EPFL @ ICLR 2024
The following 31 EPFL papers have been accepted toICLR 2024(12th International Conference on Learning Representations).
The conference will be held from May 7-11, 2024 in Vienna, Austria.
Below is a list of ICLR 2024 accepted papers with at least one EPFL author:
- Generalization of Deep ResNets in the mean-field regime by Yihang Chen, Fanghui Liu, Yiping Lu, Grigorios Chrysos, Volkan Cevher (spotlight)
- Efficient local linearity regularization to overcome catastrophic overfitting by Elias Abad Rocamora, Fanghui Liu, Grigorios Chrysos, Pablo M. Olmos, Volkan Cevher (poster)
- Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness by A. Agafonov, D. Kamzolov, A. Gasnikov, A. Kavis, K. Antonakopoulos, V. Cevher and Martin Takáč (poster)
- Robust NAS benchmark under adversarial training: assessment, theory, and beyond by Y. Wu, F. Liu, C. Simon-Gabriel, G. Chrysos, V. Cevher (poster)
- Multilinear operator networks by Y. Cheng, G. Chrysos, M. Georgopoulos, V. Cevher (poster)
- Efficient Instance-Optimal Finite-Sum Minimization by Ioannis Mavrothalassitis, Stratis Skoulakis, Leello Tadesse Dadi, Volkan Cevher (poster)
- Adversarial Training Should Be Cast as a Non-Zero-Sum Game by Alexander Robey, Fabian Latorre, George J. Pappas, Hamed Hassani, Volkan Cevher (poster)
- Generalized Policy Iteration using Tensor Approximation for Hybrid Control by Suhan Shetty, Teng Xue, Sylvain Calinon
- 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation by Chen Zhao, Tong Zhang, Mathieu Salzmann
- Social-Transmotion: Promptable Human Trajectory Prediction by Saeed Saadatnejad, Yang Gao, Kaouther Messaoud, Alexandre Alahi (poster)
- ODEFormer: Symbolic Regression of Dynamical Systems with Transformers by Stéphane d'Ascoli, Sören Becker, Philippe Schwaller, Alexander Mathis, Niki Kilbertus (spotlight)
- Beam Enumeration: Probabilistic Explainability For Sample Efficient Self-conditioned Molecular Design by Jeff Guo, Philippe Schwaller (poster)
- First-order ANIL provably learns representations despite overparametrisation by Oğuz Kaan Yüksel, Etienne Boursier, Nicolas Flammarion
- Layerwise Linear Mode Connectivity by Linara Adilova, Maksym Andriushchenko, Michael Kamp, Asja Fischer, Martin Jaggi
- Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning by Haobo Song, Hao Zhao, Soumajit Majumder, Tao Lin (poster)
- Analysis of learning a flow-based generative model from finite sample complexity by Hugo Cui, Florent Krzakala, Eric Vanden-Eijnden, Lenka Zdeborová
- Simple Hierarchical Planning with Diffusion by Chang Chen, Fei Deng, Kenji Kawaguchi, Caglar Gulcehre, Sungjin Ahn
- Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation Networks by Marc Russwurm, Konstantin Klemmer, Esther Rolf, Robin Zbinden, Devis Tuia
- Unraveling the Key Components of OOD Generalization via Diversification by Harold Luc Benoit, Liangze Jiang, Andrei Atanov, Oguzhan Fatih Kar, Mattia Rigotti, Amir Zamir (poster)
- Prediction without Preclusion: Recourse Verification with Reachable Sets by Avni Kothari, Bogdan Kulynych, Tsui-Wei Weng, Berk Ustun
- Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian Optimization by Anthony Bardou, Patrick Thiran, Thomas Begin
- Simplical Repersentation Learning with Neural k-forms by Kelly Maggs, Celia Hacker, Bastian Rieck
- Evaluating Language Model Agency through Negotiations by Tim R. Davidson, Veniamin Veselovsky, Martin Josifoski, Maxime Peyrard, Antoine Bosselut, Michal Kosinski, Robert West (poster)
- Neural SDF Flow for 3D Reconstruction of Dynamic Scenes by Wei Mao, Richard Hartley, Mathieu Salzmann, Miaomiao Liu (poster)
- A Primal-Dual Approach to Solving Variational Inequalities with General Constraints by Tatjana Chavdarova, Tong Yang, Matteo Pagliardini, Michael Jordan (poster)
- QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models by Jing Liu, Ruihao Gong, Xiuying Wei, Zhiwei Dong, Jianfei Cai, Bohan Zhuang (poster)
- Mind Your Augmentation: The Key to Decoupling Dense Self-Supervised Learning by Congpei Qiu, Tong Zhang, Yanhao Wu, Wei Ke, Mathieu Salzmann, Sabine Süsstrunk (poster)
- Implicit Gaussian process representation of vector fields over arbitrary latent manifolds by Robert L. Peach, Matteo Vinao-Carl, Nir Grossman, Michael David, Emma Mallas, David Sharp, Paresh A. Malhotra, Pierre Vandergheynst, Adam Gosztolai (poster)
- CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrapping byTim Lebailly, Thomas Stegmüller, Behzad Bozorgtabar, Jean-Philippe Thiran, Tinne Tuytelaars (spotlight)
- Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation by Devavrat Tomar, Guillaume Vray, Jean-Philippe Thiran, Behzad Bozorgtabar