Recent advances in world models have shown promise for modeling future dynamics of environmental states, enabling agents to reason and act without accessing real environments. Current methods mainly perform single-step or fixed-horizon rollouts, leaving their potential for complex task planning under-exploited. We propose Imagine-then-Plan (texttt{ITP}), a unified framework for agent learning via lookahead imagination, where an agent’s policy model interacts with the learned world model, yielding multi-step “imagined” trajectories. Since the imagination horizon may vary by tasks and […]

Ver mais

arXiv:2603.08800v1 Announce Type: new Abstract: Recent advances in multimodal large language models largely rely on CLIP-based visual encoders, which emphasize global semantic alignment but struggle with fine-grained visual understanding. In contrast, DINOv3 provides strong pixel-level perception yet lacks coarse-grained semantic abstraction, leading to limited multi-granularity reasoning. To address this gap, we propose Granulon, a novel DINOv3-based MLLM with adaptive granularity augmentation. Granulon introduces a text-conditioned granularity Controller that dynamically adjusts the visual abstraction level according to the semantic […]

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

Finalist teams advance in the Amazon Nova AI Challenge: Trusted AI Track Top eight university teams move on to head-to-head finals focused on AI security for code generation. Conversational AI Staff writer June 24, 02:11 PM June 30, 02:49 PM Since November 2024, ten top university teams from around the world have competed in the inaugural Amazon Nova AI Challenge: Trusted AI Track, focused on strengthening security in AI coding assistants and developing new automated methods to red-team […]

Ver mais

In this work, we propose a notion of practical learnability grounded in finite sample settings, and develop a conjugate learning theoretical framework based on convex conjugate duality to characterize this learnability property. Building on this foundation, we demonstrate that training deep neural networks (DNNs) with mini-batch stochastic gradient descent (SGD) achieves global optima of empirical risk by jointly controlling the extreme eigenvalues of a structure matrix and the gradient energy, and we establish a corresponding convergence theorem. We […]

Ver mais

Graph Federated Learning (GFL) enables distributed graph representation learning while protecting the privacy of graph data. However, GFL suffers from heterogeneity arising from diverse node features and structural topologies across multiple clients. To address both types of heterogeneity, we propose a novel graph Federated learning method via Semantic and Structural Alignment (FedSSA), which shares the knowledge of both node features and structural topologies. For node feature heterogeneity, we propose a novel variational model to infer class-wise node distributions, […]

Ver mais

The rapid integration of AI algorithms in safety-critical applications such as autonomous driving and healthcare is raising significant concerns about the ability to meet stringent safety standards. Traditional tools for formal safety verification struggle with the black-box nature of AI-driven systems and lack the flexibility needed to scale to the complexity of real-world applications. In this paper, we present a data-driven approach for safety verification and synthesis of black-box systems with discrete-time stochastic dynamics. We employ the concept […]

Ver mais

arXiv:2604.05030v1 Announce Type: new Abstract: We present Phase-Associative Memory (PAM), a recurrent sequence model in which all representations are complex-valued, associations accumulate in a matrix state $S_{t}$ $in$ $mathbb{C}^{d times d}$ via outer products, and retrieval operates through the conjugate inner product $K_t^* cdot Q_t / sqrt{d}$. At $sim$100M parameters on WikiText-103, PAM reaches validation perplexity 30.0, within $sim$10% of a matched transformer (27.1) trained under identical conditions, despite $4times$ arithmetic overhead from complex computation and no custom […]

Ver mais

While shopping on a major e-commerce site, I wanted to get an answer to an obscure question about a certain product. Not finding the answer immediately on the product page, I thought I’d try clicking the AI shopping assistant helper tool to ask this question. I waited with anticipation for an answer I would expect be more informative and useful than a standard search result. But it was not to be. The AI tool had nothing worthwhile. Then […]

Ver mais

arXiv:2602.04402v2 Announce Type: replace Abstract: Performative predictions influence the very outcomes they aim to forecast. We study performative predictions that affect a sample (e.g., only existing users of an app) and/or the whole population (e.g., all potential app users). This raises the question of how well models generalize under performativity. For example, how well can we draw insights about new app users based on existing users when both of them react to the app’s predictions? We address this […]

Ver mais