34 citations · 137 across the 37 of their papers we have counts for
40 papers
VoiceNet: Fine-Grained Voice Understanding Beyond Emotion at Scale
Christoph Schuhmann, Robert Kaczmarczyk, Gollam Rabby +7
Expressive speech synthesis has outpaced expressive speech perception: systems now render fine-grained vocal performances that no public benchmark can score. Most benchmarks for th…
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,…
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL
Nicolas Beltran-Velez, Felix Friedrich, Zhang Xiaofeng +4
Score- and flow-matching models often rely on preference-based reinforcement learning for two purposes: aligning with subjective preferences and, surprisingly, recovering propertie…
Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results
Jan Batzner, Sree Harsha Nelaturu, Damian Stachura +45
AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First…
No Safe Dose: How Training Data Drives Unsafe Image Generation
Felix Friedrich, Lukas Helff, Niharika Hegde +2
Text-to-image models trained on large-scale data often inevitably ingest unsafe content. While some people observe input-output amplifications, it remains unclear whether and how t…
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…
LIME: Making LLM Data More Efficient with Linguistic Metadata Embeddings
Sebastian Sztwiertnia, Felix Friedrich, Kristian Kersting +2
Pre-training decoder-only language models relies on vast amounts of high-quality data, yet the availability of such data is increasingly reaching its limits. While metadata is comm…
ActivationReasoning: Logical Reasoning in Latent Activation Spaces
Lukas Helff, Ruben Härle, Wolfgang Stammer +6
Large language models (LLMs) excel at generating fluent text, but their internal reasoning remains opaque and difficult to control. Sparse autoencoders (SAEs) make hidden activatio…
Beyond Overcorrection: Evaluating Diversity in T2I Models with DivBench
Felix Friedrich, Thiemo Ganesha Welsch, Manuel Brack +2
Current diversification strategies for text-to-image (T2I) models often ignore contextual appropriateness, leading to over-diversification where demographic attributes are modified…
How to Train your Text-to-Image Model: Evaluating Design Choices for Synthetic Training Captions
Manuel Brack, Sudeep Katakol, Felix Friedrich +4
Training data is at the core of any successful text-to-image models. The quality and descriptiveness of image text are crucial to a model's performance. Given the noisiness and inc…
Measuring and Guiding Monosemanticity
Ruben Härle, Felix Friedrich, Manuel Brack +4
There is growing interest in leveraging mechanistic interpretability and controllability to better understand and influence the internal dynamics of large language models (LLMs). H…
SLR: Automated Synthesis for Scalable Logical Reasoning
Lukas Helff, Ahmad Omar, Felix Friedrich +7
We introduce SLR, an end-to-end framework for systematic evaluation and training of Large Language Models (LLMs) via Scalable Logical Reasoning. Given a user's task specification,…
EmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech Emotion Detection
Christoph Schuhmann, Robert Kaczmarczyk, Gollam Rabby +6
Speech emotion recognition (SER) systems are constrained by existing datasets that typically cover only 6-10 basic emotions, lack scale and diversity, and face ethical challenges w…
EmoNet-Face: An Expert-Annotated Benchmark for Synthetic Emotion Recognition
Christoph Schuhmann, Robert Kaczmarczyk, Gollam Rabby +7
Effective human-AI interaction relies on AI's ability to accurately perceive and interpret human emotions. Current benchmarks for vision and vision-language models are severely lim…
AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons
Shaona Ghosh, Heather Frase, Adina Williams +99
The rapid advancement and deployment of AI systems have created an urgent need for standard safety-evaluation frameworks. This paper introduces AILuminate v1.0, the first comprehen…
The Cake that is Intelligence and Who Gets to Bake it: An AI Analogy and its Implications for Participation
Martin Mundt, Anaelia Ovalle, Felix Friedrich +5
In a widely popular analogy by Turing Award Laureate Yann LeCun, machine intelligence has been compared to cake - where unsupervised learning forms the base, supervised learning ad…
MSTS: A Multimodal Safety Test Suite for Vision-Language Models
Paul Röttger, Giuseppe Attanasio, Felix Friedrich +19
Vision-language models (VLMs), which process image and text inputs, are increasingly integrated into chat assistants and other consumer AI applications. Without proper safeguards,…
Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation
David Steinmann, Felix Divo, Maurice Kraus +4
Shortcuts, also described as Clever Hans behavior, spurious correlations, or confounders, present a significant challenge in machine learning and AI, critically affecting model gen…
SCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering in LLMs
Ruben Härle, Felix Friedrich, Manuel Brack +3
Large Language Models (LLMs) have demonstrated remarkable capabilities in generating human-like text, but their output may not be aligned with the user or even produce harmful cont…
LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Inconsistencies
Felix Friedrich, Simone Tedeschi, Patrick Schramowski +5
Building safe Large Language Models (LLMs) across multiple languages is essential in ensuring both safe access and linguistic diversity. To this end, we conduct a large-scale, comp…
LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models
Lukas Helff, Felix Friedrich, Manuel Brack +2
This paper introduces LlavaGuard, a suite of VLM-based vision safeguards that address the critical need for reliable guardrails in the era of large-scale data and models. To this e…
ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming
Simone Tedeschi, Felix Friedrich, Patrick Schramowski +4
When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normali…
Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code
Taishi Nakamura, Mayank Mishra, Simone Tedeschi +42
Pretrained language models are an integral part of AI applications, but their high computational cost for training limits accessibility. Initiatives such as Bloom and StarCoder aim…
Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You
Felix Friedrich, Katharina Hämmerl, Patrick Schramowski +4
Text-to-image generation models have recently achieved astonishing results in image quality, flexibility, and text alignment, and are consequently employed in a fast-growing number…