AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code. Verified code generation, in which an agent produces both an implementation and a machine-checked proof of its specification, offers a stronger path toward trustworthy AI-generated software. Existing benchmarks in this direction either focus on individual functions or only evaluate proof generation with provided implementations. It is still an open question whether agents can m
We introduce Shieldstral, a 3B-parameter policy-adaptive multimodal safety classifier that matches or outperforms models nearly 7times its size on text safety benchmarks and sets a new state of the art on multimodal safety classification. Shieldstral formulates content moderation as a binary question-answering task. This simple formulation unifies diverse moderation tasks into a single yes/no problem, enabling heterogeneous safety datasets with divergent taxonomies to be consolidated under one t
Deploying navigation systems at scale requires a recipe that minimizes sensor assumptions, generalizes across robot embodiments, and trains efficiently. Yet, today's best systems depend on depth sensors, multi-camera rigs, or pre-built maps, limiting the hardware they support and increasing deployment cost. We introduce Robostral Navigate, an 8B vision-language model built around this scalability objective. The model consumes only a stream of monocular RGB images - the most ubiquitous sensor acr
The Continual Learning (CL) literature has long been driven by the goal of mitigating catastrophic forgetting. This objective rests on a pervasive, often unstated assumption: that a lifelong learner should approximate the Joint-Task Learning (JTL) solution and retain all previously acquired knowledge. We challenge this retention-centered premise, arguing that in non-stationary environments prioritizing retention can impede real-time adaptation. Shifting the focus to the Average Lifelong Error (A
Adversarial robustness evaluations of large language models (LLMs) typically report attack success rate (ASR) under fixed query budgets, implicitly treating all attacks as equally costly. In practice, the computational expense of different attack strategies can vary by orders of magnitude. Consequently, ASR at a fixed budget can obscure the true effort required to jailbreak a model, thereby making it hard to determine whether an attack's cost justifies its payoff to the attacker. We propose a co
Effective model-based reinforcement learning in stochastic environments requires planning that accounts for predictive uncertainty. Propagating full state distributions analytically offers a principled way to do this, but has traditionally required restrictive policy or reward structures to remain tractable. Consequently, modern deep reinforcement learning has largely retreated to either stochastic sampling, which introduces significant target variance, or deterministic point estimates that igno
Agent security is widely treated as a question about action content. Defenses ask whether an instruction looks malicious. Benchmarks ask whether an agent performs a harmful sounding action. \textbf{We argue that agent security is fundamentally a contextual problem, and that the current content based framing systematically misdefines it.} A command to ``delete user data'' might be a routine administrative request or a prompt injection attacking production systems, and the content alone cannot dis
Current AI safety evaluation and benchmarking frameworks predominantly rely on Western-centric culture-agnostic defaults that mask critical regional laws, socio-linguistic nuances, and cultural taboos, leaving Vision-Language Models (VLMs) vulnerable in global deployments. We introduce Pluralis v0.1: a novel multimodal, multi-regional, and multilingual dataset built from a culture-first perspective. Spanning 6,448 prompts across six Asia-Pacific countries (Bangladesh, India, Korea, Pakistan, Sin
Emergent misalignment (EM) is a phenomenon in which models generalize with narrow fine-tuning, leading to broad (yet uneven) misalignment across evaluation questions. We study EM and its variability directly through the components of fine-tuning: training dynamics, model priors, and data. (1) We first explored how in-domain training loss relates to out-of-domain alignment scores across datasets and model families. Then, we tried to induce potential alternative local minima through different lear
What would it mean to have a scientific understanding of AI? Models are not static objects: they are snapshots of time-evolving processes shaped by data, objectives, architectures, and optimization dynamics. Yet much of AI research treats models as fixed artifacts, analyzing behaviors after training rather than asking why they emerge. This position paper argues that a science of AI must move beyond post-hoc fixes and study the training dynamics that produce model behavior. Such a science should