FADA: Accessible fetal ultrasound interpretation and annotation with a selectively distilled unified vision-language model

A global shortage of trained sonographers limits prenatal ultrasound screening in low- and middle-income countries, where over half of pregnant women receive no skilled sonography. Current deep learning approaches address detection, segmentation, or classification in isolation, each demanding a separate model and expert-specified labels at inference. We present FADA, a unified vision-language model built on Qwen3.5-VL that performs clinical interpretation, classification, detection, and segmentation through a single interpretation-first pipeline without external labels. FADA distills knowledge from four domain-specific foundation models (FetalCLIP, UltraSAM, USF-MAE, UltraFedFM) via offline pre-computed feature caching. Selective distillation, which applies feature alignment only to annotation tasks while interpretation relies on standard fine-tuning, consistently outperforms full distillation across most evaluation axes. The recommended variant, FADA-SKD, achieves 0.8820 mean Dice for segmentation, 0.7671 mAP@0.50 for detection, and 100% structured interpretation compliance. Expert sonographer validation across 237 images confirms clinically acceptable outputs in both autonomous and human-in-the-loop modes, with 73.5% of interpretations scoring perfectly under clinician guidance. The system is trainable on a single consumer GPU and deployable without cloud connectivity. We validate edge deployment by running the compressed 0.8B model on a commodity smartphone (Qualcomm Snapdragon 7 Gen 1, 12 GB RAM) using llama.cpp with GGUF quantization, completing the full 5-phase pipeline in approximately 60 seconds entirely offline. This establishes a practical pathway for integrating AI-assisted fetal assessment with portable ultrasound devices, directly addressing diagnostic access gaps in resource-constrained settings. Code, models, and data are available at https://github.com/mahmoodphd/FADA.

Generative Archetype-Grounded Item Representations for Sequential Recommendation

Sequential recommendation aims to predict users' next interaction with items by analyzing their historical behavior. However, the limited quality of item representations remains a critical bottleneck. While pre-trained large language models (LLMs) can provide rich semantic representations, existing approaches only rely on static encoding of fixed attributes, overlooking the crucial role of target audiences in defining item identity. Moreover, the semantic space struggles to reflect actual user behavior, resulting in a significant gap between semantic representations and behavioral patterns. To address these limitations, we propose GenAIR, a general framework that empowers sequential recommendation with Generative Archetype-grounded Item Representations. Specifically, we first leverage an LLM to analyze item metadata and infer textual description of the Archetype, which represents the conceptual profile of the item's ideal target audience. We then extract the corresponding embeddings in a single forward pass. Further, to ground these generative archetypes in real-world behavior, we introduce a behavioral calibration objective, which explicitly incorporates behavioral signals from actual interactions. This objective adjusts the structure of the embedding space to reflect empirical patterns. GenAIR enables seamless integration with most existing models while maintaining high efficiency. Comprehensive experiments conducted on three real-world datasets demonstrate that GenAIR significantly improves the performance of various sequential recommendation models and consistently outperforms state-of-the-art baseline approaches. Implementation codes are available at https://github.com/AI-Santiago/GenAIR.

From Prompt to Purchase: How AI Brand Recommendations Move Consumers on the Open Web

When a conversational assistant recommends a brand to a user with no recent observed engagement, that user's same-name Google search rises +4.3 percentage points (pp) [3.1, 5.5], visits to the brand's own site +2.4 pp [1.4, 3.5], and brand-specific retailer-page visits +1.0 pp [0.3, 1.7] over matched backward placebos. Recovering that estimate is the work. The mention creates a brand exposure no web log attributes to the assistant, and the naive all-mention funnel that seems to measure it is confounded: many mentions are incidental references to brands the user already uses ("your Netflix download"), whose downstream visits are that existing customer's own behavior and surface as a brand-specific pre-trend. We measure off-platform response on a panel that joins opt-in clickstream to the same users' ChatGPT, Claude, and Gemini conversations, and isolate the effect with a pre-trend event study, a stance classifier, non-customer conditioning, and a within-response same-category control: incidental name-drops then move behavior far less (+1.8/+1.1/+0.3), and the named brand moves far more than unnamed same-category brands in the same response. The downstream path is mostly search-mediated and reaches both own sites and retailer pages, with a destination mix that tracks baseline brand-directed behavior rather than redirecting toward either. The design is observational and we do not observe transactions, so retail is purchase-adjacent. Standard referrer-based and last-click measurement miss this upstream exposure: assistants move observably-unengaged users into open-web brand navigation along a path attributed elsewhere.

Closing the Modality Gap in Zero-Shot HAR: Contrastive Training and Separability-Optimized Prototypes on IMU Data

Zero-shot learning (ZSL) for inertial measurement unit (IMU)-based human activity recognition (HAR) faces a central challenge: bridging the gap between sensor embeddings and semantic class representations. We systematically evaluate seven configurations combining three inference methods with two training pipelines on the PAMAP2 dataset, using 14 seen and 4 unseen activity classes with subjects 108 and 109 held out for testing. We find that the modality gap is a training-time phenomenon governed by the encoder objective. A temporal convolutional network (TCN) trained with cross-entropy over label-name Sentence- BERT prototypes yields sensor embeddings with a mean cosine similarity of 0.30 to the corresponding text prototypes, while replacing the label-name prototype targets with discriminative activity descriptions raises this to 0.69. This alignment improvement transfers consistently across all three inference methods. The strongest result combines contrastive training with inverted softmax correction, achieving 73.2% accuracy and 0.583 macro F1 on unseen classes, compared to 58.3% accuracy and 0.34 macro F1 for the label-name baseline. A secondary finding is that richer text descriptions reduce inter-prototype separability in Sentence-BERT space, because shared biomechanical vocabulary causes the language model to compress the prototype cloud. This effect does not negate the benefits of contrastive alignment provided prototype descriptions retain sufficient discriminative vocabulary. We also demonstrate that overall accuracy is a misleading primary metric when test-set class distributions are imbalanced, and recommend macro-averaged F1 as the standard reporting metric for ZSL-HAR benchmarks.

Detecting Speculative Language in Biomedical Texts using Recurrent Neural Tensor Networks

In this investigation, we delve into the automated detection of speculative language within biomedical articles by utilizing distributed sentence representations and advanced deep learning techniques. The implications of such identification extend to information retrieval, multi-document summarization, and the exploration of new knowledge. Our exploration encompasses two distinct approaches for acquiring distributed sentence representations: the Paragraph Vector model and the Recursive Neural Tensor Network. These methodologies are then rigorously compared against three foundational baseline algorithms: Support Vector Machines, Naive Bayes, and pattern matching. Our findings reveal that the Recursive Neural Tensor Network (RNTN) demonstrates a slight performance edge (F1 = 0.885) over the top-performing baseline, the linear bigram SVM (F1 = 0.881). Meanwhile, the Paragraph Vector model proves less effective (F1 = 0.368), even after extensive training using an expansive, unlabeled dataset. We engage in a comprehensive discourse on the factors influencing these performance disparities and provide insightful recommendations for future research directions.

A Unified Multi-Modal Framework for Intelligent Financial Systems: Integrating Reinforcement Learning, High-Frequency Trading, and Game-Theoretic Approaches with Cross-Modal Sentiment Analysis

The rapid evolution of financial technology demands sophisticated artificial intelligence systems capable of handling diverse challenges across multiple domains simultaneously. This paper presents a groundbreaking unified framework that seamlessly integrates Proximal Policy Optimization for robo-advisory systems, advanced time-series prediction models for high-frequency trading, in-context learning mechanisms for dynamic investment advisory, game-theoretic approaches for competitive banking scenarios, and unified embeddings for cross-modal financial sentiment analysis. Our comprehensive framework addresses the critical gap in existing literature where these technologies have been developed in isolation, failing to leverage their synergistic potential. Through extensive experimentation across multiple financial datasets and real-world scenarios, we demonstrate that our integrated approach achieves superior performance compared to specialized single-domain systems. Specifically, our framework shows a 23.7% improvement in portfolio optimization metrics, reduces prediction error in high-frequency trading by 31.2%, enhances investment recommendation accuracy by 18.9%, optimizes competitive banking strategies with a 27.4% increase in Nash equilibrium convergence speed, and improves sentiment analysis accuracy by 15.6% through cross-modal fusion. The theoretical foundation of our work establishes convergence guarantees for the integrated optimization problem, while our empirical results validate the practical applicability across diverse financial institutions. This research not only advances the state-of-the-art in financial AI but also provides a blueprint for developing comprehensive intelligent systems that can adapt to the complex, interconnected nature of modern financial markets.

SIDInspector: A Mapping-First Diagnostic Resource for Semantic-ID Tokenizers

Semantic-ID (\sid) tokenizers are increasingly reused as standalone artifacts in generative recommendation: an exported item-to-code mapping becomes the address space that a later sequence generator must use. These mappings rarely come with a common inspection interface, so coverage gaps, full-code aliasing, behaviorally weak prefixes, tail compression, and prefix fan-out are often found only after downstream training. We present \tool, a mapping-first diagnostic resource for \sid tokenizer artifacts. \tool defines a small adapter contract over item mappings, metadata, interactions, and optional generator traces; validates the contract; and reports mapping-level probes for utilization, aliasing, neighborhood alignment, popularity allocation, and structural cost, with hooks for temporal churn and generator traces. \tool reports inspectable artifact profiles before downstream leaderboard scores. The released resource covers four tokenizer artifact lines: a same-item GRID/RQ-KMeans-style and ReSID/GAOQ contrast on 23,742 Musical items, plus released LETTER and LC-Rec item-index artifacts. In the Musical contrast, the GRID-style feature-text export has 3,749 unique full codes and a 0.977 full-code aliasing rate, while ReSID/GAOQ is aliasing-free in its exported mapping. Yet the strongest prefix--co-occurrence alignment comes from a deterministic category-prefix control, not from either learned export row (0.447 versus 0.154 and 0.055--0.080), showing that addressability and behaviorally meaningful prefixes should be inspected separately. Cross-domain, fixed-reranker, and mechanism-probe checks support the same diagnostic direction: prefix alignment is a candidate-exposure signal, while final ranking quality remains a downstream model question.

Atomic Intent Reasoning: Bringing LLM Semantics to Industrial Cross-Domain Recommendations

Cross-domain recommendation is a core problem in content-to-e-commerce platforms. Its objective is to leverage user interactions with content to infer potential purchasing intent on the e-commerce side, thereby enhancing conversion rates and commercial value. However, in real industrial scenarios, cross-domain recommendation faces multiple challenges: significant semantic gaps exist between different domains, and user cross-domain behavior sequences are often massive in scale and rich in noise. Although large language models (LLMs) possess powerful semantic understanding and reasoning capabilities, their millisecond-level inference latency makes direct application in online recommendation systems difficult. To address these issues, this paper introduces AIR (Atomic Intent Reasoning), an LLM-driven cross-domain recommendation framework designed for industrial-grade deployment. By migrating LLM inference to the offline phase and dynamically constructing user intent representations through efficient retrieval and composition during online operations, it achieves approximately 400* inference acceleration while maintaining semantic consistency. Experimental results across multiple public datasets demonstrate that our method achieves state-of-the-art performance in cross-domain recommendation tasks. Furthermore, large-scale online A/B testing conducted in Kuaishou E-commerce's real-world business scenarios shows that our approach delivers stable and significant improvements across multiple core business metrics, including a +3.446% increase in GMV, fully validating its effectiveness and practical value in industrial-scale recommendation systems.

Gryphon: A Unified Architecture for Semantic-ID Generation and Item-Level Scoring in Industrial Recommendations

Generative retrieval (GR) has become a scalable approach to candidate generation: each item is assigned a short hierarchical token sequence called a Semantic ID (SID), and the next item's SID is decoded autoregressively. A practical limitation is that the decoder's beam search optimizes the likelihood of token sequences, not the relevance of the underlying items. These objectives diverge when sequence likelihood is poorly calibrated due to beam search error accumulation, and when several items collapse onto a single SID and receive identical scores. We introduce Gryphon, an encoder-decoder generative recommendation architecture that adds a jointly trained item-level scoring component alongside SID generation, reusing the encoder's user representation computed in a single forward pass. Instead of ranking SIDs by accumulated token likelihood, Gryphon resolves each generated SID to its concrete items and re-scores those items directly, which sidesteps miscalibrated sequence scores and separates items that collide on the same identifier. On an industrial music service, with item-level scoring trained under a next-item-prediction objective, Gryphon attains the highest item-level Recall@1000, above the strongest baselines (+3.7% over vanilla GR and +2.5% over collision-resolved GR) at comparable parameter count and latency. Gryphon's item-level ranking also surpasses its beam-likelihood ranking of the same candidates (+4.2% gain), demonstrating the benefit of item-level scoring in GR. Deployed as the sole candidate source in a 7-day A/B test, Gryphon produced no statistically significant change in total listening time (+0.25%) while replacing a pipeline of more than 15 candidate generators and a separate preranking stage, substantially simplifying the candidate-generation system.

Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text Generation

Human evaluation plays a critical role in assessing the quality of generated text. However, the reliability and reproducibility of these evaluations depend on transparent and well-documented protocols -- details that are frequently missing in current practice. In this work, we conduct a large-scale analysis of human evaluation protocols for evaluating long-form generation tasks in *CL conference publications from 2023--2025, including a full manual review of 284 papers and LLM-assisted analysis for another 1.8k+ papers. We define a set of 20 reportable criteria related to reproducibility of human evaluation studies, and apply these criteria to systematically examine reporting norms and practices within the community. We find widespread under-reporting of important aspects of human evaluation study design, leading to ambiguity about what was measured and how, who contributed judgments, and how judgments should be interpreted. Based on these findings, we outline actionable recommendations to support more transparent and reproducible reporting in future research. Our analysis code and annotated dataset can be found at: https://github.com/larchlab/Illusions-of-the-Gold-Standard