BilAI at Flagship Conferences
The BilAI cluster is strongly represented at the most relevant flagship conferences in the fields of artificial intelligence and machine learning. Our researchers are presenting their latest work and contributing to key discussions that shape the future of the field.
These conferences also offer a great opportunity to connect with BilAI experts, exchange ideas, and explore possibilities for collaboration.
We’re proud to share our presence at these important venues—feel free to reach out and meet us there!
The 42nd International Conference on Machine Learning (ICML)
July 13-19, 2025 | Vancouver
Accepted papers by BilAI key researchers:
A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks by Thomas Schmied, Thomas Adler, Vihang Patil, Maximilian Beck, Korbinian Pöppel, Johannes Brandstetter, Günter Klambauer, Razvan Pascanu, Sepp Hochreiter
Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models by Alina Shutova, Vladimir Malinovskii, Ivan Ermakov, Surkov Nikita, Denis Mazur, Denis Kuznedelev, Vage Egiazarian, Dan Alistarh
DEALing with image reconstruction: Deep Attentive Least squares by Mehrsa Pourya, Erich Kobler, Michael Unser, Sebastian Neumayer
Differentially Private Federated k-Means Clustering with Server-Side Data by Jonathan Scott, Christoph Lampert, David Saulpic
EvoPress: Accurate Dynamic Model Compression via Evolutionary Search by Oliver Sieberling, Denis Kuznedelev, Eldar Kurtic, Dan Alistarh
Geometry-Informed Neural Networks by Arturs Berzins, Andreas Radler, Eric Volkmann, Sebastian Sanokowski, Sepp Hochreiter, Johannes Brandstetter
Layer-wise Quantization for Quantized Optimistic Dual Averaging by Anh Duc Nguyen, Ilia Markov, Zhengqing Wu, Ali Ramezani-Kebrya, Kimon Antonakopoulos, Dan Alistarh, Volkan Cevher
Mechanistic PDE Networks for Discovery of Governing Equations by Adeel Pervez, Efstratios Gavves, Francesco Locatello
Neural Collapse Beyond the Unconstrainted Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime by Diyuan Wu, Marco Mondelli
Optimal Decision Tree Pruning Revisited: Algorithms and Complexity by Juha Harviainen, Frank Sommer, Manuel Sorge, Stefan Szeider
QuEST: Quantized Gradient Estimation for Accurate Training of Extremely Low-Bitwith Large Language Models by Andrei Panferov, Jiale Chen, Soroush Tabesh, Mahdi Nikdan, Dan Alistarh
Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization by Simone Bombari, Marco Mondelli
Test-Time Training Provably Improves Transformers as In-context Learners by Halil Alperen Gozeten, Muhammed Emrullah Ildiz, Xuechen Zhang, Mahdi Soltanolkotabi, Marco Mondelli, Samet Oymak
The Disparate Benefits of Deep Ensembles by Kajetan Schweighofer, Adrián Arnaiz-Rodríguez, Sepp Hochreiter, Nuria Oliver
xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference by Maximilian Beck, Korbinian Pöppel, Phillip Lippe, Richard Kurle, Patrick Blies, Günter Klambauer, Sebastian Böck, Sepp Hochreiter
The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval
July 13-18, 2025 | Padua
Accepted papers by BilAI key researchers:
Reassessing the Effectiveness of Reinforcement Learning based Recommender Systems for Sequential Recommendation by Dilina Chandika Rajapakse, Dietmar Jannach
A Worrying Reproducibility Study of Intent-Aware Recommendation Models by Faisal Shehzad, Maurizio Ferrari Dacrema, Dietmar Jannach
OnSET: Ontology and Semantic Exploration Toolkit by Benedikt Kantz, Kevin Innerebner, Peter Waldert, Stefan Lengauer, Elisabeth Lex, Tobias Schreck
The 13th International Conference on Learning Representations (ICLR)
April 24-28, 2025 | Singapore
Accepted papers by BilAI key researchers:
Benchmarking Predictive Coding Networks -- Made Simple by Luca Pinchetti, Chang Qi, Oleh Lokshyn, Cornelius Emde, Amine M'Charrak, Mufeng Tang, Simon Frieder, Bayar Menzat, Gaspard Oliviers, Rafal Bogacz, Thomas Lukasiewicz, Tommaso Salvatori
Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences by Niklas Schmidinger, Lisa Schneckenreiter, Philipp Seidl, Johannes Schimunek, Pieter-Jan Hoedt, Johannes Brandstetter, Andreas Mayr, Sohvi Luukkonen, Sepp Hochreiter, Günter Klambauer
Can LLMs Separate Instructions From Data? And What Do We Even Mean By That? by Egor Zverev, Sahar Abdelnabi, Soroush Tabesh, Mario Fritz, Christoph Lampert
FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware by Korbinian Pöppel, Maximilian Beck, Sepp Hochreiter
High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws by Muhammed Ildiz, Halil Gozeten, Ege Taga, Marco Mondelli, Samet Oymak
How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations by Siddhartha Gairola, Moritz Böhle, Francesco Locatello, Bernt Schiele
Improving Uncertainty Estimation through Semantically Diverse Language Generation by Lukas Aichberger, Kajetan Schweighofer, Mykyta Ielanskyi, Sepp Hochreiter
LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics by Thomas Robert, Mher Safaryan, Ionut-Vlad Modoranu, Dan Alistarh
MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Masked Image Modeling Representations by Benedikt Alkin, Lukas Miklautz, Sepp Hochreiter, Johannes Brandstetter
Near, far: Patch-ordering enhances vision foundation models' scene understanding by Valentinos Pariza, Mohammadreza Salehi, Gertjan J Burghouts, Francesco Locatello, Yuki Asano
Privacy-Aware Lifelong Learning by Ozan Özdenizci, Elmar Rueckert, Robert Legenstein
Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics by Sebastian Sanokowski, Wilhelm Berghammer, Haoyu Wang, Martin Ennemoser, Sepp Hochreiter, Sebastian Lehner
Scalable Mechanistic Neural Networks by Jiale Chen, Dingling Yao, Adeel Pervez, Dan Alistarh, Francesco Locatello
Shh, don't say that! Domain Certification in LLMs by Cornelius Emde, Alasdair Paren, Preetham Arvind, Maxime Kayser, Tom Rainforth, Thomas Lukasiewicz, Philip Torr, Adel Bibi
The Computational Complexity of Positive Non-Clashing Teaching in Graphs by Robert Ganian, Liana Khazaliya, Fionn Mc Inerney, Mathis Rocton
The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws by Tian Jin, Ahmed Imtiaz Humayun, Utku Evci, Suvinay Subramanian, Amir Yazdanbakhsh, Dan Alistarh, Gintare Karolina Dziugaite
Towards Certification of Uncertainty Calibration under Adversarial Attacks by Cornelius Emde, Francesco Pinto, Thomas Lukasiewicz, Philip Torr, Adel Bibi
Training One-Dimensional Graph Neural Networks is NP-Hard by Robert Ganian, Mathis Rocton, Simon Wietheger
Unifying Causal Representation Learning with the Invariance Principle by Dingling Yao, Dario Rancati, Riccardo Cadei, Marco Fumero, Francesco Locatello
Vision-LSTM: xLSTM as Generic Vision Backbone by Benedikt Alkin, Maximilian Beck, Korbinian Pöppel, Sepp Hochreiter, Johannes Brandstetter
Wasserstein Distances, Neuronal Entanglement, and Sparsity by Shashata Sawmya, Linghao Kong, Ilia Markov, Dan Alistarh, Nir Shavit
Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse by Arthur Jacot, Peter Súkeník, Zihan Wang, Marco Mondelli
