4.5k citations · 8.5k across the 90 of their papers we have counts for
22 papers · 1 filter
Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measure
Lukas Aichberger, Kajetan Schweighofer, Sepp Hochreiter
Large Language Models (LLMs) are increasingly employed in real-world applications, driving the need to evaluate the trustworthiness of their generated text. To this end, reliable u…
FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware
Korbinian Pöppel, Maximilian Beck, Sepp Hochreiter
While Transformers and other sequence-parallelizable neural network architectures seem like the current state of the art in sequence modeling, they specifically lack state-tracking…
Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences
Niklas Schmidinger, Lisa Schneckenreiter, Philipp Seidl +7
Language models for biological and chemical sequences enable crucial applications such as drug discovery, protein engineering, and precision medicine. Currently, these language mod…
A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
Thomas Schmied, Thomas Adler, Vihang Patil +6
In recent years, there has been a trend in the field of Reinforcement Learning (RL) towards large action models trained offline on large-scale datasets via sequence modeling. Exist…
The Disparate Benefits of Deep Ensembles
Kajetan Schweighofer, Adrian Arnaiz-Rodriguez, Sepp Hochreiter +1
Ensembles of Deep Neural Networks, Deep Ensembles, are widely used as a simple way to boost predictive performance. However, their impact on algorithmic fairness is not well unders…
On Information-Theoretic Measures of Predictive Uncertainty
Kajetan Schweighofer, Lukas Aichberger, Mykyta Ielanskyi +1
Reliable estimation of predictive uncertainty is crucial for machine learning applications, particularly in high-stakes scenarios where hedging against risks is essential. Despite…
Parameter Efficient Fine-tuning via Explained Variance Adaptation
Fabian Paischer, Lukas Hauzenberger, Thomas Schmied +3
Foundation models (FMs) are pre-trained on large-scale datasets and then fine-tuned for a specific downstream task. The most common fine-tuning method is to update pretrained weigh…
Retrieval-Augmented Decision Transformer: External Memory for In-context RL
Thomas Schmied, Fabian Paischer, Vihang Patil +3
In-context learning (ICL) is the ability of a model to learn a new task by observing a few exemplars in its context. While prevalent in NLP, this capability has recently also been…
Simplified priors for Object-Centric Learning
Vihang Patil, Andreas Radler, Daniel Klotz +1
Humans excel at abstracting data and constructing \emph{reusable} concepts, a capability lacking in current continual learning systems. The field of object-centric learning address…
Contrastive Abstraction for Reinforcement Learning
Vihang Patil, Markus Hofmarcher, Elisabeth Rumetshofer +1
Learning agents with reinforcement learning is difficult when dealing with long trajectories that involve a large number of states. To address these learning problems effectively,…
Comparison Visual Instruction Tuning
Wei Lin, Muhammad Jehanzeb Mirza, Sivan Doveh +4
Comparing two images in terms of Commonalities and Differences (CaD) is a fundamental human capability that forms the basis of advanced visual reasoning and interpretation. It is e…
Improving Uncertainty Estimation through Semantically Diverse Language Generation
Lukas Aichberger, Kajetan Schweighofer, Mykyta Ielanskyi +1
Large language models (LLMs) can suffer from hallucinations when generating text. These hallucinations impede various applications in society and industry by making LLMs untrustwor…
Vision-LSTM: xLSTM as Generic Vision Backbone
Benedikt Alkin, Maximilian Beck, Korbinian Pöppel +2
Transformers are widely used as generic backbones in computer vision, despite initially introduced for natural language processing. Recently, the Long Short-Term Memory (LSTM) has…
A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization
Sebastian Sanokowski, Sepp Hochreiter, Sebastian Lehner
Learning to sample from intractable distributions over discrete sets without relying on corresponding training data is a central problem in a wide range of fields, including Combin…
Large Language Models Can Self-Improve At Web Agent Tasks
Ajay Patel, Markus Hofmarcher, Claudiu Leoveanu-Condrei +3
Training models to act as agents that can effectively navigate and perform actions in a complex environment, such as a web browser, has typically been challenging due to lack of tr…
Energy-based Hopfield Boosting for Out-of-Distribution Detection
Claus Hofmann, Simon Schmid, Bernhard Lehner +2
Out-of-distribution (OOD) detection is critical when deploying machine learning models in the real world. Outlier exposure methods, which incorporate auxiliary outlier data in the…
xLSTM: Extended Long Short-Term Memory
Maximilian Beck, Korbinian Pöppel, Markus Spanring +6
In the 1990s, the constant error carousel and gating were introduced as the central ideas of the Long Short-Term Memory (LSTM). Since then, LSTMs have stood the test of time and co…
VN-EGNN: E(3)-Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification
Florian Sestak, Lisa Schneckenreiter, Johannes Brandstetter +3
Being able to identify regions within or around proteins, to which ligands can potentially bind, is an essential step to develop new drugs. Binding site identification methods can…
Geometry-Informed Neural Networks
Arturs Berzins, Andreas Radler, Eric Volkmann +3
Geometry is a ubiquitous tool in computer graphics, design, and engineering. However, the lack of large shape datasets limits the application of state-of-the-art supervised learnin…
Overcoming Saturation in Density Ratio Estimation by Iterated Regularization
Lukas Gruber, Markus Holzleitner, Johannes Lehner +2
Estimating the ratio of two probability densities from finitely many samples, is a central task in machine learning and statistics. In this work, we show that a large class of kern…
MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations
Benedikt Alkin, Lukas Miklautz, Sepp Hochreiter +1
We introduce MIM (Masked Image Modeling)-Refiner, a contrastive learning boost for pre-trained MIM models. MIM-Refiner is motivated by the insight that strong representations withi…
SymbolicAI: A framework for logic-based approaches combining generative models and solvers
Marius-Constantin Dinu, Claudiu Leoveanu-Condrei, Markus Holzleitner +2
We introduce SymbolicAI, a versatile and modular framework employing a logic-based approach to concept learning and flow management in generative processes. SymbolicAI enables the…