EPFL papers @ NeurIPS 2024

Below is a list of NeurIPS 2024 papers with at least one EPFL author:

1. Membership Inference Attacks against Large Vision-Language Models by Zhan Li*, Yongtao Wu*, Yihang Chen*, Francesco Tonin, Elias Abad Rocamora, Volkan Cevher
2. Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling by Moritz Haas, Jin Xu, Volkan Cevher, Leena Chennuru Vankadara
3. SAMPa: Sharpness-aware Minimization Parallelized by Wanyun Xie, Thomas Pethick, Volkan Cevher
4. Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces byAngeliki Kamoutsi, Peter Schmitt-Förster, Tobias Sutter, Volkan Cevher, John Lygeros
5. On Feature Learning in Structured State Space Modelsby Leena Chennuru Vankadara, Jin Xu, Moritz Haas, Volkan Cevher
6. Why Do We Need Weight Decay in Modern Deep Learning? by Francesco D'Angelo*, Maksym Andriushchenko*, Aditya Varre, Nicolas Flammarion
7. Reconstruction of Manipulated Garment with Guided Deformation Prior by Ren Li, Corentin Dumery, Zhantao Deng, Pascal Fua
8. No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO by Skander Moalla, Andrea Miele, Razvan Pascanu, Caglar Gulcehre
9. Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers by Xiuying Wei, Skander Moalla, Razvan Pascanu, Caglar Gulcehre
10. Stochastic Bilevel Optimization with Lower-Level Contextual Markov Decision Processes by Vinzenz Thoma, Barna Pasztor, Andreas Krause, Giorgia Ramponi, Yifan Hu
11. Stochastic Optimization Algorithms for Instrumental Variable Regression with Streaming Data by Xuxing Chen, Abhishek Roy, Yifan Hu, Krishna Balasubramanian
12. Group Robust Preference Optimization in Reward-free RLHF by Shyam Sundhar Ramesh, Yifan Hu, Iason Chaimalas, Viraj Mehta, Pier Giuseppe Sessa, Haitham Bou Ammar, Ilija Bogunovic
13. MTGS: A Novel Framework for Multi-Person Temporal Gaze Following and Social Gaze Prediction by Anshul Gupta, Samy Tafasca, Arya Farkhondeh, Pierre Vuillecard, Jean-Marc Odobez
14. Toward Semantic Gaze Target Detection by Samy Tafasca, Anshul Gupta, Victor Bros, Jean-Marc Odobez
15. DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging by Matteo Pagliardini, Amirkeivan Mohtashami, François Fleuret, Martin Jaggi
16. QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs by Saleh Ashkboos, Amirkeivan Mohtashami, Maximilian L. Croci, Bo Li, Pashmina Cameron, Martin Jaggi, Dan Alistarh, Torsten Hoefler, James Hensman
17. Scaling Laws and Compute-Optimal Training without Fixed Training Duration by Alexander Hägele, Elie Bakouch, Atli Kosson, Loubna Ben allal, Leandro Von Werra, Martin Jaggi
18. Analyzing & Reducing the Need for Learning Rate Warmup in Neural Network Optimization by Atli Kosson, Bettina Messmer, Martin Jaggi
19. CoBo: Collaborative Learning via Bilevel Optimization by Diba Hashemi, Lie He, Martin Jaggi
20. Local to Global: Learning Dynamics and Effect of Initialization for Transformers by Ashok Vardhan Makkuva*, Marco Bondaschi*, Adway Girish, Alliot Nagle, Hyeji Kim, Michael Gastpar, Chanakya Ekbote
21. Transformers on Markov data: Constant depth suffices by Nived Rajaraman, Marco Bondaschi, Kannan Ramchandran, Michael Gastpar, Ashok Vardhan Makkuva
22. Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models by Alliot Nagle*, Adway Girish*, Marco Bondaschi, Michael Gastpar, Ashok Vardhan Makkuva*, Hyeji Kim*
23. 4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities by Roman Bachmann*, Oğuzhan Fatih Kar*, David Mizrahi*, Ali Garjani, Mingfei Gao, David Griffiths, Jiaming Hu, Afshin Dehghan, Amir Zamir
24. How Far Can Transformers Reason? The Locality Barrier and Inductive Scratchpad by Emmanuel Abbe, Samy Bengio, Aryo Lotfi, Colin Sandon, Omid Saremi
25. Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial ClientsF by Youssef Allouah, Abdellah El Mrini, Rachid Guerraoui, Nirupam Gupta, Rafael Pinot
26. Revisiting Ensembling in One-Shot Federated Learning by Youssef Allouah, Akash Dhasade, Rachid Guerraoui, Nirupam Gupta, Anne-Marie Kermarrec, Rafael Pinot, Rafael Pires, Rishi Sharma
27. Generative Modelling of Structurally Constrained Graphs by Manuel Madeira, Clément Vignac, Dorina Thanou, Pascal Frossard
28. Towards the Transferability of Rewards Recovered via Regularized Inverse Reinforcement Learning by Andreas Schlaginhaufen, Maryam Kamgarpour
29. AdaNCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer by Yitao Xu, Tong Zhang, Sabine Süsstrunk
30. JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models by Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko, Francesco Croce, Vikash Sehwag, Edgar Dobriban, Nicolas Flammarion, George J. Pappas, Florian Tramer, Hamed Hassani, Eric Wong
31. Attack-Aware Noise Calibration for Differential Privacy by Bogdan Kulynych, Juan Felipe Gomez, Georgios Kaissis, Flavio Calmon, Carmela Troncoso
32. This Too Shall Pass: Removing Stale Observations in Dynamic Bayesian Optimization by Anthony Bardou, Patrick Thiran, Giovanni Ranieri
33. Why the Metric Backbone Preserves Community Structure by Maximilien Dreveton, Charbel Chucri, Matthias Grossglauser, Patrick Thiran
34. Fast Proxy Experiment Design for Causal Effect Identification by Sepehr Elahi, Sina Akbari, Jalal Etesami, Patrick Thiran, Negar Kiyavash
35. Implicit Bias of Mirror Flow on Separable Data by Scott Pesme, Radu-Alexandru Dragomir, Nicolas Flammarion
36. SGD vs GD: Rank Deficiency in Linear Networks by Aditya Varre, Margarita Sagitova, Nicolas Flammarion
37. A phase transition between positional and semantic learning in a solvable model of dot-product attention by Hugo Cui, Freya Behrens, Florent Krzakala, and Lenka Zdeborová
38. Causal Effect Identification in a Sub-Population with Latent Variables by Amir Mohammad Abouei, Ehsan Mokhtarian, Negar Kiyavash, Matthias Grossglauser
39. QWO: Speeding Up Permutation-Based Causal Discovery in LiGAMs by Mohammad Shahverdikondori, Ehsan Mokhtarian, Negar Kiyavash
40. A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics by Puze Liu, Jonas Günster, Niklas Funk, Simon Gröger, Dong Chen, Haitham Bou Ammar, Julius Jankowski, Ante Marić, Sylvain Calinon, Andrej Orsula, Miguel Olivares-Mendez, Hongyi Zhou, Rudolf Lioutikov, Gerhard Neumann, Amarildo Likmeta, Amirhossein Zhalehmehrabi, Thomas Bonenfant, Marcello Restelli, Davide Tateo, Ziyuan Liu, Jan Peters
41. Deep linear networks for regression are implicitly regularized towards flat minima by Pierre Marion, Lénaïc Chizat
42. The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks by Lénaïc Chizat, Praneeth Netrapalli
43. Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach by Guillaume Wang, Alireza Mousavi-Hosseini, Lénaïc Chizat
44. Neural networks with fast and bounded units learn flexible task abstractions by Kai Sandbrink**, Jan Bauer**, Alexandra Proca**, Christopher Summerfield, Andrew Saxe, Ali Hummos (** denotes yet-to-be-randomized order)
45. Bayes-optimal learning of an extensive-width neural network from quadratically many samples by Antoine Maillard, Emanuele Troiani, Simon Martin, Florent Krzakala, Lenka Zdeborová
46. Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts by Zhitong Gao, Bingnan Li, Mathieu Salzmann, Xuming He
47. Optical Diffusion Models for Image Generation byIlker Oguz, Niyazi Dinc, Mustafa Yildirim, Junjie Ke, Innfarn Yoo, Qifei Wang, Feng Yang , Christophe Moser, Demetri Psaltis