Large language models (LLMs) have advanced rapidly in recent years (Brown et al., 2020; Touvron et al., 2023), demonstrating remarkable progress in complex reasoning (Guo et al., 2025), fluent text generation, and even automated proof discovery (Yu et al., 2025). These advances have spurred growing adoption of LLMs across education, data science, and research, where they are increasingly used for tutoring, problem explanation, data analysis, and hypothesis formulation (Wu et al., 2021; Polu and Sutskever, 2020; Khan et al., 2023; Gao et al., 2023). However, despite their broad deployment in quantitative domains, the field of statistics, which forms the foundation of modern data-driven science, has received little attention in LLM evaluation. Statistics differs fundamentally from other quantitative disciplines. Rather than focusing on symbolic manipulation or fixed-form computation, it emphasizes reasoning under uncertainty, connecting probability theory, inference, regression, Bayesian analysis, multivariate methods, and asymptotic theory into a unified framework. Yet existing large-scale LLM evaluations rarely cover these competencies: statistical problems account for less than 3% of recent reasoning benchmarks (Paster et al., 2025), and when included, they are typically treated as isolated probability puzzles without structured categorization or coverage of inferential reasoning (Gao et al., 2024). This gap makes it impossible to rigorously assess whether LLMs can function as capable statisticians or support data-driven scientific discovery. To bridge this critical gap, we introduce StatEval, the first large-scale benchmark dedicated to evaluating large language models on statistical reasoning. With nearly 20,000 meticulously curated problems, StatEval covers the entire spectrum of statistics, from basic undergraduate exercises to advanced research-level challenges, captures the full 2 breadth and depth of the discipline, as illustrated in Figure 1.

Knowin Figure 1: For an Embodied Agent, using physical tools is crucial in many tasks. Phys-ToolBench (Bottom) systematically evaluates the understanding of physical tools of multimodal LLMs. The benchmark is designed with three progressive levels of difficulty and employs a Visual Question Answering (VQA) format. Notice that in the actual benchmark, tools in the images are numerically labeled, and images here are for illustrative purposes only. The ability to use, understand, and create tools is a hallmark of human intelligence, enabling sophisticated interaction with the physical world. For any general-purpose intelligent agent to achieve true versatility, it must also master these fundamental skills. While modern Multimodal Large Language Models (MLLMs) leverage their extensive common knowledge for high-level planning in embodied AI and in downstream Vision-Language-Action (VLA) models, the extent of their true understanding of physical tools remains unquantified. To bridge this gap, we present PhysT oolBench, the first benchmark dedicated to evaluating the comprehension of physical tools by MLLMs. Our benchmark is structured as a Visual Question Answering (VQA) dataset comprising over 1,000 image-text pairs. Our comprehensive evaluation of 32 MLLMs--spanning proprietary, open-source, specialized embodied, and backbones in VLAs--reveals a significant deficiency in the tool understanding.

Understanding environmental ecosystems is vital for the sustainable management of our planet. However,existing physics-based and data-driven models often fail to generalize to varying spatial regions and scales due to the inherent data heterogeneity presented in real environmental ecosystems. This generalization issue is further exacerbated by the limited observation samples available for model training. To address these issues, we propose Geo-STARS, a geo-aware spatio-temporal modeling framework for predicting stream water temperature across different watersheds and spatial scales. The major innovation of Geo-STARS is the introduction of geo-aware embedding, which leverages geographic information to explicitly capture shared principles and patterns across spatial regions and scales. We further integrate the geo-aware embedding into a gated spatio-temporal graph neural network. This design enables the model to learn complex spatial and temporal patterns guided by geographic and hydrological context, even with sparse or no observational data. We evaluate Geo-STARS's efficacy in predicting stream water temperature, which is a master factor for water quality. Using real-world datasets spanning 37 years across multiple watersheds along the eastern coast of the United States, Geo-STARS demonstrates its superior generalization performance across both regions and scales, outperforming state-of-the-art baselines. These results highlight the promise of Geo-STARS for scalable, data-efficient environmental monitoring and decision-making.

This work has been submitted to the IEEE for possible publication. Abstract--In endovascular surgery, endovascular intervention-ists push a thin tube called a catheter, guided by a thin wire to a treatment site inside the patient's blood vessels to treat various conditions such as blood clots, aneurysms, and malformations. Guidewires with robotic tips can enhance maneuverability, but they present challenges in modeling and control. Automation of soft robotic guidewire navigation has the potential to overcome these challenges, increasing the precision and safety of endovascular navigation. In other surgical domains, end-to-end imitation learning has shown promising results. Thus, we develop a transformer-based imitation learning framework with goal conditioning, relative action outputs, and automatic contrast dye injections to enable generalizable soft robotic guidewire navigation in an aneurysm targeting task. We train the model on 36 different modular bifurcated geometries, generating 647 total demonstrations under simulated fluoroscopy, and evaluate it on three previously unseen vascular geometries. The model can autonomously drive the tip of the robot to the aneurysm location with a success rate of 83% on the unseen geometries, outperforming several baselines. In addition, we present ablation and baseline studies to evaluate the effectiveness of each design and data collection choice. IAGNOSIS and treatment of vascular conditions require an endovascular interventionist to skillfully advance catheters and guidewires through the patient's blood vessels.

Modern conversational agents like ChatGPT and Alexa+ rely on predefined policies specifying metadata, response styles, and tool-usage rules. As these LLM-based systems expand to support diverse business and user queries, such policies, often implemented as in-context prompts, are becoming increasingly complex and lengthy, making faithful adherence difficult and imposing large fixed computational costs. With the rise of multimodal agents, policies that govern visual and multimodal behaviors are critical but remain understudied. Prior prompt-compression work mainly shortens task templates and demonstrations, while existing policy-alignment studies focus only on text-based safety rules. We introduce Multimodal Policy Internalization (MPI), a new task that internalizes reasoning-intensive multimodal policies into model parameters, enabling stronger policy-following without including the policy during inference. MPI poses unique data and algorithmic challenges. We build two datasets spanning synthetic and real-world decision-making and tool-using tasks and propose TriMPI, a three-stage training framework. TriMPI first injects policy knowledge via continual pretraining, then performs supervised finetuning, and finally applies PolicyRollout, a GRPO-style reinforcement learning extension that augments rollouts with policy-aware responses for grounded exploration. TriMPI achieves notable gains in end-to-end accuracy, generalization, and robustness to forgetting. As the first work on multimodal policy internalization, we provide datasets, training recipes, and comprehensive evaluations to foster future research. Project page: https://mikewangwzhl.github.io/TriMPI.

Despite the remarkable progress in neural models, their ability to generalize, a cornerstone for applications like logical reasoning, remains a critical challenge. We delineate two fundamental aspects of this ability: compositionality, the capacity to abstract atomic logical rules underlying complex inferences, and recursiveness, the aptitude to build intricate representations through iterative application of inference rules. In the literature, these two aspects are often confounded together under the umbrella term of generalization. To sharpen this distinction, we investigated the logical generalization capabilities of pre-trained large language models (LLMs) using the syllogistic fragment as a benchmark for natural language reasoning. Though simple, this fragment provides a foundational yet expressive subset of formal logic that supports controlled evaluation of essential reasoning abilities. Our findings reveal a significant disparity: while LLMs demonstrate reasonable proficiency in recursiveness, they struggle with compositionality. To overcome these limitations and establish a reliable logical prover, we propose a hybrid architecture integrating symbolic reasoning with neural computation. This synergistic interaction enables robust and efficient inference, neural components accelerate processing, while symbolic reasoning ensures completeness. Our experiments show that high efficiency is preserved even with relatively small neural components. As part of our proposed methodology, this analysis gives a rationale and highlights the potential of hybrid models to effectively address key generalization barriers in neural reasoning systems.

The performance of Large Language Models (LLMs) is determined by their training data. Despite the proliferation of open-weight LLMs, access to LLM training data has remained limited. Even for fully open LLMs, the scale of the data makes it all but inscrutable to the general scientific community, despite potentially containing critical data scraped from the internet. In this paper, we present the full-text indexing pipeline for the Apertus LLM training data. Leveraging Elasticsearch parallel indices and the Alps infrastructure, a state-of-the-art, highly energy-efficient arm64 supercluster, we were able to index 8.6T tokens out of 15.2T used to train the Apertus LLM family, creating both a critical LLM safety tool and effectively an offline, curated, open web search engine. Our contribution is threefold. First, we demonstrate that Elasticsearch can be successfully ported onto next-generation arm64-based infrastructure. Second, we demonstrate that full-text indexing at the scale of modern LLM training datasets and the entire open web is feasible and accessible. Finally, we demonstrate that such indices can be used to ensure previously inaccessible jailbreak-agnostic LLM safety. We hope that our findings will be useful to other teams attempting large-scale data indexing and facilitate the general transition towards greener computation.

-- Interest in robotics for forest management is growing, but perception in complex, natural environments remains a significant hurdle. Conditions such as heavy occlusion, variable lighting, and dense vegetation pose challenges to automated systems, which are essential for precision forestry, biodiversity monitoring, and the automation of forestry equipment. These tasks rely on advanced perceptual capabilities, such as detection and fine-grained species classification of individual trees. Y et, existing datasets are inadequate to develop such perception systems, as they often focus on urban settings or a limited number of species. T o address this, we present SilvaScenes, a new dataset for instance segmentation of tree species from under-canopy images. Collected across five bioclimatic domains in Quebec, Canada, SilvaScenes features 1476 trees from 24 species with annotations from forestry experts. We demonstrate the relevance and challenging nature of our dataset by bench-marking modern deep learning approaches for instance segmentation. Our results show that, while tree segmentation is easy, with a top mean average precision (mAP) of 67. Segmentation and species classification of individual trees are key perception tasks for forestry applications, such as biodiversity monitoring and precision forestry [1].

Cross-domain sequential recommendation (CDSR) aims to align heterogeneous user behavior sequences collected from different domains. While cross-attention is widely used to enhance alignment and improve recommendation performance, its underlying mechanism is not fully understood. Most researchers interpret cross-attention as residual alignment, where the output is generated by removing redundant and preserving non-redundant information from the query input by referencing another domain data which is input key and value. Beyond the prevailing view, we introduce Orthogonal Alignment, a phenomenon in which cross-attention discovers novel information that is not present in the query input, and further argue that those two contrasting alignment mechanisms can co-exist in recommendation models We find that when the query input and output of cross-attention are orthogonal, model performance improves over 300 experiments. Notably, Orthogonal Alignment emerges naturally, without any explicit orthogonality constraints. Our key insight is that Orthogonal Alignment emerges naturally because it improves scaling law. We show that baselines additionally incorporating cross-attention module outperform parameter-matched baselines, achieving a superior accuracy-per-model parameter. We hope these findings offer new directions for parameter-efficient scaling in multi-modal research.

Free-text crash narratives recorded in real-world crash databases have been shown to play a significant role in improving traffic safety. However, large-scale analyses remain difficult to implement as there are no documented tools that can batch process the unstructured, non standardized text content written by various authors with diverse experience and attention to detail. In recent years, Transformer-based pre-trained language models (PLMs), such as Bidirectional Encoder Representations from Transformers (BERT) and large language models (LLMs), have demonstrated strong capabilities across various natural language processing tasks. These models can extract explicit facts from crash narratives, but their performance declines on inference-heavy tasks in, for example, Crash Type identification, which can involve nearly 100 categories. Moreover, relying on closed LLMs through external APIs raises privacy concerns for sensitive crash data. Additionally, these black-box tools often underperform due to limited domain knowledge. Motivated by these challenges, we study whether compact open-source PLMs can support reasoning-intensive extraction from crash narratives. We target two challenging objectives: 1) identifying the Manner of Collision for a crash, and 2) Crash Type for each vehicle involved in the crash event from real-world crash narratives. To bridge domain gaps, we apply fine-tuning techniques to inject task-specific knowledge to LLMs with Low-Rank Adaption (LoRA) and BERT. Experiments on the authoritative real-world dataset Crash Investigation Sampling System (CISS) demonstrate that our fine-tuned compact models outperform strong closed LLMs, such as GPT-4o, while requiring only minimal training resources. Further analysis reveals that the fine-tuned PLMs can capture richer narrative details and even correct some mislabeled annotations in the dataset.