相关论文: MiraBench: Evaluating Action-Conditioned Reliabili…

Active Learning (AL) is an active domain of research, but is seldom used in the industry despite the pressing needs. This is in part due to a misalignment of objectives, while research strives at getting the best results on selected…

Video generation models have achieved remarkable progress in creating high-quality, photorealistic content. However, their ability to accurately simulate physical phenomena remains a critical and unresolved challenge. This paper presents…

Robot learning methods have recently made great strides, but generalization and robustness challenges still hinder their widespread deployment. Failing to detect and address potential failures renders state-of-the-art learning systems not…

Uncertainty quantification is essential for assessing the reliability and trustworthiness of modern AI systems. Among existing approaches, verbalized uncertainty, where models express their confidence through natural language, has emerged…

Current video benchmarks for multimodal large language models (MLLMs) focus on event recognition, temporal ordering, and long-context recall, but overlook a harder capability required for expert procedural judgment: tracking how ongoing…

When evaluating the performance of clinical machine learning models, one must consider the deployment population. When the population of patients with observed labels is only a subset of the deployment population (label selection), standard…

ML models are increasingly deployed in settings with real world interactions such as vehicles, but unfortunately, these models can fail in systematic ways. To prevent errors, ML engineering teams monitor and continuously improve these…

Action-conditioned video models offer a promising path to building general-purpose robot simulators that can improve directly from data. Yet, despite training on large-scale robot datasets, current state-of-the-art video models still…

Despite the remarkable advances of Large Language Models (LLMs) across diverse cognitive tasks, the rapid enhancement of these capabilities also introduces emergent deceptive behaviors that may induce severe risks in high-stakes…

Machine learning models only provide probabilistic guarantees on the expected loss of random samples from the distribution represented by their training data. As a result, a model with high accuracy, may or may not be reliable for…

Machine Vision Components (MVC) are becoming safety-critical. Assuring their quality, including safety, is essential for their successful deployment. Assurance relies on the availability of precisely specified and, ideally,…

Meta-learning algorithms enable rapid adaptation to new tasks with minimal data, a critical capability for real-world robotic systems. This paper evaluates Model-Agnostic Meta-Learning (MAML) combined with Trust Region Policy Optimization…

World models - learned internal simulators of environment dynamics - are rapidly becoming foundational to autonomous decision-making in robotics, autonomous vehicles, and agentic AI. By predicting future states in compressed latent spaces,…

Humans develop an understanding of intuitive physics through active interaction with the world. This approach is in stark contrast to current video models, such as Sora, which rely on passive observation and therefore struggle with grasping…

Explanations for AI models in high-stakes domains like medicine often lack verifiability, which can hinder trust. To address this, we propose an interactive agent that produces explanations through an auditable sequence of actions. The…

A world model creates a surrogate world to train a controller and predict safety violations by learning the internal dynamic model of systems. However, the existing world models rely solely on statistical learning of how observations change…

AI models are increasingly prevalent in high-stakes environments, necessitating thorough assessment of their capabilities and risks. Benchmarks are popular for measuring these attributes and for comparing model performance, tracking…

Artificial agents now generate behavior rich enough to invite trust, surprise, and concern, yet our evaluation tools still privilege capability scores over psychological structure. This paper argues that the philosophical impasse between…

While recent video world models can generate highly realistic videos, their ability to perform semantic reasoning and planning remains unclear and unquantified. We introduce Target-Bench, the first benchmark that enables comprehensive…

Multimodal Large Language Models are primarily trained and evaluated on aligned image-text pairs, which leaves their ability to detect and resolve real-world inconsistencies largely unexplored. In open-domain applications visual and textual…