Wang, Bhiksha Raj
#4705 Cell ontology guided transcriptome foundation model: Xinyu Yuan, Zhihao Zhan, Zuobai Zhang, Manqi Zhou, Jianan Zhao, Boyu Han, Yue Li, Jian Tang
#5502 Wasserstein Distributionally Robust Optimization through the Lens of Structural Causal Models and Individual Fairness: Ahmad Reza Ehyaei, Golnoosh Farnadi, Samira Samadi
#6404 CALE: Continuous Arcade Learning Environment: Jesse Farebrother, Pablo Samuel Castro
#6504 Learning Successor Features the Simple Way: Raymond Chua, Arna Ghosh, Christos Kaplanis, Blake Aaron Richards, Doina Precup
#6508 Using Unity to Help Solve Reinforcement Learning: Connor Brennan, Andrew Robert Williams, Omar G. Younis, Vedant Vyas, Daria Yasafova, Irina Rish
#6606 Adaptive Exploration for Data-Efficient General Value Function Evaluations: Arushi Jain, Josiah P. Hanna, Doina Precup
#6612 Simplifying Constraint Inference with Inverse Reinforcement Learning: Adriana Hugessen, Harley Wiltzer, Glen Berseth
#7101 Amortizing intractable inference in diffusion models for vision, language, and control: Siddarth Venkatraman, Moksh J. Jain, Luca Scimeca, Minsu Kim, Marcin Sendera, Mohsin Hasan, Luke Rowe, Sarthak Mittal, Pablo Lemos, Emmanuel Bengio, Alexandre Adam, Jarrid Rector-Brooks, Yoshua Bengio, Glen Berseth, Nikolay Malkin
Mila @ NeurIPS 2024, 12/13/ 2024
Poster Session 5 - 11 AM - 2 PM (PST)
#1002 Trajectory Flow Matching with Applications to Clinical Time Series Modelling: Xi Zhang, Yuan Pu, Yuki Kawamura, Andrew Loza, Yoshua Bengio, Dennis Shung, Alexander Tong
#2201 Harnessing small projectors and multiple views for efficient vision pretraining: Arna Ghosh, Kumar Krishna Agrawal, Shagun Sodhani, Adam Oberman, Blake Aaron Richards
#2211 Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection: Charles Guille-Escuret, Pierre-Andre Noel, Ioannis Mitliagkas, David Vazquez, Joao Monteiro
#2606 Fisher Flow Matching for Generative Modelling over Discrete Data: Oscar Davis, Samuel Kessler, Mircea Petrache, Ismail Ilkay Ceylan, Michael Bronstein, Joey Bose
#3103 On the Scalability of GNNs for Molecular Graphs: Maciej Sypetkowski, Frederik Wenkel, Farimah Poursafaei, Nia Dickson, Karush Suri, Philip Fradkin, Dominique Beaini
#3202 Listenable Maps for Zero-Shot Audio Classifiers: Francesco Paissan, Luca Della Libera, Mirco Ravanelli, Cem Subakan
#3301 Interpreting Learned Feedback Patterns in Large Language Models: Luke Marks, Amir Abdullah, Clement Neo, Rauno Arike, David Krueger, Philip Torr, Fazl Barez
#3303 Improving Context-Aware Preference Modeling for Language Models: Silviu Pitis, Ziang Xiao, Nicolas Le Roux, Alessandro Sordoni
#3307 Do LLMs Build World Representations? Probing Through the Lens of State Abstraction: Zichao Li, Yanshuai Cao, Jackie C. K. Cheung
#3606 Grounding Multimodal Large Language Models in Actions: Andrew Szot, Bogdan Mazoure, Harsh Agrawal, Devon Hjelm, Zsolt Kira, Alexander T Toshev
#6304 Parseval Regularization for Continual Reinforcement Learning: Wesley Chung, Lynn Cherif, Doina Precup, David Meger
#6410 Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning: Harley Wiltzer, Marc G. Bellemare, David Meger, Patrick Shafto, Yash Jhaveri
Poster Session 6 - 4:30 PM - 7:30 PM (PST)
#1005 Code Repair with LLMs gives an Exploration-Exploitation Tradeoff: Hao Tang, Keya Hu, Jin Peng Zhou, Si Cheng Zhong, Wei-Long Zheng, Xujie Si, Kevin Ellis
#2002 When is an Embedding Model More Promising than Another?: Maxime Darrin, Philippe Formont, Ismail Ben Ayed, Jackie C. K. Cheung, Pablo Piantanida
#2600 Improved off-policy training of diffusion samplers: Marcin Sendera, Minsu Kim, Sarthak Mittal, Pablo Lemos, Luca Scimeca, Jarrid Rector-Brooks, Alexandre Adam, Yoshua Bengio, Nikolay Malkin
#2701 Many-Shot In-Context Learning: Rishabh Agarwal, Avi Singh, Lei M Zhang, Bernd Bohnet, Luis Rosias, Stephanie C.Y. Chan, Biao Zhang, Ankesh Anand, Zaheer Abbas, Azade Nova, John D Co-Reyes, Eric Chu, Feryal Behbahani, Aleksandra Faust, Hugo Larochelle
#3710 A Generative Model of Symmetry Transformations: James Urquhart Allingham, Bruno Mlodozeniec, Shreyas Padhy, Javier Antoran, David Krueger, Richard E. Turner, Eric Nalisnick, José Miguel Hernández-Lobato
#6110 GenRL: Multimodal-foundation world models for generalization in embodied agents: Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt, Aaron Courville, Sai Rajeswar
#6805 Efficient Reinforcement Learning by Discovering Neural Pathways: Samin Yeasar Arnob, Riyasat Ohib, Sergey Plis, Amy Zhang, Alessandro Sordoni, Doina Precup
