1 citations · 4 across the 23 of their papers we have counts for
23 papers
KletterMix: Climbing Toward High-Quality German Pretraining Data - The Full Report
Maurice Kraus, Ruben Härle, Sebastian Sztwiertnia +5
High-quality pretraining data is a central ingredient in modern language models, but German-language resources remain far less developed than their English counterparts: they are o…
A Sovereign, Open-Source Foundation Model for German and English
Soofi-Team, :, Benedikt Droste +30
We present Soofi S 30B-A3B, a sovereign, open-source Mixture-of-Experts (MoE) hybrid Mamba Transformer foundation model for German and English. Its hybrid design activates only 3B…
COCOLogic-V2: Identifying Logical Inconsistencies via Truly Hard-Negatives
David Steinmann, Antonia Wüst, Kristian Kersting +1
While interpretable models such as concept bottleneck models (CBMs) and program synthesis methods enable verification of model decisions, their evaluation is typically limited to s…
Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?
Nils Grandien, David Steinmann, Felix Friedrich +1
Sparse autoencoders (SAEs) have become an important tool for unsupervised concept discovery in large models. To make the resulting feature spaces more interpretable and manageable,…
Beyond Prompt and Parser Engineering: Soft-Prompt Tuning for Automated LLM Evaluation
Selen Erkan, Bastian Boll, Kristian Kersting +2
Benchmark scores often misrepresent a large language model's (LLM's) knowledge, because they rely, e.g., on the model's ability to follow specific formatting requirements. This esp…
Imitation learning for clinical decision support in pediatric ECMO
Fateme Golivand, Michael Skinner, Saurabh Mathur +5
Pediatric critical care is a dynamic, high-stakes process involving constant monitoring and adjustments in life-saving treatments. Modeling these interventions is crucial for effec…
Neurosymbolic Imitation Learning with Human Guidance: A Privileged Information Approach
Nikhilesh Prabhakar, Varun Balaji, Athresh Karanam +2
Imitation learning is widely used for learning to act in complex environments. While pure neural-based methods handle high dimensional data effectively, they suffer from the requir…
GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning
Hikaru Shindo, Henri Rößler, Quentin Delfosse +1
Neuro-symbolic Reinforcement Learning (NeSy-RL) combines symbolic reasoning with gradient-based optimization to achieve interpretable and generalizable policies. Relational concept…
AtManRL: Towards Faithful Reasoning via Differentiable Attention Saliency
Max Henning Höth, Kristian Kersting, Björn Deiseroth +1
Large language models (LLMs) increasingly rely on chain-of-thought (CoT) reasoning to solve complex tasks, yet a reasoning trace may merely accompany the final answer rather than c…
SocialGrid: A Benchmark for Planning and Social Reasoning in Embodied Multi-Agent Systems
Hikaru Shindo, Hanzhao Lin, Lukas Helff +2
As Large Language Models (LLMs) transition from text processors to autonomous agents, evaluating their social reasoning in embodied multi-agent settings becomes critical. We introd…
LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking
Lukas Helff, Quentin Delfosse, David Steinmann +6
As reinforcement Learning with Verifiable Rewards (RLVR) has become the dominant paradigm for scaling reasoning capabilities in LLMs, a new failure mode emerges: LLMs gaming verifi…
Recursive Inference Machines for Neural Reasoning
Mieszko Komisarczyk, Saurabh Mathur, Maurice Kraus +2
Neural reasoners such as Tiny Recursive Models (TRMs) solve complex problems by combining neural backbones with specialized inference schemes. Such inference schemes have been a ce…
Bounding Hallucinations: Merlin-Arthur Protocols for Mutual-Information Bounds in Language Models
Björn Deiseroth, Max Henning Höth, Kristian Kersting +1
Retrieval-augmented generation (RAG) relies on retrieved context to guide large language models (LLM), yet treats the retrieval as a heuristic rather than verifiable evidence -- le…
Multipole Semantic Attention: A Fast Approximation of Softmax Attention for Pretraining
Rupert Mitchell, Kristian Kersting
Pretraining transformers on long sequences (entire code repositories, collections of related documents) is bottlenecked by quadratic attention costs. We present Multipole Semantic…
Learning from Less: Guiding Deep Reinforcement Learning with Differentiable Symbolic Planning
Zihan Ye, Oleg Arenz, Kristian Kersting
When tackling complex problems, humans naturally break them down into smaller, manageable subtasks and adjust their initial plans based on observations. For instance, if you want t…
Object Centric Concept Bottlenecks
David Steinmann, Wolfgang Stammer, Antonia Wüst +1
Developing high-performing, yet interpretable models remains a critical challenge in modern AI. Concept-based models (CBMs) attempt to address this by extracting human-understandab…
Continual Learning Should Move Beyond Incremental Classification
Rupert Mitchell, Antonio Alliegro, Raffaello Camoriano +17
Continual learning (CL) is the sub-field of machine learning concerned with accumulating knowledge in dynamic environments. So far, CL research has mainly focused on incremental cl…
Interpretable end-to-end Neurosymbolic Reinforcement Learning agents
Nils Grandien, Quentin Delfosse, Kristian Kersting
Deep reinforcement learning (RL) agents rely on shortcut learning, preventing them from generalizing to slightly different environments. To address this problem, symbolic method, t…
Neural Concept Binder
Wolfgang Stammer, Antonia Wüst, David Steinmann +1
The challenge in object-based visual reasoning lies in generating concept representations that are both descriptive and distinct. Achieving this in an unsupervised manner requires…
Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning
Hector Kohler, Quentin Delfosse, Riad Akrour +2
Deep reinforcement learning agents are prone to goal misalignments. The black-box nature of their policies hinders the detection and correction of such misalignments, and the trust…
Where is the Truth? The Risk of Getting Confounded in a Continual World
Florian Peter Busch, Roshni Kamath, Rupert Mitchell +3
A dataset is confounded if it is most easily solved via a spurious correlation, which fails to generalize to new data. In this work, we show that, in a continual learning setting w…
BOWL: A Deceptively Simple Open World Learner
Roshni . R. Kamath, Rupert Mitchell, Subarnaduti Paul +2
Traditional machine learning excels on static benchmarks, but the real world is dynamic and seldom as carefully curated as test sets. Practical applications may generally encounter…
Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents
Quentin Delfosse, Sebastian Sztwiertnia, Mark Rothermel +2
Goal misalignment, reward sparsity and difficult credit assignment are only a few of the many issues that make it difficult for deep reinforcement learning (RL) agents to learn opt…