| OpenAssistant Conversations--Democratizing Large Language Model Alignment A Köpf, Y Kilcher, D von Rütte, S Anagnostidis, ZR Tam, K Stevens, ... NeurIPS (Oral) - Datasets and Benchmarks Track, 2023 | 551 | 2023 |
| Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse L Noci, S Anagnostidis, L Biggio, A Orvieto, SP Singh, A Lucchi NeurIPS, 2022 | 78 | 2022 |
| Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes A Delitzas, M Parelli, N Hars, G Vlassis, S Anagnostidis, G Bachmann, ... BMVC (Oral), 2023 | 56* | 2023 |
| Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers S Anagnostidis, D Pavllo, L Biggio, L Noci, A Lucchi, T Hofmann NeurIPS (Spotlight), 2023 | 55 | 2023 |
| Scaling MLPs: A Tale of Inductive Bias G Bachmann, S Anagnostidis, T Hofmann NeurIPS, 2023 | 49 | 2023 |
| Transformer Fusion with Optimal Transport M Imfeld, J Graldi, M Giordano, T Hofmann, S Anagnostidis, SP Singh ICLR, 2023 | 21 | 2023 |
| The curious case of benign memorization S Anagnostidis, G Bachmann, L Noci, T Hofmann ICLR, 2022 | 11 | 2022 |
| Nonblocking execution in GraphBLAS A Mastoras, S Anagnostidis, AJN Yzelman IPDPSW, 2022 | 9 | 2022 |
| Direct-search for a class of stochastic min-max problems S Anagnostidis, A Lucchi, Y Diouane AISTATS, 2021 | 9 | 2021 |
| A Language Model's Guide Through Latent Space D von Rütte, S Anagnostidis, G Bachmann, T Hofmann ICML, 2024 | 8 | 2024 |
| Random Teachers are Good Teachers F Sarnthein, G Bachmann, S Anagnostidis, T Hofmann ICML, 2023 | 8 | 2023 |
| How Susceptible are LLMs to Influence in Prompts? S Anagnostidis, J Bulian COLM, 2024 | 7 | 2024 |
| Design and implementation for nonblocking execution in GraphBLAS: tradeoffs and performance A Mastoras, S Anagnostidis, AJN Yzelman ACM TACO, 2022 | 7 | 2022 |
| Towards Meta-Pruning via Optimal Transport A Theus, O Geimer, F Wicke, T Hofmann, S Anagnostidis, SP Singh ICLR (Spotlight), 2024 | 5 | 2024 |
| Harnessing Synthetic Datasets: The Role of Shape Bias in Deep Neural Network Generalization E Benarous, S Anagnostidis, L Biggio, T Hofmann NeurIPS (Workshop on Synthetic Data Generation with Generative AI), 2023 | 5 | 2023 |
| Navigating Scaling Laws: Compute Optimality in Adaptive Model Training S Anagnostidis, G Bachmann, I Schlag, T Hofmann ICML (Spotlight), 2023 | 3* | 2023 |
| Mastering Spatial Graph Prediction of Road Networks A Sotiris, A Lucchi, T Hofmann ICCV, 2023 | 2 | 2023 |
| Cosmology from Galaxy Redshift Surveys with PointNet S Anagnostidis, A Thomsen, T Kacprzak, T Tröster, L Biggio, A Refregier, ... NeurIPS (Machine Learning and the Physical Sciences), 2022 | 2 | 2022 |
| IC-Portrait: In-Context Matching for View-Consistent Personalized Portrait H Yang, E Simsar, S Anagnostidi, Y Zang, T Hofmann, Z Liu arXiv preprint arXiv:2501.17159, 2025 | 1 | 2025 |
| Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment G Bachmann, S Anagnostidis, A Pumarola, M Georgopoulos, ... ICLR (Oral), 2025 | | 2025 |
Thomas HofmannProfessor of Computer Science, ETH ZurichVerificeret mail på inf.ethz.ch