arXiv:2604.01378v1 Announce Type: new Abstract: Offline reinforcement learning (RL) has received increasing attention for learning policies from previously collected data without interaction with the real environment, which is particularly important in high-stakes applications. While a growing body of work has…
arXiv:2604.00394v2 Announce Type: replace Abstract: Estimated density is often interpreted as indicating how typical a sample is under a model. Yet deep models trained on one dataset can assign higher density to simpler out-of-distribution (OOD) data than to in-distribution test…
arXiv:2604.01398v1 Announce Type: new Abstract: This report is part of the Qumphy project (22HLT01 Qumphy) that is funded by the European Union and is dedicated to the development of measures to quantify the uncertainties associated with Machine Learning algorithms applied…
arXiv:2507.04754v2 Announce Type: replace-cross Abstract: In designing generative models, it is commonly believed that in order to learn useful latent structure, we face a fundamental tension between expressivity and structure. In this paper we challenge this view by proposing a…
arXiv:2604.01411v1 Announce Type: new Abstract: Modern LLMs scale at test-time, e.g. via repeated sampling, where inference cost grows with model size and the number of samples. This creates a trade-off that pretraining scaling laws, such as Chinchilla, do not address.…
arXiv:2511.18123v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have become indispensable for multimodal reasoning, yet their representations often encode and amplify demographic biases, resulting in biased associations and misaligned predictions in downstream tasks. Such behavior undermines fairness and distorts the…
arXiv:2604.01430v1 Announce Type: new Abstract: Language Models (LMs) exhibit two distinct mechanisms for knowledge acquisition: in-weights learning (i.e., encoding information within the model weights) and in-context learning (ICL). Although these two modes offer complementary strengths, in-weights learning frequently struggles to…
arXiv:2603.11147v3 Announce Type: replace-cross Abstract: Audiovisual (AV) archives in museums and galleries are growing rapidly, but much of this material remains effectively locked away because it lacks consistent, searchable metadata. Existing method for archiving requires extensive manual effort. We address…
arXiv:2604.01476v1 Announce Type: new Abstract: Reinforcement learning for LLMs is vulnerable to reward hacking, where models exploit shortcuts to maximize reward without solving the intended task. We systematically study this phenomenon in coding tasks using an environment-manipulation setting, where models…
arXiv:2604.01279v1 Announce Type: new Abstract: We introduce Sven (Singular Value dEsceNt), a new optimization algorithm for neural networks that exploits the natural decomposition of loss functions into a sum over individual data points, rather than reducing the full loss to…
