Archimedes Shines Bright at NeurIPS 2024
The NeurIPS 2024 conference featured a strong presence from the Archimedes Research Unit at Athena Research Center, showcasing 38 groundbreaking contributions across machine learning and optimization. Our researchers presented research ranging from game theory to graph meta networks, cementing their role as leaders in the AI research community. Below an overview of their impressive contributions:
Oral Presentation
- Ioannis Kalogeropoulos, Giorgos Bouritsas, Yannis Panagakis “Scale Equivariant Graph Meta Networks”
Spotlight
- George Christodoulou, Alkmini Sgouritsa, Ioannis Vlachos “Mechanism Design Augmented with Output Advice”
- Jikai Jin, Vasilis Syrgkanis “Learning Linear Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity”
- D. Legacci, P. Mertikopoulos, C. H. Papadimitriou, G. Piliouras, B. S. R. Pradelski
“No-Regret Learning in Harmonic Games: Extrapolation in the Presence of Conflicting Interests”
- Deepak Ravikumar, Efstathia Soufleri and Kaushik Roy “Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature”
- C. Tzamos, V. Kontonis, M. Ma “Active classification with Few Querries under Misspecification “
Posters
- Nivasini Ananthakrishnan, Nika Haghtalab, Chara Podimata, Kunhe Yang
“Is Knowledge Power? On the (Im)Possibility of Learning from Strategic Interactions”
- Angelos Assos, Yuval Dagan, Constantinos Daskalakis “Maximizing Utility in Multi-Agent Environments by Anticipating the Behavior of Other Learners”
- E. Balkanski, V. Gkatzelis, G. Shahkarami “Randomized Strategic Facility Location with Predictions
- Vahid Balazadeh, Keertana Chidambaram, Viet Nguyen, Rahul Krishnan, Vasilis Syrgkanis “Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity”
- Francesca Babiloni, Alexandros Lattas, Jiankang Deng, Stefanos Zafeiriou “ID-to-3D: “Expressive ID-guided 3D Heads via Score Distillation Sampling”
- Yang Cai, Constantinos Daskalakis, Haipeng Luo, Chen-Yu Wei, Weiqiang Zheng “On Tractable Φ-Equilibria in Non-Concave Games”
- Daniel Chee Hian Tan, David Chanin, Aengus Lynch, Brooks Paige, Dimitrios Kanoulas, Adrià Garriga-Alonso, Robert Kirk “Analysing the Generalisation and Reliability of Steering Vectors”
- Robby Costales, Stefanos Nikolaidis “Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity”
- Giannis Daras, Weili Nie, Karsten Kreis, Alex Dimakis, Morteza Mardani, Nikola Borislavov Kovachki, Arash Vahdat “Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models”
- Simone Foti, Stefanos Zafeiriou, Tolga Birdal “UV-free Texture Generation with Denoising and Geodesic Heat Diffusion”
- Charles Guille-Escuret, Pierre-Andre Noel, Ioannis Mitliagkas, David Vazquez, Joao Monteiro “Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection
A novel approach to detecting out-of-distribution samples, enhancing the reliability of machine learning systems”
- Guru Guruganesh, Yoav Kolumbus, Jon Schneider, Inbal Talgam-Cohen, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Joshua R. Wang, S. Matthew Weinberg “Contracting with a Learning Agent”
- Rashida Hakim, Ana-Andreea Stoica, Christos Papadimitriou, Mihalis Yannakakis “The Fairness-Quality Tradeoff in Clustering”
- Alkis Kalavasis, Amin Karbasi, Argyris Oikonomou, Katerina Sotiraki, Grigoris Velegkas, Manolis Zampetakis “Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models”
- Fivos Kalogiannis, Jingming Yan, Ioannis Panageas “Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem”
- Jeongyeol Kwon, Shie Mannor, Constantine Caramanis, Yonathan Efroni “RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation”
- Jeffrey Li, Alex Fang, Georgios Smyrnis, Maor Ivgi, Matt Jordan, Samir Yitzhak Gadre, Hritik Bansal, Etash Kumar Guha, Sedrick Keh, Kushal Arora, Saurabh Garg, Rui Xin, Niklas Muennighoff, Reinhard Heckel, Jean Mercat, Mayee F Chen, Suchin Gururangan, Mitchell Wortsman, Alon Albalak, Yonatan Bitton, Marianna Nezhurina, Amro Kamal Mohamed Abbas, Cheng-Yu Hsieh, Dhruba Ghosh, Joshua P Gardner, Maciej Kilian, Hanlin Zhang, Rulin Shao, Sarah M Pratt, Sunny Sanyal, Gabriel Ilharco, Giannis Daras, Kalyani Marathe, Aaron Gokaslan, Jieyu Zhang, Khyathi Chandu, Thao Nguyen, Igor Vasiljevic, Sham M. Kakade, Shuran Song, Sujay Sanghavi, Fartash Faghri, Sewoong Oh, Luke Zettlemoyer, Kyle Lo, Alaaeldin El-Nouby, Hadi Pouransari, Alexander T Toshev, Stephanie Wang, Dirk Groeneveld, Luca Soldaini, Pang Wei Koh, Jenia Jitsev, Thomas Kollar, Alex Dimakis, Yair Carmon, Achal Dave, Ludwig Schmidt, Vaishaal Shankar “DataComp-LM: In search of the next generation of training sets for language models”
- Vijay Lingam, Atula Tejaswi Neerkaje, Aditya Vavre, Aneesh Shetty, Gautham Krishna Gudur, Joydeep Ghosh, Eunsol Choi, Alex Dimakis, Aleksandar Bojchevski, Sujay Sanghavi “SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors”
- K. Lotidis, A. Giannou, P. Mertikopoulos, N. Bambos “Accelerated Regularized “Learning in Finite N-Person Games”
- Thomas Melistas, Nikos Spyrou, Nefeli Gkouti, Pedro Sanchez, Athanasios Vlontzos, Yannis Panagakis, Giorgos Papanastasiou, Sotirios A. Tsaftaris “Benchmarking Counterfactual Image Generation”
- Anay Mehrotra, Manolis Zampetakis, Paul Kassianik, Blaine Nelson, Hyrum S Anderson, Yaron Singer, Amin Karbasi “Tree of Attacks: Jailbreaking Black-Box LLMs Automatically”
- Georgios Mentzelopoulos, Evangelos Chatzipantazis, Ashwin G Ramayya, Michelle Hedlund, Vivek Buch, Kostas Daniilidis, Konrad Kording, Flavia Vitale “Neural decoding from stereotactic EEG: accounting for electrode variability across subjects”
- Théo Moutakanni, Maxime Oquab, Marc Szafraniec, Maria Vakalopoulou, Piotr Bojanowski “You Don’t Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning”
- J. Oldfield, M. Georgopoulos, G. Chrysos, C. Tzelepis, Yannis Panagakis, M. Nicolaou, J. Deng, I. Patras “Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization”
- Stefanos Pertigkiozoglou, Evangelos Chatzipantazis, Shubhendu Trivedi, Kostas Daniilidis “Improving Equivariant Model Training via Constraint Relaxation”
- Jiyuan Tan, Jose Blanchet, Vasilis Syrgkanis “Consistency of Neural Causal Partial Identification”
- Tsikouras Nikos, Caramanis Constantinos, Tzamos Christos “Optimization Can Learn Johnson-Lindenstrauss Embeddings”
- Wang, Y., Feng, D., Dai, Y., Chen, Z., Huang, J., Ananiadou, S., Xie, Q., and H. Wang HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection.
- Qianqian Xie, Weiguang Han, Zhengyu Chen, Ruoyu Xiang, Xiao Zhang, Yueru He, Mengxi Xiao, Dong Li, Yongfu Dai, Duanyu Feng, Yijing Xu, Haoqiang Kang, Ziyan Kuang, Chenhan Yuan, Kailai Yang, Zheheng Luo, Tianlin Zhang, Zhiwei Liu, Guojun Xiong, Zhiyang Deng, Yuechen Jiang, Zhiyuan Yao, Haohang Li, Yangyang Yu, Gang Hu, Jiajia Huang, Xiao-Yang Liu, Alejandro Lopez-Lira, Benyou Wang, Yanzhao Lai, Hao Wang, Min Peng, Sophia Ananiadou, Jimin Huang “FinBen: An Holistic Financial Benchmark for Large Language Models”
- Yinshuang Xu, Dian Chen, Katherine Liu, Sergey Zakharov, Rares Andrei Ambrus, Kostas Daniilidis, Vitor Campagnolo Guizilini “$SE(3)$ Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation”
- Yang, K., Liu, Z., Xie, Q., Huang, J., Zhang, T. and Ananiadou Sophia, “MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Model”
Archimedes presence at NeurIPS 2024 demonstrates our commitment to excellence and pushing the boundaries of AI research. Many congratulations to our researchers for their great work!
Ioannis Kalogeropoulos (Archimedes PhD Student, NKUA) presenting joint work with Giorgos Bouritsas (Archimedes Post Doc) and Yannis Panagakis (Archimedes Lead Researcher, Prof NKUA)
Nikos Tsikouras (Archimedes PhD Student, NKUA) presenting joint work with Caramanis Constantinos (Archimedes Lead Researcher, Prof. UT Austin) and Tzamos Christos (Archimedes Lead Researcher, Prof NKUA)
