When you purchase through links in our articles, we may earn a small commission. Microsoft's Copilot AI text-to-speech gets new, cleaner'scripted mode' Copilot Audio Expressions can now read text aloud in a more direct fashion without altering its content. Microsoft's AI Manager Mustafa Suleyman recently unveiled in a social media post a new feature called "Scripted Mode" in Copilot Labs for turning written scripts into text-to-speech. Copilot Labs is an experimental platform where you can try out Microsoft's newest AI features that are still in development. Scripted mode just dropped for audio generation in Copilot Labs (c/o our new MAI-Voice-1 model).

The Download: America's gun crisis, and how AI video models work We can't "make American children healthy again" without tackling the gun crisis This week, the Trump administration released a strategy for improving the health and well-being of American children. The report was titled--you guessed it--Make Our Children Healthy Again. It suggests American children should be eating more healthily. And they should be getting more exercise. This week's news of yet more high-profile shootings at schools in the US throws this disconnect into even sharper relief. Experts believe it is time to treat gun violence in the US as what it is: a public health crisis.

How do AI models generate videos? With powerful video generation tools now in the hands of more people than ever, let's take a look at how they work. It's been a big year for video generation. In the last nine months OpenAI made Sora public, Google DeepMind launched Veo 3, the video startup Runway launched Gen-4. All can produce video clips that are (almost) impossible to distinguish from actual filmed footage or CGI animation. This year also saw Netflix debut an AI visual effect in its show, the first time video generation has been used to make mass-market TV.

In-context learning (ICL) allows a language model to improve its problem-solving capability when provided with suitable information in context. Since the choice of in-context information can be determined based on the problem itself, in-context learning is analogous to human learning from teachers in a classroom. Recent works (Didolkar et al., 2024a; 2024b) show that ICL performance can be improved by leveraging a frontier large language model's (LLM) ability to predict required skills to solve a problem, popularly referred to as an LLM's metacognition, and using the recommended skills to construct necessary in-context examples. While this skill-based strategy boosts ICL performance in larger models, its gains on small language models (SLMs) have been minimal, highlighting a performance gap in ICL capabilities. We investigate this gap and show that skill-based prompting can hurt SLM performance on easy questions by introducing unnecessary information, akin to cognitive overload. To address this, we introduce AdaptMI, an adaptive approach to selecting skill-based in-context Math Instructions for SLMs. Inspired by cognitive load theory from human pedagogy, our method only introduces skill-based examples when the model performs poorly. We further propose AdaptMI+, which adds examples targeted to the specific skills missing from the model's responses. On 5-shot evaluations across popular math benchmarks and five SLMs (1B--7B; Qwen, Llama), AdaptMI+ improves accuracy by up to 6% over naive skill-based strategies.

Embodied AI systems operate in dynamic environments, requiring seamless integration of perception and generation modules to process high-frequency input and output demands. Traditional sequential computation patterns, while effective in ensuring accuracy, face significant limitations in achieving the necessary "thinking" frequency for real-world applications. In this work, we present Auras, an algorithm-system co-designed inference framework to optimize the inference frequency of embodied AI agents. Auras disaggregates the perception and generation and provides controlled pipeline parallelism for them to achieve high and stable throughput. Faced with the data staleness problem that appears when the parallelism is increased, Auras establishes a public context for perception and generation to share, thereby promising the accuracy of embodied agents. Experimental results show that Auras improves throughput by 2.54x on average while achieving 102.7% of the original accuracy, demonstrating its efficacy in overcoming the constraints of sequential computation and providing high throughput.

Molecular Tumor Boards (MTBs) are multidisciplinary forums where oncology specialists collaboratively assess complex patient cases to determine optimal treatment strategies. A central element of this process is the patient summary, typically compiled by a medical oncologist, radiation oncologist, or surgeon, or their trained medical assistant, who distills heterogeneous medical records into a concise narrative to facilitate discussion. This manual approach is often labor-intensive, subjective, and prone to omissions of critical information. To address these limitations, we introduce the Healthcare Agent Orchestrator (HAO), a Large Language Model (LLM)-driven AI agent that coordinates a multi-agent clinical workflow to generate accurate and comprehensive patient summaries for MTBs. Evaluating predicted patient summaries against ground truth presents additional challenges due to stylistic variation, ordering, synonym usage, and phrasing differences, which complicate the measurement of both succinctness and completeness. To overcome these evaluation hurdles, we propose TBFact, a ``model-as-a-judge'' framework designed to assess the comprehensiveness and succinctness of generated summaries. Using a benchmark dataset derived from de-identified tumor board discussions, we applied TBFact to evaluate our Patient History agent. Results show that the agent captured 94% of high-importance information (including partial entailments) and achieved a TBFact recall of 0.84 under strict entailment criteria. We further demonstrate that TBFact enables a data-free evaluation framework that institutions can deploy locally without sharing sensitive clinical data. Together, HAO and TBFact establish a robust foundation for delivering reliable and scalable support to MTBs.

Retrieval-Augmented Generation (RAG) systems in the legal domain face a critical challenge: standard, flat-text retrieval is blind to the hierarchical, diachronic, and causal structure of law, leading to anachronistic and unreliable answers. This paper introduces the Structure-Aware Temporal Graph RAG (SAT-Graph RAG), an ontology-driven framework designed to overcome these limitations by explicitly modeling the formal structure and diachronic nature of legal norms. We ground our knowledge graph in a formal, LRMoo-inspired model that distinguishes abstract legal Works from their versioned Expressions. We model temporal states as efficient aggregations that reuse the versioned expressions (CTVs) of unchanged components, and we reify legislative events as first-class Action nodes to make causality explicit and queryable. This structured backbone enables a unified, planner-guided query strategy that applies explicit policies to deterministically resolve complex requests for (i) point-in-time retrieval, (ii) hierarchical impact analysis, and (iii) auditable provenance reconstruction. Through a case study on the Brazilian Constitution, we demonstrate how this approach provides a verifiable, temporally-correct substrate for LLMs, enabling higher-order analytical capabilities while drastically reducing the risk of factual errors. The result is a practical framework for building more trustworthy and explainable legal AI systems.

Question Answering over Tabular Data (Table QA) presents unique challenges due to the diverse structure, size, and data types of real-world tables. The SemEval 2025 Task 8 (DataBench) introduced a benchmark composed of large-scale, domain-diverse datasets to evaluate the ability of models to accurately answer structured queries. We propose a Natural Language to SQL (NL-to-SQL) approach leveraging large language models (LLMs) such as GPT-4o, GPT-4o-mini, and DeepSeek v2:16b to generate SQL queries dynamically. Our system follows a multi-stage pipeline involving example selection, SQL query generation, answer extraction, verification, and iterative refinement. Experiments demonstrate the effectiveness of our approach, achieving 70.5\% accuracy on DataBench QA and 71.6\% on DataBench Lite QA, significantly surpassing baseline scores of 26\% and 27\% respectively. This paper details our methodology, experimental results, and alternative approaches, providing insights into the strengths and limitations of LLM-driven Table QA.

Accurately assessing candidate seniority from resumes is a critical yet challenging task, complicated by the prevalence of overstated experience and ambiguous self-presentation. In this study, we investigate the effectiveness of large language models (LLMs), including fine-tuned BERT architectures, for automating seniority classification in resumes. To rigorously evaluate model performance, we introduce a hybrid dataset comprising both real-world resumes and synthetically generated hard examples designed to simulate exaggerated qualifications and understated seniority. Using the dataset, we evaluate the performance of Large Language Models in detecting subtle linguistic cues associated with seniority inflation and implicit expertise. Our findings highlight promising directions for enhancing AI-driven candidate evaluation systems and mitigating bias introduced by self-promotional language. The dataset is available for the research community at https://bit.ly/4mcTovt

The question-answering (QA) simulator is a model that mimics real student learning behaviors and predicts their correctness of their responses to questions. QA simulators enable educational recommender systems (ERS) to collect large amounts of training data without interacting with real students, thereby preventing harmful recommendations made by an undertrained ERS from undermining actual student learning. Given the QA history, there are two categories of solutions to predict the correctness, conducting the simulation: (1) LLM-free methods, which apply a traditional sequential model to transfer the QA history into a vector representation first, and make predictions based on the representation; (2) LLM-based methods, which leverage the domain knowledge and reasoning capability of LLM to enhence the prediction. LLM-free methods offer fast inference but generally yield suboptimal performance. In contrast, most LLM-based methods achieve better results, but at the cost of slower inference speed and higher GPU memory consumption. In this paper, we propose a method named LLM Distillation based Simulator (LDSim), which distills domain knowledge and reasoning capability from an LLM to better assist prediction, thereby improving simulation performance. Extensive experiments demonstrate that our LDSim achieves strong results on both the simulation task and the knowledge tracing (KT) task. Our code is publicly available at https://anonymous.4open.science/r/LDSim-05A9.