Learning complex functions that involve multi-step reasoning poses a significant challenge for standard supervised learning from input-output examples. Chain-of-thought (CoT) supervision, which provides intermediate reasoning steps together with the final output, has emerged as a powerful empirical technique, underpinning much of the recent progress in the reasoning capabilities of large language models. This paper develops a statistical theory of learning under CoT supervision. A key characteristic of the CoT setting, in contrast to standard supervision, is the mismatch between the training objective (CoT risk) and the test objective (end-to-end risk). A central part of our analysis, distinguished from prior work, is explicitly linking those two types of risk to achieve sharper sample complexity bounds. This is achieved via the *CoT information measure* $\mathcal{I}_{\mathcal{D}, h_\star}^{\mathrm{CoT}}(ε; \calH)$, which quantifies the additional discriminative power gained from observing the reasoning process. The main theoretical results demonstrate how CoT supervision can yield significantly faster learning rates compared to standard E2E supervision. Specifically, it is shown that the sample complexity required to achieve a target E2E error $ε$ scales as $d/\mathcal{I}_{\mathcal{D}, h_\star}^{\mathrm{CoT}}(ε; \calH)$, where $d$ is a measure of hypothesis class complexity, which can be much faster than standard $d/ε$ rates. Information-theoretic lower bounds in terms of the CoT information are also obtained. Together, these results suggest that CoT information is a fundamental measure of statistical complexity for learning under chain-of-thought supervision.

The Madden-Julian Oscillation, or MJO, is a significant weather pattern that affects weather, influencing rainfall, temperature, and even storm frequency and intensity. When the MJO is active, it can affect the weather globally. To better predict weather changes with 3-4 weeks in advance, we rely on the ability to predict the MJO's activity. Data-driven methods such as the ones that rely on deep neural networks have been recently employed to make such predictions. By examining existing MJO patterns, neural networks attempt to predict upcoming ones. However, while neural networks are robust enough to predict the MJO's activity, they do not provide confidence intervals for those predictions. To address this shortcoming, we use a model known as the "Gaussian process" or GP. This statistical tool is distinctive because it not only provides predictions but also quantifies the level of confidence in them.

Large Language Models (LLMs) are increasingly equipped with capabilities of real-time web search and integrated with protocols like Model Context Protocol (MCP). This extension could introduce new security vulnerabilities. We present a systematic investigation of LLM vulnerabilities to hidden adversarial prompts through malicious font injection in external resources like webpages, where attackers manipulate code-to-glyph mapping to inject deceptive content which are invisible to users. We evaluate two critical attack scenarios: (1) "malicious content relay" and (2) "sensitive data leakage" through MCP-enabled tools. Our experiments reveal that indirect prompts with injected malicious font can bypass LLM safety mechanisms through external resources, achieving varying success rates based on data sensitivity and prompt design. Our research underscores the urgent need for enhanced security measures in LLM deployments when processing external content.

Artificial Intelligence (AI) systems have historically been used as tools that execute narrowly defined tasks. Yet recent advances in AI have unlocked possibilities for a new class of models that genuinely collaborate with humans in complex reasoning, from conceptualizing problems to brainstorming solutions. Such AI thought partners enable novel forms of collaboration and extended cognition, yet they also pose major risks-including and beyond risks of typical AI tools and agents. In this commentary, we systematically identify risks of AI thought partners through a novel framework that identifies risks at multiple levels of analysis, including Real-time, Individual, and Societal risks arising from collaborative cognition (RISc). We leverage this framework to propose concrete metrics for risk evaluation, and finally suggest specific mitigation strategies for developers and policymakers. As AI thought partners continue to proliferate, these strategies can help prevent major harms and ensure that humans actively benefit from productive thought partnerships.

This paper presents a comprehensive synthesis of major breakthroughs in artificial intelligence (AI) over the past fifteen years, integrating historical, theoretical, and technological perspectives. It identifies key inflection points in AI' s evolution by tracing the convergence of computational resources, data access, and algorithmic innovation. The analysis highlights how researchers enabled GPU based model training, triggered a data centric shift with ImageNet, simplified architectures through the Transformer, and expanded modeling capabilities with the GPT series. Rather than treating these advances as isolated milestones, the paper frames them as indicators of deeper paradigm shifts. By applying concepts from statistical learning theory such as sample complexity and data efficiency, the paper explains how researchers translated breakthroughs into scalable solutions and why the field must now embrace data centric approaches. In response to rising privacy concerns and tightening regulations, the paper evaluates emerging solutions like federated learning, privacy enhancing technologies (PETs), and the data site paradigm, which reframe data access and security. In cases where real world data remains inaccessible, the paper also assesses the utility and constraints of mock and synthetic data generation. By aligning technical insights with evolving data infrastructure, this study offers strategic guidance for future AI research and policy development.

We explore the use of conformal prediction to provide statistical uncertainty guarantees for runway detection in vision-based landing systems (VLS). Using fine-tuned YOLOv5 and YOLOv6 models on aerial imagery, we apply conformal prediction to quantify localization reliability under user-defined risk levels. We also introduce Conformal mean Average Precision (C-mAP), a novel metric aligning object detection performance with conformal guarantees. Our results show that conformal prediction can improve the reliability of runway detection by quantifying uncertainty in a statistically sound way, increasing safety on-board and paving the way for certification of ML system in the aerospace domain.

Empowered by vast internal knowledge reservoir, the new generation of large language models (LLMs) demonstrate untapped potential to tackle medical tasks. However, there is insufficient effort made towards summoning up a synergic effect from multiple LLMs' expertise and background. In this study, we propose a multi-LLM collaboration framework tailored on a medical multiple-choice questions dataset. Through post-hoc analysis on 3 pre-trained LLM participants, our framework is proved to boost all LLMs reasoning ability as well as alleviate their divergence among questions. We also measure an LLM's confidence when it confronts with adversary opinions from other LLMs and observe a concurrence between LLM's confidence and prediction accuracy.

While the safety risks of image-based large language models have been extensively studied, their video-based counterparts (Video LLMs) remain critically under-examined. To systematically study this problem, we introduce \textbf{VideoSafetyBench (VSB-77k) - the first large-scale, culturally diverse benchmark for Video LLM safety}, which compromises 77,646 video-query pairs and spans 19 principal risk categories across 10 language communities. \textit{We reveal that integrating video modality degrades safety performance by an average of 42.3\%, exposing systemic risks in multimodal attack exploitation.} To address this vulnerability, we propose \textbf{VideoSafety-R1}, a dual-stage framework achieving unprecedented safety gains through two innovations: (1) Alarm Token-Guided Safety Fine-Tuning (AT-SFT) injects learnable alarm tokens into visual and textual sequences, enabling explicit harm perception across modalities via multitask objectives. (2) Then, Safety-Guided GRPO enhances defensive reasoning through dynamic policy optimization with rule-based rewards derived from dual-modality verification. These components synergize to shift safety alignment from passive harm recognition to active reasoning. The resulting framework achieves a 65.1\% improvement on VSB-Eval-HH, and improves by 59.1\%, 44.3\%, and 15.0\% on the image safety datasets MMBench, VLGuard, and FigStep, respectively. \textit{Our codes are available in the supplementary materials.} \textcolor{red}{Warning: This paper contains examples of harmful language and videos, and reader discretion is recommended.}

With recent Nobel Prizes recognising AI contributions to science, Large Language Models (LLMs) are transforming scientific research by enhancing productivity and reshaping the scientific method. LLMs are now involved in experimental design, data analysis, and workflows, particularly in chemistry and biology. However, challenges such as hallucinations and reliability persist. In this contribution, we review how Large Language Models (LLMs) are redefining the scientific method and explore their potential applications across different stages of the scientific cycle, from hypothesis testing to discovery. We conclude that, for LLMs to serve as relevant and effective creative engines and productivity enhancers, their deep integration into all steps of the scientific process should be pursued in collaboration and alignment with human scientific goals, with clear evaluation metrics. T he transition to AI - driven science raises ethical questions about creativity, oversight, and responsibility. With careful guidance, LLMs could evolve into creative engines, driving transformative breakthroughs across scientific disciplines responsibly and effectively. However, the scientific community must also decide how much it leaves to LLMs to drive science, even when associations with'reasoning', mostly currently undeserved, are made in exchange for the potential to explore hypothesis and solution regions that might otherwise remain unexplored by human exploration alone.

Iterative RAG for multi-hop question answering faces challenges with lengthy contexts and the buildup of irrelevant information. This hinders a model's capacity to process and reason over retrieved content and limits performance. While recent methods focus on compressing retrieved information, they are either restricted to single-round RAG, require finetuning or lack scalability in iterative RAG. To address these challenges, we propose Notes Writing, a method that generates concise and relevant notes from retrieved documents at each step, thereby reducing noise and retaining only essential information. This indirectly increases the effective context length of Large Language Models (LLMs), enabling them to reason and plan more effectively while processing larger volumes of input text. Notes Writing is framework agnostic and can be integrated with different iterative RAG methods. We demonstrate its effectiveness with three iterative RAG methods, across two models and four evaluation datasets. Notes writing yields an average improvement of 15.6 percentage points overall, with minimal increase in output tokens.