February 2026

arXiv:2602.21357v1 Announce Type: new Abstract: Bayesian inference for inverse problems involves computing expectations under posterior distributions — e.g., posterior means, variances, or predictive quantities — typically via Monte Carlo (MC) estimation. When the quantity of interest varies significantly under the posterior, accurate estimates demand many samples — a cost often prohibitive for partial differential equation-constrained problems. To address this challenge, we introduce conditional neural control variates, a modular method that learns amortized control variates from joint model-data samples […]

Ver mais

arXiv:2602.21272v1 Announce Type: new Abstract: Hamiltonian Monte Carlo (HMC) is a state of the art method for sampling from distributions with differentiable densities, but can converge slowly when applied to challenging multimodal problems. Running HMC with a time varying Hamiltonian, in order to interpolate from an initial tractable distribution to the target of interest, can address this problem. In conjunction with a weighting scheme to eliminate bias, this can be viewed as a special case of Sequential Monte […]

Ver mais

arXiv:2602.21445v1 Announce Type: new Abstract: Action chunking has recently emerged as a standard practice in flow-based Vision-Language-Action (VLA) models. However, the effect and choice of the execution horizon – the number of actions to be executed from each predicted chunk – remains underexplored. In this work, we first show that varying the execution horizon leads to substantial performance deviations, with performance initially improving and then declining as the horizon increases. To uncover the reasons, we analyze the cross- […]

Ver mais

arXiv:2602.21444v1 Announce Type: new Abstract: 6G is deemed as a key technology to support emerging applications with stringent requirements for highly dependable and timecritical communication. In this paper, we investigate 6G networks integrated with TSN and how to compensate for wireless stochastic behavior which involves a large intrinsic packet delay variation. We evaluate a 6G solution to reduce packet delay variation that is based on de-jittering. For this, we propose to use virtual timeslots for providing the required […]

Ver mais

arXiv:2602.21442v1 Announce Type: new Abstract: The recent field of neural algorithmic reasoning (NAR) studies the ability of graph neural networks (GNNs) to emulate classical algorithms like Bellman-Ford, a phenomenon known as algorithmic alignment. At the same time, recent advances in large language models (LLMs) have spawned the study of mechanistic interpretability, which aims to identify granular model components like circuits that perform specific computations. In this work, we introduce Mechanistic Interpretability for Neural Algorithmic Reasoning (MINAR), an efficient […]

Ver mais

arXiv:2602.21441v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) deliver detailed responses on vision-language tasks, yet remain susceptible to object hallucination (introducing objects not present in the image), undermining reliability in practice. Prior efforts often rely on heuristic penalties, post-hoc correction, or generic decoding tweaks, which do not directly intervene in the mechanisms that trigger object hallucination and thus yield limited gains. To address this challenge, we propose a causal decoding framework that applies targeted causal interventions […]

Ver mais

arXiv:2602.21435v1 Announce Type: new Abstract: Unified Vision-Language Models (UVLMs) aim to advance multimodal learning by supporting both understanding and generation within a single framework. However, existing approaches largely focus on architectural unification while overlooking the need for explicit interaction between the two capabilities during task solving. As a result, current models treat understanding and generation as parallel skills rather than synergistic processes. To achieve real synergy, we introduce the interleaved Analyzing-Drafting problem-solving loop (AD-Loop), a new think paradigm […]

Ver mais

arXiv:2602.21429v1 Announce Type: new Abstract: Flow-based generative models, such as diffusion models and flow matching models, have achieved remarkable success in learning complex data distributions. However, a critical gap remains for their deployment in safety-critical domains: the lack of formal guarantees that generated samples will satisfy hard constraints. We address this by proposing a safety filtering framework that acts as an online shield for any pre-trained generative model. Our key insight is to cooperate with the generative process […]

Ver mais

arXiv:2602.21428v1 Announce Type: new Abstract: Medical Vision Language Models (VLMs) can change their answers when clinicians rephrase the same question, which raises deployment risks. We introduce Paraphrase Sensitivity Failure (PSF)-Med, a benchmark of 19,748 chest Xray questions paired with about 92,000 meaningpreserving paraphrases across MIMIC-CXR and PadChest. Across six medical VLMs, we measure yes/no flips for the same image and find flip rates from 8% to 58%. However, low flip rate does not imply visual grounding: text-only baselines […]

Ver mais

arXiv:2602.21426v1 Announce Type: new Abstract: We consider the problem of sampling from a posterior distribution arising in Bayesian inverse problems in science, engineering, and imaging. Our method belongs to the family of independence Metropolis-Hastings (IMH) sampling algorithms, which are common in Bayesian inference. Relying on the existence of an approximate posterior distribution that is cheaper to sample from but may have significant bias, we introduce Proximal-IMH, a scheme that removes this bias by correcting samples from the approximate […]

Ver mais