Prompt engineering for large language models is challenging, as even small prompt perturbations or model changes can significantly impact the generated output texts. Existing evaluation methods of LLM outputs, either automated metrics or human evaluation, have limitations, such as providing limited insights or being labor-intensive. We propose Spotlight, a new approach that combines both automation and human analysis. Based on data mining techniques, we automatically distinguish between random (decoding) variations and systematic differences in language model outputs. This process provides token patterns that describe the systematic differences and guide the user in manually analyzing the effects of their prompts and changes in models efficiently. We create three benchmarks to quantitatively test the reliability of token pattern extraction methods and demonstrate that our approach provides new insights into established prompt data. From a human-centric perspective, through demonstration studies and a user study, we show that our token pattern approach helps users understand the systematic differences of language model outputs. We are further able to discover relevant differences caused by prompt and model changes (e.g. related to gender or culture), thus supporting the prompt engineering process and human-centric model behavior research.
Large Language Model (LLM)-based in-application assistants, or copilots, can automate software tasks, but users often prefer learning by doing, raising questions about the optimal level of automation for an effective user experience. We investigated two automation paradigms by designing and implementing a fully automated copilot (AutoCopilot) and a semi-automated copilot (GuidedCopilot) that automates trivial steps while offering step-by-step visual guidance. In a user study (N=20) across data analysis and visual design tasks, GuidedCopilot outperformed AutoCopilot in user control, software utility, and learnability, especially for exploratory and creative tasks, while AutoCopilot saved time for simpler visual tasks. A follow-up design exploration (N=10) enhanced GuidedCopilot with task-and state-aware features, including in-context preview clips and adaptive instructions. Our findings highlight the critical role of user control and tailored guidance in designing the next generation of copilots that enhance productivity, support diverse skill levels, and foster deeper software engagement.
The NIME conference traditionally focuses on interfaces for music and musical expression. In this paper we reverse this tradition to ask, can interfaces developed for music be successfully appropriated to non-musical applications? To help answer this question we designed and developed a new device, which uses interface metaphors borrowed from analogue synthesisers and audio mixing to physically control the intangible aspects of a Large Language Model. We compared two versions of the device, with and without the audio-inspired augmentations, with a group of artists who used each version over a one week period. Our results show that the use of audio-like controls afforded more immediate, direct and embodied control over the LLM, allowing users to creatively experiment and play with the device over its non-mixer counterpart. Our project demonstrates how cross-sensory metaphors can support creative thinking and embodied practice when designing new technological interfaces.
Long-term action anticipation (LTA) aims to predict future actions over an extended period. Previous approaches primarily focus on learning exclusively from video data but lack prior knowledge. Recent researches leverage large language models (LLMs) by utilizing text-based inputs which suffer severe information loss. To tackle these limitations single-modality methods face, we propose a novel Intention-Conditioned Vision-Language (ICVL) model in this study that fully leverages the rich semantic information of visual data and the powerful reasoning capabilities of LLMs. Considering intention as a high-level concept guiding the evolution of actions, we first propose to employ a vision-language model (VLM) to infer behavioral intentions as comprehensive textual features directly from video inputs. The inferred intentions are then fused with visual features through a multi-modality fusion strategy, resulting in intention-enhanced visual representations. These enhanced visual representations, along with textual prompts, are fed into LLM for future action anticipation. Furthermore, we propose an effective example selection strategy jointly considers visual and textual similarities, providing more relevant and informative examples for in-context learning. Extensive experiments with state-of-the-art performance on Ego4D, EPIC-Kitchens-55, and EGTEA GAZE+ datasets fully demonstrate the effectiveness and superiority of the proposed method.
Movie Dubbing aims to convert scripts into speeches that align with the given movie clip in both temporal and emotional aspects while preserving the vocal timbre of a given brief reference audio. Existing methods focus primarily on reducing the word error rate while ignoring the importance of lip-sync and acoustic quality. To address these issues, we propose a large language model (LLM) based flow matching architecture for dubbing, named FlowDubber, which achieves high-quality audio-visual sync and pronunciation by incorporating a large speech language model and dual contrastive aligning while achieving better acoustic quality via the proposed voice-enhanced flow matching than previous works. First, we introduce Qwen2.5 as the backbone of LLM to learn the in-context sequence from movie scripts and reference audio. Then, the proposed semantic-aware learning focuses on capturing LLM semantic knowledge at the phoneme level. Next, dual contrastive aligning (DCA) boosts mutual alignment with lip movement, reducing ambiguities where similar phonemes might be confused. Finally, the proposed Flow-based Voice Enhancing (FVE) improves acoustic quality in two aspects, which introduces an LLM-based acoustics flow matching guidance to strengthen clarity and uses affine style prior to enhance identity when recovering noise into mel-spectrograms via gradient vector field prediction. Extensive experiments demonstrate that our method outperforms several state-of-the-art methods on two primary benchmarks. The demos are available at {\href{https://galaxycong.github.io/LLM-Flow-Dubber/}{\textcolor{red}{https://galaxycong.github.io/LLM-Flow-Dubber/}}}.
The integration of artificial intelligence in healthcare has opened new horizons for improving medical diagnostics and patient care. However, challenges persist in developing systems capable of generating accurate and contextually relevant radiology reports, particularly in low-resource languages. In this study, we present a comprehensive benchmark to evaluate the performance of instruction-tuned Vision-Language Models (VLMs) in the specialized task of radiology report generation across three low-resource languages: Italian, German, and Spanish. Employing the LLaVA architectural framework, we conducted a systematic evaluation of pre-trained models utilizing general datasets, domain-specific datasets, and low-resource language-specific datasets. In light of the unavailability of models that possess prior knowledge of both the medical domain and low-resource languages, we analyzed various adaptations to determine the most effective approach for these contexts. The results revealed that language-specific models substantially outperformed both general and domain-specific models in generating radiology reports, emphasizing the critical role of linguistic adaptation. Additionally, models fine-tuned with medical terminology exhibited enhanced performance across all languages compared to models with generic knowledge, highlighting the importance of domain-specific training. We also explored the influence of the temperature parameter on the coherence of report generation, providing insights for optimal model settings. Our findings highlight the importance of tailored language and domain-specific training for improving the quality and accuracy of radiological reports in multilingual settings. This research not only advances our understanding of VLMs adaptability in healthcare but also points to significant avenues for future investigations into model tuning and language-specific adaptations.
Generative models have revolutionized Artificial Intelligence (AI), particularly in multimodal applications. However, adapting these models to the medical domain poses unique challenges due to the complexity of medical data and the stringent need for clinical accuracy. In this work, we introduce a framework specifically designed for multimodal medical data generation. By enabling the generation of multi-view chest X-rays and their associated clinical report, it bridges the gap between general-purpose vision-language models and the specialized requirements of healthcare. Leveraging the MIMIC-CXR dataset, the proposed framework shows superior performance in generating high-fidelity images and semantically coherent reports. Our quantitative evaluation reveals significant results in terms of FID and BLEU scores, showcasing the quality of the generated data. Notably, our framework achieves comparable or even superior performance compared to real data on downstream disease classification tasks, underlining its potential as a tool for medical research and diagnostics. This study highlights the importance of domain-specific adaptations in enhancing the relevance and utility of generative models for clinical applications, paving the way for future advancements in synthetic multimodal medical data generation.
Effective data visualization requires not only technical proficiency but also a deep understanding of the domain-specific context in which data exists. This context often includes tacit knowledge about data provenance, quality, and intended use, which is rarely explicit in the dataset itself. We present the Data Therapist, a web-based tool that helps domain experts externalize this implicit knowledge through a mixed-initiative process combining iterative Q&A with interactive annotation. Powered by a large language model, the system analyzes user-supplied datasets, prompts users with targeted questions, and allows annotation at varying levels of granularity. The resulting structured knowledge base can inform both human and automated visualization design. We evaluated the tool in a qualitative study involving expert pairs from Molecular Biology, Accounting, Political Science, and Usable Security. The study revealed recurring patterns in how experts reason about their data and highlights areas where AI support can improve visualization design.
Reasoning stands as a cornerstone of intelligence, enabling the synthesis of existing knowledge to solve complex problems. Despite remarkable progress, existing reasoning benchmarks often fail to rigorously evaluate the nuanced reasoning capabilities required for complex, real-world problemsolving, particularly in multi-disciplinary and multimodal contexts. In this paper, we introduce a graduate-level, multi-disciplinary, EnglishChinese benchmark, dubbed as Reasoning Bench (R-Bench), for assessing the reasoning capability of both language and multimodal models. RBench spans 1,094 questions across 108 subjects for language model evaluation and 665 questions across 83 subjects for multimodal model testing in both English and Chinese. These questions are meticulously curated to ensure rigorous difficulty calibration, subject balance, and crosslinguistic alignment, enabling the assessment to be an Olympiad-level multi-disciplinary benchmark. We evaluate widely used models, including OpenAI o1, GPT-4o, DeepSeek-R1, etc. Experimental results indicate that advanced models perform poorly on complex reasoning, especially multimodal reasoning. Even the top-performing model OpenAI o1 achieves only 53.2% accuracy on our multimodal evaluation. Data and code are made publicly available at here.
Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities in multimodal tasks, but visual object hallucination remains a persistent issue. It refers to scenarios where models generate inaccurate visual object-related information based on the query input, potentially leading to misinformation and concerns about safety and reliability. Previous works focus on the evaluation and mitigation of visual hallucinations, but the underlying causes have not been comprehensively investigated. In this paper, we analyze each component of LLaVA-like LVLMs -- the large language model, the vision backbone, and the projector -- to identify potential sources of error and their impact. Based on our observations, we propose methods to mitigate hallucination for each problematic component. Additionally, we developed two hallucination benchmarks: QA-VisualGenome, which emphasizes attribute and relation hallucinations, and QA-FB15k, which focuses on cognition-based hallucinations.
The rapid expansion of IoT ecosystems introduces severe challenges in scalability, security, and real-time decision-making. Traditional centralized architectures struggle with latency, privacy concerns, and excessive resource consumption, making them unsuitable for modern large-scale IoT deployments. This paper presents a novel Federated Learning-driven Large Language Model (FL-LLM) framework, designed to enhance IoT system intelligence while ensuring data privacy and computational efficiency. The framework integrates Generative IoT (GIoT) models with a Gradient Sensing Federated Strategy (GSFS), dynamically optimizing model updates based on real-time network conditions. By leveraging a hybrid edge-cloud processing architecture, our approach balances intelligence, scalability, and security in distributed IoT environments. Evaluations on the IoT-23 dataset demonstrate that our framework improves model accuracy, reduces response latency, and enhances energy efficiency, outperforming traditional FL techniques (i.e., FedAvg, FedOpt). These findings highlight the potential of integrating LLM-powered federated learning into large-scale IoT ecosystems, paving the way for more secure, scalable, and adaptive IoT management solutions.
Charging infrastructure is not expanding quickly enough to accommodate the increasing usage of Electric Vehicles (EVs). For this reason, EV owners experience extended waiting periods, range anxiety, and overall dissatisfaction. Challenges, such as fragmented data and the complexity of integrating factors like location, energy pricing, and user preferences, make the current recommendation systems ineffective. To overcome these limitations, we propose RecomBot, which is a Large Language Model (LLM)-powered prompt-based recommender system that dynamically suggests optimal Charging Stations (CSs) using real-time heterogeneous data. By leveraging natural language reasoning and fine-tuning EV-specific datasets, RecomBot enhances personalization, improves charging efficiency, and adapts to various EV types, offering a scalable solution for intelligent EV recommendation systems. Through testing across various prompt engineering scenarios, the results obtained underline the capability and efficiency of the proposed model.
Urban Air Mobility (UAM) is an emerging System of System (SoS) that faces challenges in system architecture, planning, task management, and execution. Traditional architectural approaches struggle with scalability, adaptability, and seamless resource integration within dynamic and complex environments. This paper presents an intelligent holonic architecture that incorporates Large Language Model (LLM) to manage the complexities of UAM. Holons function semi autonomously, allowing for real time coordination among air taxis, ground transport, and vertiports. LLMs process natural language inputs, generate adaptive plans, and manage disruptions such as weather changes or airspace closures.Through a case study of multimodal transportation with electric scooters and air taxis, we demonstrate how this architecture enables dynamic resource allocation, real time replanning, and autonomous adaptation without centralized control, creating more resilient and efficient urban transportation networks. By advancing decentralized control and AI driven adaptability, this work lays the groundwork for resilient, human centric UAM ecosystems, with future efforts targeting hybrid AI integration and real world validation.
Antenna modeling is a time-consuming and complex process, decreasing the speed of antenna analysis and design. In this paper, a large language model (LLM)- enabled antenna modeling method, called LEAM, is presented to address this challenge. LEAM enables automatic antenna model generation based on language descriptions via prompt input, images, descriptions from academic papers, patents, and technical reports (either one or multiple). The effectiveness of LEAM is demonstrated by three examples: a Vivaldi antenna generated from a complete user description, a slotted patch antenna generated from an incomplete user description and the operating frequency, and a monopole slotted antenna generated from images and descriptions scanned from the literature. For all the examples, correct antenna models are generated in a few minutes. The code can be accessed via https://github.com/TaoWu974/LEAM.
Accurate classification of focal liver lesions is crucial for diagnosis and treatment in hepatology. However, traditional supervised deep learning models depend on large-scale annotated datasets, which are often limited in medical imaging. Recently, Vision-Language models (VLMs) such as Contrastive Language-Image Pre-training model (CLIP) has been applied to image classifications. Compared to the conventional convolutional neural network (CNN), which classifiers image based on visual information only, VLM leverages multimodal learning with text and images, allowing it to learn effectively even with a limited amount of labeled data. Inspired by CLIP, we pro-pose a Liver-VLM, a model specifically designed for focal liver lesions (FLLs) classification. First, Liver-VLM incorporates class information into the text encoder without introducing additional inference overhead. Second, by calculating the pairwise cosine similarities between image and text embeddings and optimizing the model with a cross-entropy loss, Liver-VLM ef-fectively aligns image features with class-level text features. Experimental results on MPCT-FLLs dataset demonstrate that the Liver-VLM model out-performs both the standard CLIP and MedCLIP models in terms of accuracy and Area Under the Curve (AUC). Further analysis shows that using a lightweight ResNet18 backbone enhances classification performance, particularly under data-constrained conditions.
Retrieval-augmented generation (RAG) systems have predominantly focused on text-based retrieval, limiting their effectiveness in handling visually-rich documents that encompass text, images, tables, and charts. To bridge this gap, we propose a unified multi-granularity multimodal retrieval framework tailored for two benchmark tasks: MMDocIR and M2KR. Our approach integrates hierarchical encoding strategies, modality-aware retrieval mechanisms, and vision-language model (VLM)-based candidate filtering to effectively capture and utilize the complex interdependencies between textual and visual modalities. By leveraging off-the-shelf vision-language models and implementing a training-free hybrid retrieval strategy, our framework demonstrates robust performance without the need for task-specific fine-tuning. Experimental evaluations reveal that incorporating layout-aware search and VLM-based candidate verification significantly enhances retrieval accuracy, achieving a top performance score of 65.56. This work underscores the potential of scalable and reproducible solutions in advancing multimodal document retrieval systems.
While significant progress has been made in research and development on open-source and cost-efficient large-language models (LLMs), serving scalability remains a critical challenge, particularly for small organizations and individuals seeking to deploy and test their LLM innovations. Inspired by peer-to-peer networks that leverage decentralized overlay nodes to increase throughput and availability, we propose GenTorrent, an LLM serving overlay that harnesses computing resources from decentralized contributors. We identify four key research problems inherent to enabling such a decentralized infrastructure: 1) overlay network organization; 2) LLM communication privacy; 3) overlay forwarding for resource efficiency; and 4) verification of serving quality. This work presents the first systematic study of these fundamental problems in the context of decentralized LLM serving. Evaluation results from a prototype implemented on a set of decentralized nodes demonstrate that GenTorrent achieves a latency reduction of over 50% compared to the baseline design without overlay forwarding. Furthermore, the security features introduce minimal overhead to serving latency and throughput. We believe this work pioneers a new direction for democratizing and scaling future AI serving capabilities.
We evaluate the current state of collective communication on GPU-based supercomputers for large language model (LLM) training at scale. Existing libraries such as RCCL and Cray-MPICH exhibit critical limitations on systems such as Frontier -- Cray-MPICH underutilizes network and compute resources, while RCCL suffers from severe scalability issues. To address these challenges, we introduce PCCL, a communication library with highly optimized implementations of all-gather and reduce-scatter operations tailored for distributed deep learning workloads. PCCL is designed to maximally utilize all available network and compute resources and to scale efficiently to thousands of GPUs. It achieves substantial performance improvements, delivering 6-33x speedups over RCCL and 28-70x over Cray-MPICH for all-gather on 2048 GCDs of Frontier. These gains translate directly to end-to-end performance: in large-scale GPT-3-style training, PCCL provides up to 60% and 40% speedups over RCCL for 7B and 13B parameter models, respectively.
Hallucinations in vision-language models (VLMs) hinder reliability and real-world applicability, usually stemming from distribution shifts between pretraining data and test samples. Existing solutions, such as retraining or fine-tuning on additional data, demand significant computational resources and labor-intensive data collection, while ensemble-based methods incur additional costs by introducing auxiliary VLMs. To address these challenges, we propose a novel test-time adaptation framework using reinforcement learning to mitigate hallucinations during inference without retraining or any auxiliary VLMs. By updating only the learnable parameters in the layer normalization of the language model (approximately 0.003% of the model parameters), our method reduces distribution shifts between test samples and pretraining samples. A CLIP-based hallucination evaluation model is proposed to provide dual rewards to VLMs. Experimental results demonstrate a 15.4% and 17.3% reduction in hallucination rates on LLaVA and InstructBLIP, respectively. Our approach outperforms state-of-the-art baselines with a 68.3% improvement in hallucination mitigation, demonstrating its effectiveness.
Speculative decoding accelerates large language model inference by using smaller draft models to generate candidate tokens for parallel verification. However, current approaches are limited by sequential stage dependencies that prevent full hardware utilization. We present PipeSpec, a framework that generalizes speculative decoding to $k$ models arranged in a hierarchical pipeline, enabling asynchronous execution with lightweight coordination for prediction verification and rollback. Our analytical model characterizes token generation rates across pipeline stages and proves guaranteed throughput improvements over traditional decoding for any non-zero acceptance rate. We further derive closed-form expressions for steady-state verification probabilities that explain the empirical benefits of pipeline depth. Experimental results show that PipeSpec achieves up to 2.54$\times$ speedup while outperforming state-of-the-art methods. We validate PipeSpec across text summarization and code generation tasks using LLaMA 2 and 3 models, demonstrating that pipeline efficiency increases with model depth, providing a scalable approach to accelerating LLM inference on multi-device systems.