VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge

Current multimodal benchmarks often conflate reasoning with domain-specific knowledge, making it difficult to isolate and evaluate general reasoning abilities in non-expert settings. To address this, we introduce VisualPuzzles, a benchmark that targets visual reasoning while deliberately minimizing reliance on specialized knowledge. VisualPuzzles consists of diverse questions spanning five categories: algorithmic, analogical, deductive, inductive, and spatial reasoning. One major source of our questions is manually translated logical reasoning questions from the Chinese Civil Service Examination. Experiments show that VisualPuzzles requires significantly less intensive domain-specific knowledge and more complex reasoning compared to benchmarks like MMMU, enabling us to better evaluate genuine multimodal reasoning. Evaluations show that state-of-the-art multimodal large language models consistently lag behind human performance on VisualPuzzles, and that strong performance on knowledge-intensive benchmarks does not necessarily translate to success on reasoning-focused, knowledge-light tasks. Additionally, reasoning enhancements such as scaling up inference compute (with "thinking" modes) yield inconsistent gains across models and task types, and we observe no clear correlation between model size and performance. We also found that models exhibit different reasoning and answering patterns on VisualPuzzles compared to benchmarks with heavier emphasis on knowledge. VisualPuzzles offers a clearer lens through which to evaluate reasoning capabilities beyond factual recall and domain knowledge.

Unsupervised Learning of Phylogenetic Trees via Split-Weight Embedding

Unsupervised learning has become a staple in classical machine learning, successfully identifying clustering patterns in data across a broad range of domain applications. Surprisingly, despite its accuracy and elegant simplicity, unsupervised learning has not been sufficiently exploited in the realm of phylogenetic tree inference. The main reason for the delay in adoption of unsupervised learning in phylogenetics is the lack of a meaningful, yet simple, way of embedding phylogenetic trees into a vector space. Here, we propose the simple yet powerful split-weight embedding which allows us to fit standard clustering algorithms to the space of phylogenetic trees. We show that our split-weight embedded clustering is able to recover meaningful evolutionary relationships in simulated and real (Adansonia baobabs) data.