Backdoor attacks enable adversaries to embed malicious behavior into machine learning models by poisoning training data with triggers. Researchers focused largely on backdoors in unimodal models. However, the rise of multimodal systems, e.g., vision–language models (VLMs) and multimodal large language models (MLLMs), has significantly increased the attack surface. Multimodal backdoors can exploit cross-modal triggers, representation-level manipulation, instruction-conditioned behaviors, and test-time activation pathways that are not available in unimodal models. Nevertheless, quantifying progress in this field remains challenging due […]

Ver mais

Contextual Reinforcement Learning (CRL) tackles the problem of solving a set of related Contextual Markov Decision Processes (CMDPs) that vary across different context variables. Traditional approaches–independent training and multi-task learning–struggle with either excessive computational costs or negative transfer. A recently proposed multi-policy approach, Model-Based Transfer Learning (MBTL), has demonstrated effectiveness by strategically selecting a few tasks to train and zero-shot transfer. However, CMDPs encompass a wide range of problems, exhibiting structural properties that vary from problem to problem. […]

Ver mais

arXiv:2603.15699v1 Announce Type: new Abstract: The energy consumption of Large Language Models (LLMs) is raising growing concerns due to their adverse effects on environmental stability and resource use. Yet, these energy costs remain largely opaque to users, especially when models are accessed through an API — a black box in which all information depends on what providers choose to disclose. In this work, we investigate inference time measurements as a proxy to approximate the associated energy costs of […]

Ver mais

arXiv:2603.22964v1 Announce Type: cross Abstract: Generalization is a central concept in machine learning theory, yet for quantum models, it is predominantly analyzed through uniform bounds that depend on a model’s overall capacity rather than the specific function learned. These capacity-based uniform bounds are often too loose and entirely insensitive to the actual training and learning process. Previous theoretical guarantees have failed to provide non-uniform, data-dependent bounds that reflect the specific properties of the learned solution rather than the […]

Ver mais

arXiv:2603.05201v1 Announce Type: cross Abstract: Data normalisation, a common and often necessary preprocessing step in engineering and scientific applications, can severely distort the discovery of governing equations by magnitudebased sparse regression methods. This issue is particularly acute for the Sparse Identification of Nonlinear Dynamics (SINDy) framework, where the core assumption of sparsity is undermined by the interaction between data scaling and measurement noise. The resulting discovered models can be dense, uninterpretable, and physically incorrect. To address this critical […]

Ver mais

Dario Amodei envisions a “compressed 21st century” where powerful AI achieves one hundred years of progress in one decade. This radical upside includes curing most diseases, doubling human lifespans, and eliminating global poverty. By accelerating science and supporting democracy, AI offers an inspiring, humanitarian future worth fighting for.

Ver mais

We address the problem of training conversion prediction models in advertising domains under privacy constraints, where direct links between ad clicks and conversions are unavailable. Motivated by privacy-preserving browser APIs and the deprecation of third-party cookies, we study a setting where the learner observes a sequence of clicks and a sequence of conversions, but can only link a conversion to a set of candidate clicks (an attribution set) rather than a unique source. We formalize this as learning […]

Ver mais

arXiv:2604.08555v1 Announce Type: new Abstract: Physician-physician discussions of patient cases represent a rich source of clinical knowledge and reasoning that could feed AI agents to enrich and even participate in subsequent interactions. However, privacy regulations and ethical considerations severely restrict access to such data. While synthetic data generation using Large Language Models offers a promising alternative, existing approaches primarily focus on patient-physician interactions or structured medical records, leaving a significant gap in physician-to-physician communication synthesis. We present SynDocDis, […]

Ver mais

arXiv:2602.04872v1 Announce Type: new Abstract: Recent progress has rapidly advanced our understanding of the mechanisms underlying in-context learning in modern attention-based neural networks. However, existing results focus exclusively on unimodal data; in contrast, the theoretical underpinnings of in-context learning for multi-modal data remain poorly understood. We introduce a mathematically tractable framework for studying multi-modal learning and explore when transformer-like architectures can recover Bayes-optimal performance in-context. To model multi-modal problems, we assume the observed data arises from a latent […]

Ver mais

Learning models that can handle distribution shifts is a key challenge in domain generalization. Invariance learning, an approach that focuses on identifying features invariant across environments, improves model generalization by capturing stable relationships, which may represent causal effects when the data distribution is encoded within a structural equation model (SEM) and satisfies modularity conditions. This has led to a growing body of work that builds on invariance learning, leveraging the inherent heterogeneity across environments to develop methods that […]

Ver mais