arXiv subjects

Andreas Krause

Publications and source records attributed to Andreas Krause.

At least 19 recordsLinked to original sources

arXiv2026

On Repulsive and Attractive Teachers: Separating Correctness from Behavior in Self-Distillation

On-policy self-distillation provides dense, token-level supervision by conditioning a model on privileged information and distilling the resulting teacher distribution back into the model. However, privileged information can change not only what the teacher knows, but also how it behaves, entangling correctness-relevant learning signals with unintended behavioral shifts. We study this effect in reasoning tasks by contrasting attractive self-distillation, which moves the model toward a privileged teacher, with repulsive self-distillation, which moves it away from a privileged teacher. We find that both objectives can induce strong and opposing behavioral shifts: attraction suppresses exploratory reasoning and promotes shorter, more confident responses, whereas repulsion increases response length, can trigger unintended switches into a model's latent thinking mode, and ultimately becomes unstable. Motivated by these observations, we study contrastive self-distillation, which combines attraction toward a correct-solution-conditioned teacher with repulsion from an incorrect-solution-conditioned teacher. In contrast to prior work that combines such distillation signals with a GRPO objective, we isolate the self-distillation objective and study its behavior on its own. We find that the shared behavioral shifts of the two teachers largely cancel, leaving a token-level signal that more directly reflects correctness. Across non-thinking, instruct-only, and already-thinking models, this contrastive objective improves reasoning performance while maintaining stable response lengths.

cs.LG↗

arXiv2026

Local Sparsity Enables Unsupervised LLM Safety Detection

Deployment-time safety methods for large language models (LLMs) are predominantly supervised and assume access to unsafe training data. Nevertheless, new attacks and harm categories regularly arise, not captured by models trained in such a supervised fashion. An alternative approach is to view this problem through the lens of anomaly detection, namely, to rely solely on modeling safe data and flagging out-of-distribution inputs. However, LLM activations lie in a high-dimensional space, raising concerns about whether anomaly detection is statistically feasible. We show that, under the linear representation hypothesis (LRH), there may indeed be hope. In the LRH concept space, which is typically recovered via a sparse autoencoder (SAE), nearby points share a small common active support. Using this local sparsity insight, we propose a framework for locally masked SAE-based anomaly detection, supported by theoretical justifications. We validate it on various architectures and datasets, including both capability-testing datasets and safety-specific datasets. Finally, when we allow algorithms to use 1% out-of-distribution data for calibration, locally sparse methods achieve near-optimal performance, demonstrating their ability to capture meaningful safety information while using only 1-2% of SAE neurons for computation.

cs.LG↗

arXiv2026

TARC: Time-Adaptive Robotic Control

Most robotic systems rely on fixed-frequency discrete-time controllers, creating a trade-off between the efficiency of low-frequency control and the responsiveness of high-frequency feedback. As a result, systems typically default to high control rates for robustness, at the cost of wasted inference and unnecessary actuation. Addressing this, we introduce Time-Adaptive Robotic Control (TARC), a reinforcement learning framework in which the policy jointly predicts a control action and its duration of application. TARC learns temporally extended actions by optimizing task performance under soft or hard constraints on the number of control switches, enabling adaptive modulation of control rates. We evaluate TARC on two robotic hardware platforms: a high-speed RC car and the Unitree Go1 quadruped, and on a vision-language action model in simulation, where each query incurs a costly transformer forward pass. Across all settings, TARC matches the performance of high-frequency discrete-time controllers while operating at less than half their control frequency. Unlike fixed-rate controllers, TARC adapts its control frequency online, allocating high-frequency feedback only when required.

cs.RO↗

arXiv2026

Optimistic Online LQR via Intrinsic Rewards

Optimism in the face of uncertainty is a popular approach to balance exploration and exploitation in reinforcement learning. Here, we consider the online linear quadratic regulator (LQR) problem, i.e., to learn the LQR corresponding to an unknown linear dynamical system by adapting the control policy online based on closed-loop data collected during operation. In this work, we propose Intrinsic Rewards LQR (IR-LQR), an optimistic online LQR algorithm that applies the idea of intrinsic rewards originating from reinforcement learning and the concept of variance regularization to promote uncertainty-driven exploration. IR-LQR typically retains the structure of a standard LQR synthesis problem by only modifying the cost function, resulting in an intuitively pleasing, simple, computationally cheap, and efficient algorithm. This is in contrast to existing optimistic online LQR formulations that rely on more complicated iterative search algorithms or solve computationally demanding optimization problems. We show that IR-LQR achieves the optimal worst-case regret rate of $\sqrt{T}$, and compare it to various state-of-the-art online LQR algorithms via numerical experiments carried out on an aircraft pitch angle control and an unmanned aerial vehicle example.

eess.SY↗

arXiv2026

Safe Exploration via Policy Priors

Safe exploration is a key requirement for reinforcement learning (RL) agents to learn and adapt online, beyond controlled (e.g. simulated) environments. In this work, we tackle this challenge by utilizing suboptimal yet conservative policies (e.g., obtained from offline data or simulators) as priors. Our approach, SOOPER, uses probabilistic dynamics models to optimistically explore, yet pessimistically fall back to the conservative policy prior if needed. We prove that SOOPER guarantees safety throughout learning, and establish convergence to an optimal policy by bounding its cumulative regret. Extensive experiments on key safe RL benchmarks and real-world hardware demonstrate that SOOPER is scalable, outperforms the state-of-the-art and validate our theoretical guarantees in practice.

cs.LG↗

arXiv2026

Enhancing VLM Reward Models Through Structure-Aware Fine-Tuning

Designing effective reward functions remains a major bottleneck in Reinforcement Learning (RL). Recent work uses large foundation Vision-Language Models (VLMs) as reward models, computing text-observation similarity to bypass manual reward engineering. Although promising, these rewards are often noisy and unreliable, limiting their direct utility during deployment. We present Structure-Aware Fine-Tuning (SAFT), a simple, self-supervised method that refines these imperfect reward signals online without access to ground-truth supervision. SAFT leverages intrinsic structural priors to regularize the VLM's latent space via LoRA adapters. We rigorously evaluate SAFT across a spectrum of base model capabilities to demonstrate its versatility. Our results show that SAFT consistently denoises the reward landscape, yielding faster policy convergence and substantially improved alignment (EPIC distance) relative to the underlying base model, suggesting that failures can often be attributed to structural brittleness rather than semantic misunderstanding. By replacing extensive human preference annotation with structural inductive biases inherent to the task, SAFT offers a scalable path for stabilizing text-conditioned RL and underscores the broader value of incorporating task structure as a general inductive bias.

cs.LG↗

arXiv2026

What Matters for Simulation to Online Reinforcement Learning on Real Robots

We investigate what specific design choices enable successful online reinforcement learning (RL) on physical robots. Across 100 real-world training runs on three distinct robotic platforms, we systematically ablate algorithmic, systems, and experimental decisions that are typically left implicit in prior work. We find that some widely used defaults can be harmful, while a set of robust, readily adopted design choices within standard RL practice yield stable learning across tasks and hardware. These results provide the first large-sample empirical study of such design choices, enabling practitioners to deploy online RL with lower engineering effort.

cs.RO↗

arXiv2026

Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models

In-context learning is commonly interpreted as a form of conditional inference, in which the prompt specifies a context and the model's output is treated as an estimate of the corresponding conditional distribution. If this interpretation holds, then LLM estimates should satisfy basic probabilistic identities. In particular, the law of total probability asserts that prior-weighted conditional distributions aggregate into population-level marginals over any valid partition of the population. In this work, we investigate to what extent LLM estimates adhere to this self-consistency principle. We use binary trees as an evaluation scaffold to recursively partition a population into increasingly fine-grained subpopulations. We then prompt LLMs with verbalized subpopulation descriptions in context, aggregate the resulting estimates back into population-level estimates, and compare them across partitions of varying granularity. Applying this protocol across problem domains and state-of-the-art frontier models, we show widespread violations of basic consistency properties. An in-depth study of persona prompting reveals a pattern we call the macro fallacy: estimates reconstructed from more fine-grained subpopulation responses are often better aligned with human reference data than direct population-level estimates. This effect persists across variations in tree structure and estimation task, and can be partially recovered through implicit prompting. Together, these findings suggest that models possess relevant subpopulation knowledge but do not reliably propagate it into aggregate estimates. This gap establishes statistical self-consistency as an unsaturated, reference-free criterion for evaluating LLMs.

cs.CL↗

arXiv2026

Uncertainty Quantification for Flow-Based Vision-Language-Action Models

Vision-language-action models (VLAs) combine vision-language backbones with expressive generative action heads trained via flow matching on large-scale robotic datasets. Despite their strong empirical performance in robotic manipulation, VLAs lack mechanisms to quantify confidence in their predictions and to detect when their actions may be unreliable. This presents a critical limitation for real-world deployment in non-stationary environments, where models inevitably encounter scenarios outside their pretraining distribution and may fail without warning. To address this, we derive an efficient method for quantifying epistemic uncertainty in flow-matching models by leveraging velocity-field disagreement (VFD) across a small ensemble. We successfully use this uncertainty estimate for failure detection during deployment and active fine-tuning of flow-based VLAs. To this end, we propose SAVE, a framework for uncertainty-guided active multitask fine-tuning that reduces the number of costly expert demonstrations required to adapt VLAs to new tasks. Through extensive experiments on the LIBERO benchmark, we demonstrate that VFD yields better-calibrated uncertainty estimates predictive of downstream performance, that VFD achieves strong performance in detecting failures, and that uncertainty-guided data acquisition with SAVE requires at least 22% fewer samples than baselines. In summary, our work shows that quantifying epistemic uncertainty in flow-based VLAs improves both failure awareness and adaptation. Project website: tum-lsy.github.io/uq_vla/.

cs.RO↗

arXiv2026

Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules

Standard flow and diffusion pre-training matches the distribution of available data (e.g., molecules), which often covers only a small fraction of the valid design space. In generative discovery, however, one aims to sample valid new-to-nature designs, assigned negligible probability under, and thus inaccessible to, standard models fitted to the observed data. To overcome this limitation, we depart from data distribution matching and view a generative model through its generable set: the region it covers with non-negligible probability. This allows to introduce a new learning principle for out-of-distribution flow modeling: enlarging a model's generable set to increase coverage of the valid design space. We propose Active Flow Expansion (ActFlow), a continued pre-training method that employs verifier feedback to expand a pre-trained model over new valid regions by iteratively adapting to synthetic data generated through active exploration in the learned flow representation. Theoretically, we establish to our knowledge first-of-their-kind statistical learning guarantees for out-of-distribution flow modeling, analyzing generable set expansion as a local-to-global reachability process over a learned representation. Empirically, we assess ActFlow with suitable out-of-distribution generative modeling metrics across small organic molecules, mid-sized drug-like molecules, therapeutic peptides, and protein sequence design tasks. Results show that ActFlow expands valid coverage far beyond the region modeled by the initial pre-trained model, significantly outperforming widely adopted synthetic flow pre-training methods.

cs.LG↗

arXiv2026

Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport

The success of generative molecular design hinges on a model's steerability toward high-reward samples. Because many molecular properties are intrinsically linked to molecular size, accurately capturing the joint distribution of properties and the number of atoms is essential. However, current diffusion and flow-based models fix the number of atoms, which ultimately limits their ability to navigate this complex relationship. To address this, we introduce Morph, a flexible-size generative model for conditional and unconditional 3D molecular design based on geometric graphs. By dynamically adapting size, Morph can seamlessly integrate existing structural priors, like scaffolds, and significantly enhances property steering. We show that Morph matches current fixed-size state-of-the-art models while offering the benefit of unparalleled sampling flexibility. We demonstrate out-of-distribution generation in regimes where previous models fail, paving the way for enhanced generative modeling for molecular design.

cs.LG↗

arXiv2026

ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning

Reinforcement Learning from Human Feedback (RLHF) has become the standard for aligning Large Language Models (LLMs), yet its efficacy is bottlenecked by the high cost of acquiring preference data, especially in low-resource and expert domains. To address this, we introduce ACTIVEULTRAFEEDBACK, a modular active learning pipeline that leverages uncertainty estimates to dynamically identify the most informative responses for annotation. Our pipeline facilitates the systematic evaluation of standard response selection methods alongside DOUBLE REVERSE THOMPSON SAMPLING (DRTS) and DELTAUCB, two novel methods prioritizing response pairs with large predicted quality gaps, leveraging recent results showing that such pairs provide good signals for fine-tuning. Our experiments demonstrate that ACTIVEULTRAFEEDBACK yields high-quality datasets that lead to significant improvements in downstream performance, notably achieving comparable or superior results with as little as one-sixth of the annotated data relative to static baselines. Our pipeline is available at https://github.com/lasgroup/ActiveUltraFeedback and our preference datasets at https://huggingface.co/ActiveUltraFeedback.

cs.LG↗

arXiv2026

Scalable Ride-Sourcing Vehicle Rebalancing with Service Accessibility Guarantee: A Constrained Mean-Field Reinforcement Learning Approach

The expansion of ride-sourcing services such as Uber and Lyft has reshaped urban transportation by offering flexible, on-demand mobility via mobile applications. Despite convenience, these platforms confront significant operational challenges, particularly vehicle rebalancing-strategic repositioning of a fleet of vehicles to address spatiotemporal mismatches in supply and demand. Inadequate rebalancing results in prolonged rider waiting times and inefficient vehicle utilization, but also leads to fairness issues, such as the inequitable distribution of service and disparities in driver income. To tackle these, we introduce continuous-state mean-field control (MFC) and mean-field reinforcement learning (MFRL) models with continuous repositioning actions. MFC and MFRL offer scalable solutions by modeling each vehicle's behavior through interaction with the vehicle distribution, rather than with individual vehicles. This mitigates the curse of dimensionality with respect to the number of agents, enabling coordination across large fleets with significantly reduced computational complexity and eliminating the need to retrain the model when fleet size changes. To ensure equitable service access across geographic regions, we integrate an accessibility constraint into models and derive rebalancing policies that strike a balance between high fulfillment of rider demand and fair coverage of vehicle supply. Extensive evaluation using data-driven simulation of Shenzhen demonstrates the efficiency and robustness of our approach. Remarkably, it scales to tens of thousands of vehicles, with training times comparable to linear programming rebalancing. Besides, our policies effectively explore the efficiency-equity Pareto front, outperforming conventional benchmarks across key metrics like fleet utilization, fulfilled requests, and pickup distance, while ensuring equitable service access.

cs.LG↗

arXiv2026

Position: Anthropomorphic Misalignment Research Needs Stronger Evidence

We argue that many Anthropomorphic Misalignment Research (AMR) studies need stronger evidence to ensure that they can provide a robust foundation for critical safety decisions, such as model deployment and regulation. By evaluating failure modes across different misalignment concepts, such as deception, emergent misalignment, and sycophancy, we show how conceptual ambiguity, non-robust datasets, experimental design, and insufficient causal interventions can lead to overinterpretation of model behaviors. This position paper aims to offer guidance on evidentiary considerations that can help improve methodological rigor in AMR. To achieve this, we provide a clear call to action through a proposed framework of evidence levels and a diagnostic checklist. These shared standards will enable more productive scientific discourse and ensure that claims about AI risks rest on solid empirical foundations.

cs.CY↗

arXiv2026

Constrained Flow Optimization via Sequential Fine Tuning for Molecular Design

Adapting generative foundation models, in particular diffusion and flow models, to optimize given reward functions (e.g., binding affinity) while satisfying constraints (e.g., molecular synthesizability) is fundamental for their adoption in real-world scientific discovery applications such as molecular design or protein engineering. While recent works have introduced scalable methods for reward-guided fine-tuning of such models via reinforcement learning and control schemes, it remains an open problem how to algorithmically trade-off reward maximization and constraint satisfaction in a reliable and predictable manner. Motivated by this challenge, we first present a rigorous framework for Constrained Generative Optimization, which brings an optimization viewpoint to the introduced adaptation problem and retrieves the relevant task of constrained generation as a sub-case. Then, we introduce Constrained Flow Optimization (CFO), an algorithm that automatically and provably balances reward maximization and constraint satisfaction by reducing the original problem to sequential fine-tuning via established, scalable methods. We provide convergence guarantees for constrained generative optimization and constrained generation via CFO. Ultimately, we present an experimental evaluation of CFO on both synthetic, yet illustrative, settings, and a molecular design task. Across these evaluations, CFO achieves consistent increases in reward while ensuring high constraint satisfaction, showcasing its practical utility for constrained generative optimization.

cs.LG↗

arXiv2026

Sampling-Based Safe Reinforcement Learning

Safe exploration remains a fundamental challenge in reinforcement learning (RL), limiting the deployment of RL agents in the real world. We propose Sampling-Based Safe Reinforcement Learning (SBSRL), a model-based RL algorithm that maintains safety throughout the learning process by enforcing constraints jointly across a finite set of dynamics samples. This formulation approximates an intractable worst-case optimization over uncertain dynamics and enables practical safety guarantees in continuous domains. We further introduce an exploration strategy based on constraining epistemic uncertainty, eliminating the need for explicit exploration bonuses. Under regularity conditions, we derive high-probability guarantees of safety throughout learning and a finite-time sample complexity bound for recovering a near-optimal policy. Empirically, SBSRL achieves safe and efficient exploration both in simulation and in real robotic hardware, and readily extends to practical deep-ensemble implementations that scale to high-dimensional continuous control problems.

cs.LG↗

arXiv2026

Test-time Offline Reinforcement Learning on Goal-related Experience

Foundation models compress a large amount of information in a single, large neural network, which can then be queried for individual tasks. There are strong parallels between this widespread framework and offline goal-conditioned reinforcement learning algorithms: a universal value function is trained on a large number of goals, and the policy is evaluated on a single goal in each test episode. Extensive research in foundation models has shown that performance can be substantially improved through test-time training, specializing the model to the current goal. We find similarly that test-time offline reinforcement learning on experience related to the test goal can lead to substantially better policies at modest compute costs. We propose a novel self-supervised data selection criterion, which selects transitions from an offline dataset according to their relevance to the current state and quality with respect to the evaluation goal. We demonstrate across a wide range of high-dimensional loco-navigation and manipulation tasks that fine-tuning a policy on the selected data for a few gradient steps leads to significant performance gains over standard offline pre-training. Our goal-conditioned test-time training (GC-TTT) algorithm applies this routine in a receding-horizon fashion during evaluation, adapting the policy to the current trajectory as it is being rolled out. Finally, we study compute allocation at inference, demonstrating that, at comparable costs, GC-TTT induces performance gains that are not achievable by scaling model size.

cs.LG↗

arXiv2026

POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles

Balancing exploration and exploitation is a core challenge in sequential decision-making and black-box optimization. We introduce POETS ($\textbf{Po}$licy $\textbf{E}$nsembles for $\textbf{T}$hompson $\textbf{S}$ampling), a novel framework that bridges uncertainty quantification and policy optimization. Our approach is grounded in the insight that policies trained with Kullback-Leibler (KL) regularization implicitly encode an underlying reward function. Building on this, POETS bypasses the complex, nested process of training an uncertainty-aware reward model and separately fitting a policy to this model. Instead, we directly train a policy ensemble to capture epistemic uncertainty by matching implicitly encoded reward functions to online, bootstrapped data. To overcome the prohibitive compute and memory constraints of ensembling Large Language Models (LLMs), POETS utilizes an efficient architecture: the ensemble shares a pre-trained backbone while maintaining diversity through independent Low-Rank Adaptation (LoRA) branches. Theoretically, we prove that POETS implicitly conducts KL-regularized Thompson sampling and thus inherits strong cumulative regret bounds of ${\mathcal O}(\sqrt{T γ_T})$. Empirically, we demonstrate that POETS achieves state-of-the-art sample efficiency across diverse scientific discovery domains, including protein search and quantum circuit design. Furthermore, it improves the optimization trajectories of reinforcement learning, proving particularly robust in off-policy settings with experience replay or in small dataset regimes.

cs.LG↗