Abstract
We investigate the open problem of the existence of genuinely unextendible product bases (GUPBs), that is, multipartite unextendible product bases (UPBs) which remain unextendible even with respect to biproduct vectors across all bipartitions of the parties. To this end, we exploit the well-known connection between UPBs and graph theory through orthogonality graphs and orthogonal representations, together with recent progress in this framework, and employ forbidden induced subgraph characterizations to single out the admissible local orthogonality graphs for GUPBs. Using this approach, we establish that GUPBs of size thirteen in three-qutrit systems-the smallest candidate GUPBs-do not exist. We further provide a partial characterization of graphs relevant to larger bases and systems with ququart subsystems.

Abstract
Understanding posterior contraction behavior in Bayesian hierarchical models is of fundamental importance, but progress in this question is relatively sparse in comparison to the theory of density estimation. In this paper, we study two classes of hierarchical models for grouped data, where observations within groups are exchangeable. Using moment tensor decomposition of the distribution of the latent variables, we establish a precise equivalence between the class of Admixture models (such as Latent Dirichlet Allocation) and the class of Mixture of products of multinomial distributions. This correspondence enables us to leverage the result from the latter class of models, which are more well-understood, so as to arrive at the identifiability and posterior contraction rates in both classes under conditions much weaker than in existing literature. For instance, our results shed light on cases where the topics are not linearly independent or the number of topics is misspecified in the admixture setting. Finally, we analyze individual documents' latent allocation performance via the borrowing of strength properties of hierarchical Bayesian modeling. Many illustrations and simulations are provided to support the theory.

Abstract
Vehicle data is essential for advancing data-driven development throughout the automotive lifecycle, including requirements engineering, design, verification, and validation, and post-deployment optimization. Developers currently collect data in a decentralized and fragmented manner across simulations, test benches, and real-world driving, resulting in data silos, inconsistent formats, and limited interoperability. This leads to redundant efforts, inefficient integration, and suboptimal use of data. This fragmentation results in data silos, inconsistent storage structures, and limited interoperability, leading to redundant data collection, inefficient integration, and suboptimal application. To address these challenges, this article presents a structured literature review and develops an inductive taxonomy for automotive data. This taxonomy categorizes data according to its sources and applications, improving data accessibility and utilization. The analysis reveals a growing emphasis on real-world driving and machine learning applications while highlighting a critical gap in data availability for requirements engineering. By providing a systematic framework for structuring automotive data, this research contributes to more efficient data management and improved decision-making in the automotive industry.

Abstract
A pair of graphs $(\Gamma,\Sigma)$ is called unstable if their direct product $\Gamma\times\Sigma$ admits automorphisms not from $\mathrm{Aut}(\Gamma)\times\mathrm{Aut}(\Sigma)$, and such automorphisms are said to be unexpected. The stability of a graph $\Gamma$ refers to that of $(\Gamma,K_2)$. While the stability of individual graphs has been relatively well studied, much less is known for graph pairs. In this paper, we propose a conjecture that provides the best possible reduction of the stability of a graph pair to the stability of a single graph. We prove one direction of this conjecture and establish partial results for the converse. This enables the determination of the stability of a broad class of graph pairs, with complete results when one factor is a cycle.

Abstract
We introduce and study two Maker-Breaker-like games for constructing planar graphs: the edge drawing game, where two players take turns drawing non-intersecting edges between points in the plane, and the circle packing game, where the players take turns placing disjoint circles in the plane. Both games produce planar graphs: the edge drawing game results in a plane graph drawing, and the circle packing game yields a planar graph via the contact graph of the packing. For both games, we give necessary conditions under which a given planar graph can be constructed. We also show that the two games are indeed different by giving a class of graphs which can be constructed in one but not the other.

Abstract
Generalized Category Discovery (GCD) is an open-world problem that clusters unlabeled data by leveraging knowledge from partially labeled categories. A key challenge is that unlabeled data may contain both known and novel categories. Existing approaches suffer from two main limitations. First, they fail to exploit multi-granularity conceptual information in visual data, which limits representation quality. Second, most assume that the number of unlabeled categories is known during training, which is impractical in real-world scenarios. To address these issues, we propose a Multi-Granularity Conceptual Experts (MGCE) framework that adaptively mines visual concepts and integrates multi-granularity knowledge for accurate category discovery. MGCE consists of two modules: (1) Dynamic Conceptual Contrastive Learning (DCCL), which alternates between concept mining and dual-level representation learning to jointly optimize feature learning and category discovery; and (2) Multi-Granularity Experts Collaborative Learning (MECL), which extends the single-expert paradigm by introducing additional experts at different granularities and by employing a concept alignment matrix for effective cross-expert collaboration. Importantly, MGCE can automatically estimate the number of categories in unlabeled data, making it suitable for practical open-world settings. Extensive experiments on nine fine-grained visual recognition benchmarks demonstrate that MGCE achieves state-of-the-art results, particularly in novel-class accuracy. Notably, even without prior knowledge of category numbers, MGCE outperforms parametric approaches that require knowing the exact number of categories, with an average improvement of 3.6\%. Code is available at https://github.com/HaiyangZheng/MGCE.

Abstract
Continual learning involves learning from a stream of data without repetition of data points, a scenario that is inherently complex due to distributional shift across tasks. We propose a query-only attention mechanism that discards keys and values, yet preserves the core inductive bias of transformer architectures. In continual learning scenarios, this simplified mechanism significantly mitigates both loss of plasticity and catastrophic forgetting, outperforming baselines such as selective re-initialization. We establish a conceptual link between query-only attention, full transformer attention, and model agnostic meta-learning, framing them as instances of meta-learning. We further provide intuition for why query-based models and attention networks help preserve plasticity in continual settings. Finally, through preliminary Hessian spectrum analysis, we observe that models maintaining higher curvature rank across tasks tend to retain plasticity. Our findings suggest that full attention may not be essential for capturing the benefits of meta-learning in continual learning.

Abstract
Knowledge graphs (KGs) are increasingly used to represent biomedical information in structured, interpretable formats. However, existing biomedical KGs often focus narrowly on molecular interactions or adverse events, overlooking the rich data found in drug leaflets. In this work, we present (1) a hackable, end-to-end pipeline to create KGs from unstructured online content using a web scraper and an LLM; and (2) a curated dataset, MEDAKA, generated by applying this method to publicly available drug leaflets. The dataset captures clinically relevant attributes such as side effects, warnings, contraindications, ingredients, dosage guidelines, storage instructions and physical characteristics. We evaluate it through manual inspection and with an LLM-as-a-Judge framework, and compare its coverage with existing biomedical KGs and databases. We expect MEDAKA to support tasks such as patient safety monitoring and drug recommendation. The pipeline can also be used for constructing KGs from unstructured texts in other domains. Code and dataset are available at https://github.com/medakakg/medaka.

Abstract
We study the problem of zero-shot link prediction on knowledge graphs (KGs), which requires models to generalize over novel entities and novel relations. Knowledge graph foundation models (KGFMs) address this task by enforcing equivariance over both nodes and relations, learning from structural properties of nodes and relations, which are then transferable to novel graphs with similar structural properties. However, the conventional notion of deterministic equivariance imposes inherent limits on the expressive power of KGFMs, preventing them from distinguishing structurally similar but semantically distinct relations. To overcome this limitation, we introduce probabilistic node-relation equivariance, which preserves equivariance in distribution while incorporating a principled randomization to break symmetries during inference. Building on this principle, we present Flock, a KGFM that iteratively samples random walks, encodes them into sequences via a recording protocol, embeds them with a sequence model, and aggregates representations of nodes and relations via learned pooling. Crucially, Flock respects probabilistic node-relation equivariance and is a universal approximator for isomorphism-invariant link-level functions over KGs. Empirically, Flock perfectly solves our new diagnostic dataset Petals where current KGFMs fail, and achieves state-of-the-art performances on entity- and relation prediction tasks on 54 KGs from diverse domains.

Abstract
High-assurance reasoning, particularly in critical domains such as law and medicine, requires conclusions that are accurate, verifiable, and explicitly grounded in evidence. This reasoning relies on premises codified from rules, statutes, and contracts, inherently involving defeasible or non-monotonic logic due to numerous exceptions, where the introduction of a single fact can invalidate general rules, posing significant challenges. While large language models (LLMs) excel at processing natural language, their capabilities in standard inference tasks do not translate to the rigorous reasoning required over high-assurance text guidelines. Core reasoning challenges within such texts often manifest specific logical structures involving negation, implication, and, most critically, defeasible rules and exceptions. In this paper, we propose a novel neurosymbolically-grounded architecture called LOGicalThought (LogT) that uses an advanced logical language and reasoner in conjunction with an LLM to construct a dual symbolic graph context and logic-based context. These two context representations transform the problem from inference over long-form guidelines into a compact grounded evaluation. Evaluated on four multi-domain benchmarks against four baselines, LogT improves overall performance by 11.84% across all LLMs. Performance improves significantly across all three modes of reasoning: by up to +10.2% on negation, +13.2% on implication, and +5.5% on defeasible reasoning compared to the strongest baseline.