In this report, we present the Qwen3-TTS series, a family of advanced multilingual, controllable, robust, and streaming text-to-speech models. Qwen3-TTS supports state-of-the-art 3-second voice cloning and description-based control, allowing both the creation of entirely novel voices and fine-grained manipulation over the output speech. Trained on over 5 million hours of speech data spanning 10 languages, Qwen3-TTS adopts a dual-track LM architecture for real-time synthesis, coupled with two speech tokenizers: 1) Qwen-TTS-Tokenizer-25Hz is a single-codebook codec emphasizing semantic content, which offers seamlessly integration with Qwen-Audio and enables streaming waveform reconstruction via a block-wise DiT. 2) Qwen-TTS-Tokenizer-12Hz achieves extreme bitrate reduction and ultra-low-latency streaming, enabling immediate first-packet emission ($97\,\mathrm{ms}$) through its 12.5 Hz, 16-layer multi-codebook design and a lightweight causal ConvNet. Extensive experiments indicate state-of-the-art performance across diverse objective and subjective benchmark (e.g., TTS multilingual test set, InstructTTSEval, and our long speech test set). To facilitate community research and development, we release both tokenizers and models under the Apache 2.0 license.

Cross-subject EEG-based emotion recognition (EER) remains challenging due to strong inter-subject variability, which induces substantial distribution shifts in EEG signals, as well as the high complexity of emotion-related neural representations in both spatial organization and temporal evolution. Existing approaches typically improve spatial modeling, temporal modeling, or generalization strategies in isolation, which limits their ability to align representations across subjects while capturing multi-scale dynamics and suppressing subject-specific bias within a unified framework. To address these gaps, we propose a Region-aware Spatiotemporal Modeling framework with Collaborative Domain Generalization (RSM-CoDG) for cross-subject EEG emotion recognition. RSM-CoDG incorporates neuroscience priors derived from functional brain region partitioning to construct region-level spatial representations, thereby improving cross-subject comparability. It also employs multi-scale temporal modeling to characterize the dynamic evolution of emotion-evoked neural activity. In addition, the framework employs a collaborative domain generalization strategy, incorporating multidimensional constraints to reduce subject-specific bias in a fully unseen target subject setting, which enhances the generalization to unknown individuals. Extensive experimental results on SEED series datasets demonstrate that RSM-CoDG consistently outperforms existing competing methods, providing an effective approach for improving robustness. The source code is available at https://github.com/RyanLi-X/RSM-CoDG.

As environmental disasters happen more frequently and severely, seeking the source of pollutants or harmful particulates using plume tracking becomes even more important. Plume tracking on small quadrotors would allow these systems to operate around humans and fly in more confined spaces, but can be challenging due to poor sensitivity and long response times from gas sensors that fit on small quadrotors. In this work, we present an approach to complement chemical plume tracking with airflow source-seeking behavior using a custom flow sensor that can sense both airflow magnitude and direction on small quadrotors < 100 g. We use this sensor to implement a modified version of the `Cast and Surge' algorithm that takes advantage of flow direction sensing to find and navigate towards flow sources. A series of characterization experiments verified that the system can detect airflow while in flight and reorient the quadrotor toward the airflow. Several trials with random starting locations and orientations were used to show that our source-seeking algorithm can reliably find a flow source. This work aims to provide a foundation for future platforms that can use flow sensors in concert with other sensors to enable richer plume tracking data collection and source-seeking.

This paper introduces a neural network-based nonlinear shrinkage estimator of covariance matrices for the purpose of minimum variance portfolio optimization. It is a hybrid approach that integrates statistical estimation with machine learning. Starting from the Ledoit-Wolf (LW) shrinkage estimator, we decompose the LW covariance matrix into its eigenvalues and eigenvectors, and apply a lightweight transformer-based neural network to learn a nonlinear eigenvalue shrinkage function. Trained with portfolio risk as the loss function, the resulting precision matrix (the inverse covariance matrix) estimator directly targets portfolio risk minimization. By conditioning on the sample-to-dimension ratio, the approach remains scalable across different sample sizes and asset universes. Empirical results on stock daily returns from Standard & Poor's 500 Index (S&P500) demonstrate that the proposed method consistently achieves lower out-of-sample realized risk than benchmark approaches. This highlights the promise of integrating structural statistical models with data-driven learning.

While modern Text-to-Speech (TTS) systems achieve high fidelity for read-style speech, they struggle to generate Autonomous Sensory Meridian Response (ASMR), a specialized, low-intensity speech style essential for relaxation. The inherent challenges include ASMR's subtle, often unvoiced characteristics and the demand for zero-shot speaker adaptation. In this paper, we introduce DeepASMR, the first framework designed for zero-shot ASMR generation. We demonstrate that a single short snippet of a speaker's ordinary, read-style speech is sufficient to synthesize high-fidelity ASMR in their voice, eliminating the need for whispered training data from the target speaker. Methodologically, we first identify that discrete speech tokens provide a soft factorization of ASMR style from speaker timbre. Leveraging this insight, we propose a two-stage pipeline incorporating a Large Language Model (LLM) for content-style encoding and a flow-matching acoustic decoder for timbre reconstruction. Furthermore, we contribute DeepASMR-DB, a comprehensive 670-hour English-Chinese multi-speaker ASMR speech corpus, and introduce a novel evaluation protocol integrating objective metrics, human listening tests, LLM-based scoring and unvoiced speech analysis. Extensive experiments confirm that DeepASMR achieves state-of-the-art naturalness and style fidelity in ASMR generation for anyone of any voice, while maintaining competitive performance on normal speech synthesis.

Managing perishable products with limited lifetimes is a fundamental challenge in inventory management, as poor ordering decisions can quickly lead to stockouts or excessive waste. We study a perishable inventory system with random lead times in which both the demand process and the lead time distribution are unknown. We consider a practical setting where orders are placed using limited historical data together with observed covariates and current system states. To improve learning efficiency under limited data, we adopt a marginal cost accounting scheme that assigns each order a single lifetime cost and yields a unified loss function for end-to-end learning. This enables training a deep learning-based policy that maps observed covariates and system states directly to order quantities. We develop two end-to-end variants: a purely black-box approach that outputs order quantities directly (E2E-BB), and a structure-guided approach that embeds the projected inventory level (PIL) policy, capturing inventory effects through explicit computation rather than additional learning (E2E-PIL). We further show that the objective induced by E2E-PIL is homogeneous of degree one, enabling a boosting technique from operational data analytics (ODA) that yields an enhanced policy (E2E-BPIL). Experiments on synthetic and real data establish a robust performance ordering: E2E-BB is dominated by E2E-PIL, which is further improved by E2E-BPIL. Using an excess-risk decomposition, we show that embedding heuristic policy structure reduces effective model complexity and improves learning efficiency with only a modest loss of flexibility. More broadly, our results suggest that deep learning-based decision tools are more effective and robust when guided by human knowledge, highlighting the value of integrating advanced analytics with inventory theory.

As large language models (LLMs) are increasingly deployed in real-world applications, safety guardrails are required to go beyond coarse-grained filtering and support fine-grained, interpretable, and adaptable risk assessment. However, existing solutions often rely on rapid classification schemes or post-hoc rules, resulting in limited transparency, inflexible policies, or prohibitive inference costs. To this end, we present YuFeng-XGuard, a reasoning-centric guardrail model family designed to perform multi-dimensional risk perception for LLM interactions. Instead of producing opaque binary judgments, YuFeng-XGuard generates structured risk predictions, including explicit risk categories and configurable confidence scores, accompanied by natural language explanations that expose the underlying reasoning process. This formulation enables safety decisions that are both actionable and interpretable. To balance decision latency and explanatory depth, we adopt a tiered inference paradigm that performs an initial risk decision based on the first decoded token, while preserving ondemand explanatory reasoning when required. In addition, we introduce a dynamic policy mechanism that decouples risk perception from policy enforcement, allowing safety policies to be adjusted without model retraining. Extensive experiments on a diverse set of public safety benchmarks demonstrate that YuFeng-XGuard achieves stateof-the-art performance while maintaining strong efficiency-efficacy trade-offs. We release YuFeng-XGuard as an open model family, including both a full-capacity variant and a lightweight version, to support a wide range of deployment scenarios.

Denoising Diffusion Probabilistic Models (DDPMs) have achieved remarkable success in high-fidelity image generation. However, evaluating their semantic controllability-specifically for fine-grained, single-domain tasks-remains challenging. Standard metrics like FID and Inception Score (IS) often fail to detect identity misalignment in such specialized contexts. In this work, we investigate Class-Conditional DDPMs for K-pop idol face generation (32x32), a domain characterized by high inter-class similarity. We propose a calibrated metric, Relative Classification Accuracy (RCA), which normalizes generative performance against an oracle classifier's baseline. Our evaluation reveals a critical trade-off: while the model achieves high visual quality (FID 8.93), it suffers from severe semantic mode collapse (RCA 0.27), particularly for visually ambiguous identities. We analyze these failure modes through confusion matrices and attribute them to resolution constraints and intra-gender ambiguity. Our framework provides a rigorous standard for verifying identity consistency in conditional generative models.

Clinical empathy is essential for patient care, but physicians need continually balance emotional warmth with factual precision under the cognitive and emotional constraints of clinical practice. This study investigates how large language models (LLMs) can function as empathy editors, refining physicians' written responses to enhance empathetic tone while preserving underlying medical information. More importantly, we introduce novel quantitative metrics, an Empathy Ranking Score and a MedFactChecking Score to systematically assess both emotional and factual quality of the responses. Experimental results show that LLM edited responses significantly increase perceived empathy while preserving factual accuracy compared with fully LLM generated outputs. These findings suggest that using LLMs as editorial assistants, rather than autonomous generators, offers a safer, more effective pathway to empathetic and trustworthy AI-assisted healthcare communication.

We present BanditLP, a scalable multi-stakeholder contextual bandit framework that unifies neural Thompson Sampling for learning objective-specific outcomes with a large-scale linear program for constrained action selection at serving time. The methodology is application-agnostic, compatible with arbitrary neural architectures, and deployable at web scale, with an LP solver capable of handling billions of variables. Experiments on public benchmarks and synthetic data show consistent gains over strong baselines. We apply this approach in LinkedIn's email marketing system and demonstrate business win, illustrating the value of integrated exploration and constrained optimization in production.

Personalized learning systems have emerged as a promising approach to enhance student outcomes by tailoring educational content, pacing, and feedback to individual needs. However, most existing systems remain fragmented, specializing in either knowledge tracing, diagnostic modeling, or resource recommendation, but rarely integrating these components into a cohesive adaptive cycle. In this paper, we propose ALIGNAgent (Adaptive Learner Intelligence for Gap Identification and Next-step guidance), a multi-agent educational framework designed to deliver personalized learning through integrated knowledge estimation, skill-gap identification, and targeted resource recommendation.ALIGNAgent begins by processing student quiz performance, gradebook data, and learner preferences to generate topic-level proficiency estimates using a Skill Gap Agent that employs concept-level diagnostic reasoning to identify specific misconceptions and knowledge deficiencies. After identifying skill gaps, the Recommender Agent retrieves preference-aware learning materials aligned with diagnosed deficiencies, implementing a continuous feedback loop where interventions occur before advancing to subsequent topics. Extensive empirical evaluation on authentic datasets from two undergraduate computer science courses demonstrates ALIGNAgent's effectiveness, with GPT-4o-based agents achieving precision of 0.87-0.90 and F1 scores of 0.84-0.87 in knowledge proficiency estimation validated against actual exam performance.

Generalizing Multimodal Large Language Models (MLLMs) to novel video domains is essential for real-world deployment but remains challenging due to the scarcity of labeled data. While In-Context Learning (ICL) offers a training-free adaptation path, standard methods rely on large annotated pools, which are often impractical in specialized environments like industrial or surgical settings since they require the experts' annotations. To bridge this gap, we introduce VIOLA (Video In-cOntext Learning with minimal Annotation), a label-efficient framework that synergizes minimal expert supervision with abundant unlabeled data. First, to maximize the efficiency of a strict annotation budget, we propose density-uncertainty-weighted sampling. Unlike standard diversity or uncertainty strategies that risk selecting visual outliers, our method leverages density estimation to identify samples that are simultaneously diverse, representative, and informative. Second, to utilize the remaining unlabeled data without noise propagation, we construct a hybrid pool and introduce confidence-aware retrieval and confidence-aware prompting. These mechanisms explicitly model label reliability, retrieving demonstrations based on a composite score of similarity and confidence while enabling the MLLM to adaptively distinguish between verified ground truths and noisy pseudo-labels. Extensive experiments across nine diverse benchmarks using four MLLMs demonstrate that our framework significantly outperforms various baselines in low-resource settings, achieving robust adaptation with minimal annotation costs.

A key task in ML is to optimize models at various stages, e.g. by choosing hyperparameters or picking a stopping point. A traditional ML approach is to use validation loss, i.e. to apply the training loss function on a validation set to guide these optimizations. However, ML for healthcare has a distinct goal from traditional ML: Models must perform well relative to specific clinical requirements, vs. relative to the loss function used for training. These clinical requirements can be captured more precisely by tailored metrics. Since many optimization tasks do not require the driving metric to be differentiable, they allow a wider range of options, including the use of metrics tailored to be clinically-relevant. In this paper we describe two controlled experiments which show how the use of clinically-tailored metrics provide superior model optimization compared to validation loss, in the sense of better performance on the clinical task. The use of clinically-relevant metrics for optimization entails some extra effort, to define the metrics and to code them into the pipeline. But it can yield models that better meet the central goal of ML for healthcare: strong performance in the clinic.

Targeted drug delivery in the gastrointestinal (GI) tract using magnetic robots offers a promising alternative to systemic treatments. However, controlling these robots is a major challenge. Stationary magnetic systems have a limited workspace, while mobile systems (e.g., coils on a robotic arm) suffer from a "model-calibration bottleneck", requiring complex, pre-calibrated physical models that are time-consuming to create and computationally expensive. This paper presents a compact, low-cost mobile magnetic manipulation platform that overcomes this limitation using Deep Reinforcement Learning (DRL). Our system features a compact four-electromagnet array mounted on a UR5 collaborative robot. A Soft Actor-Critic (SAC)-based control strategy is trained through a sim-to-real pipeline, enabling effective policy deployment within 15 minutes and significantly reducing setup time. We validated the platform by controlling a 7-mm magnetic capsule along 2D trajectories. Our DRL-based controller achieved a root-mean-square error (RMSE) of 1.18~mm for a square path and 1.50~mm for a circular path. We also demonstrated successful tracking over a clinically relevant, 30 cm * 20 cm workspace. This work demonstrates a rapidly deployable, model-free control framework capable of precise magnetic manipulation in a large workspace,validated using a 2D GI phantom.

Machine unlearning aims to remove specific knowledge (e.g., copyrighted or private data) from a trained model without full retraining. In practice, models are often quantized (e.g., 4-bit) for deployment, but we find that quantization can catastrophically restore forgotten information [1]. In this paper, we (1) analyze why low-bit quantization undermines unlearning, and (2) propose a quantization-aware unlearning method to mitigate this. We first compute weight-change statistics and bucket overlaps in quantization to show that typical unlearning updates are too small to cross quantization thresholds. Building on this insight, we introduce a logits space hinge loss: for each forget example, we force the output logits of the unlearned model to differ from the original model by at least a margin (half the quantization step). This ensures forgotten examples remain distinguishable even after quantization. We evaluate on language and classification tasks (including a Twitter misinformation dataset) and show our method preserves forgetting under 4-bit quantization, whereas existing methods almost entirely recover the forgotten knowledge.

A world model is an AI system that simulates how an environment evolves under actions, enabling planning through imagined futures rather than reactive perception. Current world models, however, suffer from visual conflation: the mistaken assumption that high-fidelity video generation implies an understanding of physical and causal dynamics. We show that while modern models excel at predicting pixels, they frequently violate invariant constraints, fail under intervention, and break down in safety-critical decision-making. This survey argues that visual realism is an unreliable proxy for world understanding. Instead, effective world models must encode causal structure, respect domain-specific constraints, and remain stable over long horizons. We propose a reframing of world models as actionable simulators rather than visual engines, emphasizing structured 4D interfaces, constraint-aware dynamics, and closed-loop evaluation. Using medical decision-making as an epistemic stress test, where trial-and-error is impossible and errors are irreversible, we demonstrate that a world model's value is determined not by how realistic its rollouts appear, but by its ability to support counterfactual reasoning, intervention planning, and robust long-horizon foresight.

Hallucination in large language models (LLMs) remains an acute concern, contributing to the spread of misinformation and diminished public trust, particularly in high-risk domains. Among hallucination types, factuality is crucial, as it concerns a model's alignment with established world knowledge. Adversarial factuality, defined as the deliberate insertion of misinformation into prompts with varying levels of expressed confidence, tests a model's ability to detect and resist confidently framed falsehoods. Existing work lacks high-quality, domain-specific resources for assessing model robustness under such adversarial conditions, and no prior research has examined the impact of injected misinformation on long-form text factuality. To address this gap, we introduce AdversaRiskQA, the first verified and reliable benchmark systematically evaluating adversarial factuality across Health, Finance, and Law. The benchmark includes two difficulty levels to test LLMs' defensive capabilities across varying knowledge depths. We propose two automated methods for evaluating the adversarial attack success and long-form factuality. We evaluate six open- and closed-source LLMs from the Qwen, GPT-OSS, and GPT families, measuring misinformation detection rates. Long-form factuality is assessed on Qwen3 (30B) under both baseline and adversarial conditions. Results show that after excluding meaningless responses, Qwen3 (80B) achieves the highest average accuracy, while GPT-5 maintains consistently high accuracy. Performance scales non-linearly with model size, varies by domains, and gaps between difficulty levels narrow as models grow. Long-form evaluation reveals no significant correlation between injected misinformation and the model's factual output. AdversaRiskQA provides a valuable benchmark for pinpointing LLM weaknesses and developing more reliable models for high-stakes applications.

The use of Transfer Learning & Transformers has steadily improved accuracy and has significantly contributed in solving complex computation problems. However, this transformer led accuracy improvement in Applied AI Analytics specifically in sentiment analytics comes with the dark side. It is observed during experiments that a lot of these improvements in transformer led accuracy of one class of sentiment has been at the cost of polarization of another class of sentiment and the failing of neutrality. This lack of neutrality poses an acute problem in the Applied NLP space, which relies heavily on the computational outputs of sentiment analytics for reliable industry ready tasks.

Characters in novels have typically been modeled based on their presence in scenes in narrative, considering aspects like their actions, named mentions, and dialogue. This conception of character places significant emphasis on the main character who is present in the most scenes. In this work, we instead adopt a framing developed from a new literary theory proposing a six-component structural model of character. This model enables a comprehensive approach to character that accounts for the narrator-character distinction and includes a component neglected by prior methods, discussion by other characters. We compare general-purpose LLMs with task-specific transformers for operationalizing this model of character on major 19th-century British realist novels. Our methods yield both component-level and graph representations of character discussion. We then demonstrate that these representations allow us to approach literary questions at scale from a new computational lens. Specifically, we explore Woloch's classic "the one vs the many" theory of character centrality and the gendered dynamics of character discussion.

Drawing inspiration from recent findings including surprisingly decent performance of transformers without positional encoding (NoPE) in the domain of language models and how registers (additional throwaway tokens not tied to input) may improve the performance of large vision transformers (ViTs), we invent and test a variant of ViT called fractal ViT that breaks permutation invariance among the tokens by applying an attention mask between the regular tokens and ``summary tokens'' similar to registers, in isolation or in combination with various positional encodings. These models do not improve upon ViT with registers, highlighting the fact that these findings may be scale, domain, or application-specific.

Spatial transcriptomics enables spatial gene expression profiling, motivating computational models that capture spatially conditioned regulatory relationships. We introduce SAGE-FM, a lightweight spatial transcriptomics foundation model based on graph convolutional networks (GCNs) trained with a masked central spot prediction objective. Trained on 416 human Visium samples spanning 15 organs, SAGE-FM learns spatially coherent embeddings that robustly recover masked genes, with 91% of masked genes showing significant correlations (p < 0.05). The embeddings generated by SAGE-FM outperform MOFA and existing spatial transcriptomics methods in unsupervised clustering and preservation of biological heterogeneity. SAGE-FM generalizes to downstream tasks, enabling 81% accuracy in pathologist-defined spot annotation in oropharyngeal squamous cell carcinoma and improving glioblastoma subtype prediction relative to MOFA. In silico perturbation experiments further demonstrate that the model captures directional ligand-receptor and upstream-downstream regulatory effects consistent with ground truth. These results demonstrate that simple, parameter-efficient GCNs can serve as biologically interpretable and spatially aware foundation models for large-scale spatial transcriptomics.

A common solution for mitigating outdated or incorrect information in Large Language Models (LLMs) is to provide updated facts in-context or through knowledge editing. However, these methods introduce knowledge conflicts when the knowledge update fails to overwrite the model's parametric knowledge, which propagate to faulty reasoning. Current benchmarks for this problem, however, largely focus only on single knowledge updates and fact recall without evaluating how these updates affect downstream reasoning. In this work, we introduce TRACK (Testing Reasoning Amid Conflicting Knowledge), a new benchmark for studying how LLMs propagate new knowledge through multi-step reasoning when it conflicts with the model's initial parametric knowledge. Spanning three reasoning-intensive scenarios (WIKI, CODE, and MATH), TRACK introduces multiple, realistic conflicts to mirror real-world complexity. Our results on TRACK reveal that providing updated facts to models for reasoning can worsen performance compared to providing no updated facts to a model, and that this performance degradation exacerbates as more updated facts are provided. We show this failure stems from both inability to faithfully integrate updated facts, but also flawed reasoning even when knowledge is integrated. TRACK provides a rigorous new benchmark to measure and guide future progress on propagating conflicting knowledge in multi-step reasoning.

Bias in chest X-ray classifiers frequently stems from sex- and age-related shortcuts, leading to systematic underdiagnosis of minority subgroups. Previous pixel-space attribute neutralizers, which rely on convolutional encoders, lessen but do not fully remove this attribute leakage at clinically usable edit strengths. This study evaluates whether substituting the U-Net convolutional encoder with a Vision Transformer backbone in the Attribute-Neutral Framework can reduce demographic attribute leakage while preserving diagnostic accuracy. A data-efficient Image Transformer Small (DeiT-S) neutralizer was trained on the ChestX-ray14 dataset. Its edited images, generated across eleven edit-intensity levels, were evaluated with an independent AI judge for attribute leakage and with a convolutional neural network (ConvNet) for disease prediction. At a moderate edit level (alpha = 0.5), the Vision Transformer (ViT) neutralizer reduces patient sex-recognition area under the curve (AUC) to approximately 0.80, about 10 percentage points below the original framework's convolutional U-Net encoder, despite being trained for only half as many epochs. Meanwhile, macro receiver operating characteristic area under the curve (ROC AUC) across 15 findings stays within five percentage points of the unedited baseline, and the worst-case subgroup AUC remains near 0.70. These results indicate that global self-attention vision models can further suppress attribute leakage without sacrificing clinical utility, suggesting a practical route toward fairer chest X-ray AI.

The rapid evolution of Retrieval-Augmented Generation (RAG) toward multimodal, high-stakes enterprise applications has outpaced the development of domain specific evaluation benchmarks. Existing datasets often rely on general-domain corpora or purely textual retrieval, failing to capture the complexity of specialized technical documents where information is inextricably multimodal and reasoning requires synthesizing disjoint evidence. We address this gap by introducing MiRAGE, a Multiagent framework for RAG systems Evaluation, that leverages a collaborative swarm of specialized agents to generate verified, domain-specific, multimodal, and multi-hop Question-Answer datasets. MiRAGE orchestrates a swarm of specialized agents: a recursive context optimization loop to aggregate scattered evidence, an adversarial verifier agent to guarantee factual grounding, and an agent to recognize the expert persona and the relevant domain to mimic expert cognitive workflows. Extensive empirical evaluation across four distinct domains (regulations, finance, quantitative biology, and journalism) demonstrates that MiRAGE generates datasets with significantly higher reasoning complexity (>2.3 average hops) and factual faithfulness. Our ablation studies point that MiRAGE can be powered by LLMs if textual descriptions of the images are available. Visual grounding still remains a frontier. By automating the creation of gold standard evaluation datasets that reflect the latent thematic structure of proprietary corpora, MiRAGE provides the necessary infrastructure to rigorously benchmark the next generation information retrieval systems.

The use of artificial intelligence (AI) for drone control can have a transformative impact on drone capabilities, especially when real world information can be integrated with drone sensing, command, and control, part of a growing field of physical AI. Large language models (LLMs) can be advantageous if trained at scale on general knowledge, but especially and in particular when the training data includes information such as detailed map geography topology of the entire planet, as well as the ability to access real time situational data such as weather. However, challenges remain in the interface between drones and LLMs in general, with each application requiring a tedious, labor intensive effort to connect the LLM trained knowledge to drone command and control. Here, we solve that problem, using an interface strategy that is LLM agnostic and drone agnostic, providing the first universal, versatile, comprehensive and easy to use drone control interface. We do this using the new model context protocol (MCP) standard, an open standard that provides a universal way for AI systems to access external data, tools, and services. We develop and deploy a cloud based Linux machine hosting an MCP server that supports the Mavlink protocol, an ubiquitous drone control language used almost universally by millions of drones including Ardupilot and PX4 framework.We demonstrate flight control of a real unmanned aerial vehicle. In further testing, we demonstrate extensive flight planning and control capability in a simulated drone, integrated with a Google Maps MCP server for up to date, real time navigation information. This demonstrates a universal approach to integration of LLMs with drone command and control, a paradigm that leverages and exploits virtually all of modern AI industry with drone technology in an easy to use interface that translates natural language to drone control.

Standard autoregressive decoding in large language models (LLMs) is inherently short-sighted, often failing to find globally optimal reasoning paths due to its token-by-token generation process. While inference-time strategies like foresight sampling attempt to mitigate this by simulating future steps, they typically rely on ad-hoc heuristics for valuing paths and pruning the search space. This paper introduces Martingale Foresight Sampling (MFS), a principled framework that reformulates LLM decoding as a problem of identifying an optimal stochastic process. By modeling the quality of a reasoning path as a stochastic process, we leverage Martingale theory to design a theoretically-grounded algorithm. Our approach replaces heuristic mechanisms with principles from probability theory: step valuation is derived from the Doob Decomposition Theorem to measure a path's predictable advantage, path selection uses Optional Stopping Theory for principled pruning of suboptimal candidates, and an adaptive stopping rule based on the Martingale Convergence Theorem terminates exploration once a path's quality has provably converged. Experiments on six reasoning benchmarks demonstrate that MFS surpasses state-of-the-art methods in accuracy while significantly improving computational efficiency. Code will be released at https://github.com/miraclehetech/EACL2026-Martingale-Foresight-Sampling.

Emergency Department overcrowding is a critical issue that compromises patient safety and operational efficiency, necessitating accurate demand forecasting for effective resource allocation. This study evaluates and compares three distinct predictive models: Seasonal AutoRegressive Integrated Moving Average with eXogenous regressors (SARIMAX), EXtreme Gradient Boosting (XGBoost) and Long Short-Term Memory (LSTM) networks for forecasting daily ED arrivals over a seven-day horizon. Utilizing data from an Australian tertiary referral hospital spanning January 2017 to December 2021, this research distinguishes itself by decomposing demand into eight specific ward categories and stratifying patients by clinical complexity. To address data distortions caused by the COVID-19 pandemic, the study employs the Prophet model to generate synthetic counterfactual values for the anomalous period. Experimental results demonstrate that all three proposed models consistently outperform a seasonal naive baseline. XGBoost demonstrated the highest accuracy for predicting total daily admissions with a Mean Absolute Error of 6.63, while the statistical SARIMAX model proved marginally superior for forecasting major complexity cases with an MAE of 3.77. The study concludes that while these techniques successfully reproduce regular day-to-day patterns, they share a common limitation in underestimating sudden, infrequent surges in patient volume.

This paper examines how to make large language models reliable for high-stakes legal work by reducing hallucinations. It distinguishes three AI paradigms: (1) standalone generative models ("creative oracle"), (2) basic retrieval-augmented systems ("expert archivist"), and (3) an advanced, end-to-end optimized RAG system ("rigorous archivist"). The authors introduce two reliability metrics -False Citation Rate (FCR) and Fabricated Fact Rate (FFR)- and evaluate 2,700 judicial-style answers from 12 LLMs across 75 legal tasks using expert, double-blind review. Results show that standalone models are unsuitable for professional use (FCR above 30%), while basic RAG greatly reduces errors but still leaves notable misgrounding. Advanced RAG, using techniques such as embedding fine-tuning, re-ranking, and self-correction, reduces fabrication to negligible levels (below 0.2%). The study concludes that trustworthy legal AI requires rigor-focused, retrieval-based architectures emphasizing verification and traceability, and provides an evaluation framework applicable to other high-risk domains.

Training modern deep learning models is increasingly constrained by GPU memory and compute limits. While Randomized Numerical Linear Algebra (RandNLA) offers proven techniques to compress these models, the lack of a unified, production-grade library prevents widely adopting these methods. We present Panther, a PyTorch-compatible library that consolidates established RandNLA algorithms into a single high-performance framework. Panther engineers efficient, drop-in replacements for standard components including sketched linear layers, 2D convolution, multi-head attention, and randomized matrix decompositions (such as pivoted CholeskyQR). By implementing a custom C++/CUDA backend (pawX), Panther provides an optimized implementation that can run on both CPUs and GPUs. We demonstrate the effectiveness of RandNLA techniques and Panther's ease of adoption. By replacing standard PyTorch linear layers with Panther layers (requiring only a few lines of code) we achieve significant memory savings (up to 75%) on BERT while maintaining comparable loss. Source code is available (MIT License) at https://github.com/FahdSeddik/panther, along with demonstration video at https://youtu.be/7M3RQb4KWxs.

The integration of Large Language Models (LLMs) into the public health policy sector offers a transformative approach to navigating the vast repositories of regulatory guidance maintained by agencies such as the Centers for Disease Control and Prevention (CDC). However, the propensity for LLMs to generate hallucinations, defined as plausible but factually incorrect assertions, presents a critical barrier to the adoption of these technologies in high-stakes environments where information integrity is non-negotiable. This empirical evaluation explores the effectiveness of Retrieval-Augmented Generation (RAG) architectures in mitigating these risks by grounding generative outputs in authoritative document context. Specifically, this study compares a baseline Vanilla LLM against Basic RAG and Advanced RAG pipelines utilizing cross-encoder re-ranking. The experimental framework employs a Mistral-7B-Instruct-v0.2 model and an all-MiniLM-L6-v2 embedding model to process a corpus of official CDC policy analytical frameworks and guidance documents. The analysis measures the impact of two distinct chunking strategies, recursive character-based and token-based semantic splitting, on system accuracy, measured through faithfulness and relevance scores across a curated set of complex policy scenarios. Quantitative findings indicate that while Basic RAG architectures provide a substantial improvement in faithfulness (0.621) over Vanilla baselines (0.347), the Advanced RAG configuration achieves a superior faithfulness average of 0.797. These results demonstrate that two-stage retrieval mechanisms are essential for achieving the precision required for domain-specific policy question answering, though structural constraints in document segmentation remain a significant bottleneck for multi-step reasoning tasks.