The integration of Retrieval-Augmented Generation (RAG) with Multimodal Large Language Models (MLLMs) has revolutionized information retrieval and expanded the practical applications of AI. However, current systems struggle in accurately interpreting user intent, employing diverse retrieval strategies, and effectively filtering unintended or inappropriate responses, limiting their effectiveness. This paper introduces Contextual Understanding and Enhanced Search with MLLM (CUE-M), a novel multimodal search framework that addresses these challenges through a multi-stage pipeline comprising image context enrichment, intent refinement, contextual query generation, external API integration, and relevance-based filtering. CUE-M incorporates a robust filtering pipeline combining image-based, text-based, and multimodal classifiers, dynamically adapting to instance- and category-specific concern defined by organizational policies. Evaluations on a multimodal Q&A dataset and a public safety benchmark demonstrate that CUE-M outperforms baselines in accuracy, knowledge integration, and safety, advancing the capabilities of multimodal retrieval systems.

In this work, we propose the first motion transfer approach in diffusion transformer through Mixture of Score Guidance (MSG), a theoretically-grounded framework for motion transfer in diffusion models. Our key theoretical contribution lies in reformulating conditional score to decompose motion score and content score in diffusion models. By formulating motion transfer as a mixture of potential energies, MSG naturally preserves scene composition and enables creative scene transformations while maintaining the integrity of transferred motion patterns. This novel sampling operates directly on pre-trained video diffusion models without additional training or fine-tuning. Through extensive experiments, MSG demonstrates successful handling of diverse scenarios including single object, multiple objects, and cross-object motion transfer as well as complex camera motion transfer. Additionally, we introduce MotionBench, the first motion transfer dataset consisting of 200 source videos and 1000 transferred motions, covering single/multi-object transfers, and complex camera motions.

Fake news on social media platforms poses a significant threat to societal systems, underscoring the urgent need for advanced detection methods. The existing detection methods can be divided into machine intelligence-based, crowd intelligence-based, and hybrid intelligence-based methods. Among them, hybrid intelligence-based methods achieve the best performance but fail to consider the reliability issue in detection. In light of this, we propose a novel Reliability Aware Hybrid Intelligence (RAHI) method for fake news detection. Our method comprises three integral modules. The first module employs a Bayesian deep learning model to capture the inherent reliability within machine intelligence. The second module uses an Item Response Theory (IRT)-based user response aggregation to account for the reliability in crowd intelligence. The third module introduces a new distribution fusion mechanism, which takes the distributions derived from both machine and crowd intelligence as input, and outputs a fused distribution that provides predictions along with the associated reliability. The experiments on the Weibo dataset demonstrate the advantages of our method. This study contributes to the research field with a novel RAHI-based method, and the code is shared at https://github.com/Kangwei-g/RAHI. This study has practical implications for three key stakeholders: internet users, online platform managers, and the government.

If you've ever watched a movie with closed captioning, you've probably seen [APPLAUSE] or [dramatic music] pop up at the bottom of the screen to help people who are deaf or hard of hearing better understand the non-dialog audio elements that shape what's happening in a scene. Google is bringing a similar capability to the Android mobile operating system, and, naturally, it's powered by artificial intelligence. This is one of many new features coming to Android and Google Pixel devices today. Expressive Captions is a new tool that's part of Google's existing Live Caption feature, which enables captions on almost any media playing on your phone, no matter what app you're in. The new addition expands the scope by captioning tone and nonspeech elements.

This paper explores transformer-based models for music overpainting, focusing on jazz piano variations. Music overpainting generates new variations while preserving the melodic and harmonic structure of the input. Existing approaches are limited by small datasets, restricting scalability and diversity. We introduce VAR4000, a subset of a larger dataset for jazz piano performances, consisting of 4,352 training pairs. Using a semi-automatic pipeline, we evaluate two transformer configurations on VAR4000, comparing their performance with the smaller JAZZVAR dataset. Preliminary results show promising improvements in generalisation and performance with the larger dataset configuration, highlighting the potential of transformer models to scale effectively for music overpainting on larger and more diverse datasets.

Recent advances in diffusion models have revolutionized 2D and 3D content creation, yet generating photorealistic dynamic 4D scenes remains a significant challenge. Existing dynamic 4D generation methods typically rely on distilling knowledge from pre-trained 3D generative models, often fine-tuned on synthetic object datasets. Consequently, the resulting scenes tend to be object-centric and lack photorealism. While text-to-video models can generate more realistic scenes with motion, they often struggle with spatial understanding and provide limited control over camera viewpoints during rendering. To address these limitations, we present PaintScene4D, a novel text-to-4D scene generation framework that departs from conventional multi-view generative models in favor of a streamlined architecture that harnesses video generative models trained on diverse real-world datasets. Our method first generates a reference video using a video generation model, and then employs a strategic camera array selection for rendering. We apply a progressive warping and inpainting technique to ensure both spatial and temporal consistency across multiple viewpoints. Finally, we optimize multi-view images using a dynamic renderer, enabling flexible camera control based on user preferences. Adopting a training-free architecture, our PaintScene4D efficiently produces realistic 4D scenes that can be viewed from arbitrary trajectories. The code will be made publicly available. Our project page is at https://paintscene4d.github.io/

Large Language Models (LLMs) have shown impressive results in multiple domains of natural language processing (NLP) but are mainly focused on the English language. Recently, more LLMs have incorporated a larger proportion of multilingual text to represent low-resource languages. In Arabic NLP, several Arabic-centric LLMs have shown remarkable results on multiple benchmarks in the past two years. However, most Arabic LLMs have more than 7 billion parameters, which increases their hardware requirements and inference latency, when compared to smaller LLMs. This paper introduces Arabic Stable LM 1.6B in a base and chat version as a small but powerful Arabic-centric LLM. Our Arabic Stable LM 1.6B chat model achieves impressive results on several benchmarks beating multiple models with up to 8x the parameters. In addition, we show the benefit of mixing in synthetic instruction tuning data by augmenting our fine-tuning data with a large synthetic dialogue dataset.

Artificial Intelligence (AI) song generation has emerged as a popular topic, yet the focus on exploring the latent correlations between specific lyrical and rhythmic features remains limited. In contrast, this pilot study particularly investigates the relationships between keywords and rhythmically stressed features such as strong beats in songs. It focuses on several key elements: keywords or non-keywords, stressed or unstressed syllables, and strong or weak beats, with the aim of uncovering insightful correlations. Experimental results indicate that, on average, 80.8\% of keywords land on strong beats, whereas 62\% of non-keywords fall on weak beats. The relationship between stressed syllables and strong or weak beats is weak, revealing that keywords have the strongest relationships with strong beats. Additionally, the lyrics-rhythm matching score, a key matching metric measuring keywords on strong beats and non-keywords on weak beats across various time signatures, is 0.765, while the matching score for syllable types is 0.495. This study demonstrates that word types strongly align with their corresponding beat types, as evidenced by the distinct patterns, whereas syllable types exhibit a much weaker alignment. This disparity underscores the greater reliability of word types in capturing rhythmic structures in music, highlighting their crucial role in effective rhythmic matching and analysis. We also conclude that keywords that consistently align with strong beats are more reliable indicators of lyrics-rhythm associations, providing valuable insights for AI-driven song generation through enhanced structural analysis. Furthermore, our development of tailored Lyrics-Rhythm Matching (LRM) metrics maximizes lyrical alignments with corresponding beat stresses, and our novel LRM file format captures critical lyrical and rhythmic information without needing original sheet music.

Social interactions are fundamental to human life. The recent emergence of large language models (LLMs)-based virtual assistants has demonstrated their potential to revolutionize human interactions and lifestyles. However, existing assistive systems mainly provide reactive services to individual users, rather than offering in-situ assistance during live social interactions with conversational partners. In this study, we introduce SocialMind, the first LLM-based proactive AR social assistive system that provides users with in-situ social assistance. SocialMind employs human-like perception leveraging multi-modal sensors to extract both verbal and nonverbal cues, social factors, and implicit personas, incorporating these social cues into LLM reasoning for social suggestion generation. Additionally, SocialMind employs a multi-tier collaborative generation strategy and proactive update mechanism to display social suggestions on Augmented Reality (AR) glasses, ensuring that suggestions are timely provided to users without disrupting the natural flow of conversation. Evaluations on three public datasets and a user study with 20 participants show that SocialMind achieves 38.3% higher engagement compared to baselines, and 95% of participants are willing to use SocialMind in their live social interactions.

Generative AI is rapidly reshaping creative work, raising critical questions about its beneficiaries and societal implications. This study challenges prevailing assumptions by exploring how generative AI interacts with diverse forms of human capital in creative tasks. Through two random controlled experiments in flash fiction writing and song composition, we uncover a paradox: while AI democratizes access to creative tools, it simultaneously amplifies cognitive inequalities. Our findings reveal that AI enhances general human capital (cognitive abilities and education) by facilitating adaptability and idea integration but diminishes the value of domain-specific expertise. We introduce a novel theoretical framework that merges human capital theory with the automation-augmentation perspective, offering a nuanced understanding of human-AI collaboration. This framework elucidates how AI shifts the locus of creative advantage from specialized expertise to broader cognitive adaptability. Contrary to the notion of AI as a universal equalizer, our work highlights its potential to exacerbate disparities in skill valuation, reshaping workplace hierarchies and redefining the nature of creativity in the AI era. These insights advance theories of human capital and automation while providing actionable guidance for organizations navigating AI integration amidst workforce inequalities.