Multimodal Large Language Models (MLLMs) have transformed text-to-image workflows, allowing designers to create novel visual concepts with unprecedented speed. This progress has given rise to a thriving prompt trading market, where curated prompts that induce trademark styles are bought and sold. Although commercially attractive, prompt trading also introduces a largely unexamined security risk: the prompts themselves can be stolen. In this paper, we expose this vulnerability and present RLStealer, a reinforcement learning based prompt inversion framework that recovers its template from only a small set of example images. RLStealer treats template stealing as a sequential decision making problem and employs multiple similarity based feedback signals as reward functions to effectively explore the prompt space. Comprehensive experiments on publicly available benchmarks demonstrate that RLStealer gets state-of-the-art performance while reducing the total attack cost to under 13% of that required by existing baselines. Our further analysis confirms that RLStealer can effectively generalize across different image styles to efficiently steal unseen prompt templates. Our study highlights an urgent security threat inherent in prompt trading and lays the groundwork for developing protective standards in the emerging MLLMs marketplace.

Cultural awareness capabilities has emerged as a critical capability for Multimodal Large Language Models (MLLMs). However, current benchmarks lack progressed difficulty in their task design and are deficient in cross-lingual tasks. Moreover, current benchmarks often use real-world images. Each real-world image typically contains one culture, making these benchmarks relatively easy for MLLMs. Based on this, we propose C$^3$B ($\textbf{C}$omics $\textbf{C}$ross-$\textbf{C}$ultural $\textbf{B}$enchmark), a novel multicultural, multitask and multilingual cultural awareness capabilities benchmark. C$^3$B comprises over 2000 images and over 18000 QA pairs, constructed on three tasks with progressed difficulties, from basic visual recognition to higher-level cultural conflict understanding, and finally to cultural content generation. We conducted evaluations on 11 open-source MLLMs, revealing a significant performance gap between MLLMs and human performance. The gap demonstrates that C$^3$B poses substantial challenges for current MLLMs, encouraging future research to advance the cultural awareness capabilities of MLLMs.

Abstract--Pharmacokinetics (PK) plays a critical role in drug development and regulatory decision-making for human and veterinary medicine, directly affecting public health through drug safety and efficacy assessments. However, PK data are often embedded in complex, heterogeneous tables with variable structures and inconsistent terminologies, posing significant challenges for automated PK data retrieval and standardization. In the first stage, AutoPK identifies and extracts PK parameter variants using large language models (LLMs), a hybrid similarity metric, and LLMbased validation. The second stage filters relevant rows, converts the table into a key-value text format, and uses an LLM to reconstruct a standardized, machine-readable table. Evaluated on a real-world dataset of 605 annotated PK tables, including captions and footnotes, AutoPK demonstrates significant improvements in precision and recall over direct LLM baselines. For instance, AutoPK with LLaMA 3.1-70B achieved an F1-score of 0.92 on half-life and 0.91 on clearance parameters, outperforming direct use of LLaMA 3.1-70B by margins of 0.10 and 0.21, respectively. Smaller models such as Gemma 3-27B and Phi 3-12B with AutoPK achieved 2-7 fold F1 gains over their direct use, with Gemma's hallucination rates reduced from 60-95% down to 8-14%. Notably, AutoPK enabled open-source models like Gemma 3-27B to outperform commercial systems such as GPT -4o Mini on several PK parameters. AutoPK enables scalable and high-confidence PK data extraction, making it well-suited for critical applications in veterinary pharmacology, drug safety monitoring, and public health decision-making, while addressing heterogeneous table structures and terminology and demonstrating generalizability across key PK parameters. Personal use of this material is permitted. This is the author's version of the work accepted for publication in: Proceedings of the 2025 IEEE 37th International Conference on Tools with Artificial Intelligence (ICT AI). The final published version will be available via IEEE Xplore.

The widespread adoption of large language and vision models in real-world applications has made urgent the need to address hallucinations -- instances where models produce incorrect or nonsensical outputs. These errors can propagate misinformation during deployment, leading to both financial and operational harm. Although much research has been devoted to mitigating hallucinations, our understanding of it is still incomplete and fragmented. Without a coherent understanding of hallucinations, proposed solutions risk mitigating surface symptoms rather than underlying causes, limiting their effectiveness and generalizability in deployment. To tackle this gap, we first present a unified, multi-level framework for characterizing both image and text hallucinations across diverse applications, aiming to reduce conceptual fragmentation. We then link these hallucinations to specific mechanisms within a model's lifecycle, using a task-modality interleaved approach to promote a more integrated understanding. Our investigations reveal that hallucinations often stem from predictable patterns in data distributions and inherited biases. By deepening our understanding, this survey provides a foundation for developing more robust and effective solutions to hallucinations in real-world generative AI systems.

Electroencephalography (EEG) interpretation using multimodal large language models (MLLMs) offers a novel approach for analyzing brain signals. However, the complex nature of brain activity introduces critical challenges: EEG signals simultaneously encode both cognitive processes and intrinsic neural states, creating a mismatch in EEG paired-data modality that hinders effective cross-modal representation learning. Through a pivot investigation, we uncover complementary relationships between these modalities. Leveraging this insight, we propose mapping EEG signals and their corresponding modalities into a unified semantic space to achieve generalized interpretation. To fully enable conversational capabilities, we further introduce WaveMind-Instruct-338k, the first cross-task EEG dataset for instruction tuning. The resulting model demonstrates robust classification accuracy while supporting flexible, open-ended conversations across four downstream tasks, thereby offering valuable insights for both neuroscience research and the development of general-purpose EEG models.

We propose VibeCodeHPC, an automatic tuning system for HPC programs based on multi-agent LLMs for code generation. VibeCodeHPC tunes programs through multi-agent role allocation and iterative prompt refinement. We describe the system configuration with four roles: Project Manager (PM), System Engineer (SE), Programmer (PG), and Continuous Delivery (CD). We introduce dynamic agent deployment and activity monitoring functions to facilitate effective multi-agent collaboration. In our case study, we convert and optimize CPU-based matrix-matrix multiplication code written in C to GPU code using CUDA. The multi-agent configuration of VibeCodeHPC achieved higher-quality code generation per unit time compared to a solo-agent configuration. Additionally, the dynamic agent deployment and activity monitoring capabilities facilitated more effective identification of requirement violations and other issues.

Extending the context window support of large language models (LLMs) is crucial for tasks with long-distance dependencies. RoPE-based interpolation and extrapolation methods, such as linear scaling and frequency-aware schemes, enable longer input length support without retraining, while post-training quantization (PTQ) makes deployment practical. However, we show that combining RoPE position interpolation (PI) with PTQ degrades accuracy due to coupled effects including long-context aliasing, dynamic-range dilation, anisotropy from axis-aligned quantizers vs. rotated RoPE pairs, and outlier shifting that produces position-dependent logit noise. We provide, to the best of our knowledge, the first systematic analysis of the PI+PTQ approach and introduce two practical diagnostics: interpolation pressure (per-band sensitivity to phase scaling) and tail-inflation ratios (outlier shift from short to long contexts). Following the analysis results, we propose Q-ROAR (Quantization, RoPE-interpolation, and Outlier Aware Rescaling), a weight-only, interpolation-aware stabilization of PI for quantized LLMs. Q-ROAR groups RoPE dimensions into a small number of frequency bands and performs a lightweight search over per-band scales for Key and Query weights (with an optional symmetric variant to preserve logit scale). The search is guided by our diagnostics and uses a tiny long-context development dataset, requiring no fine-tuning to the model, no architecture or kernel changes, and no additional deployment overhead. Empirically, Q-ROAR reduces the model's perplexity on long-context workloads by more than 14%, while preserving short-context performance, inference throughput, and compatibility with existing LLM system stacks.

Large Language Models (LLMs) offer new opportunities to automate complex interdisciplinary research domains. Epidemic modeling, characterized by its complexity and reliance on network science, dynamical systems, epidemiology, and stochastic simulations, represents a prime candidate for leveraging LLM-driven automation. We introduce \textbf{EpidemIQs}, a novel multi-agent LLM framework that integrates user inputs and autonomously conducts literature review, analytical derivation, network modeling, mechanistic modeling, stochastic simulations, data visualization and analysis, and finally documentation of findings in a structured manuscript. We introduced two types of agents: a scientist agent for planning, coordination, reflection, and generation of final results, and a task-expert agent to focus exclusively on one specific duty serving as a tool to the scientist agent. The framework consistently generated complete reports in scientific article format. Specifically, using GPT 4.1 and GPT 4.1 mini as backbone LLMs for scientist and task-expert agents, respectively, the autonomous process completed with average total token usage 870K at a cost of about \$1.57 per study, achieving a 100\% completion success rate through our experiments. We evaluate EpidemIQs across different epidemic scenarios, measuring computational cost, completion success rate, and AI and human expert reviews of generated reports. We compare EpidemIQs to the single-agent LLM, which has the same system prompts and tools, iteratively planning, invoking tools, and revising outputs until task completion. The comparison shows consistently higher performance of the proposed framework across five different scenarios. EpidemIQs represents a step forward in accelerating scientific research by significantly reducing costs and turnaround time of discovery processes, and enhancing accessibility to advanced modeling tools.

Abstract--Conversational Recommender Systems (CRSs) aim to provide personalized recommendations through multi-turn natural language interactions with users. Given the strong interaction and reasoning skills of Large Language Models (LLMs), leveraging LLMs for CRSs has recently emerged as a promising direction. However, existing LLM-based methods often lack explicit optimization of interaction strategies, instead relying on unified prompts and the LLM's internal knowledge to decide how to interact, which can lead to suboptimal outcomes. In this paper, we propose a novel R einforced S trategy O ptimization (RSO) method for CRS, which decomposes the process of generating strategy-driven response decisions into the macro-level strategy planning and micro-level strategy adaptation through a network-of-experts architecture. At the macro level, a Planner expert selects macro-level interaction strategies (e.g., recommend, explain, encourage). At the micro level, an Actor expert generates detailed responses conditioned on the selected macro-level strategy, guided by auxiliary experts that provide complementary information such as user preferences and factual grounding. This hierarchical decomposition disentangles the optimization of different sub-tasks involved in CRS response generation, enabling more tractable learning at each level. T o address the scarcity of high-quality multi-turn training data, we formulate strategy learning as a reinforcement learning problem, guided by an LLMbased reward model to achieve automatic strategy exploration. Extensive experiments show that RSO significantly improves interaction performance compared to state-of-the-art baselines, demonstrating the effectiveness of explicit hierarchical strategy optimization for CRS. Conversational Recommender Systems (CRSs) [3]-[9] aim to interact with users through natural language conversation, elicit their preferences, and refine recommendations to maximize user satisfaction and acceptance of the recommendations. X. Zhao and H. Cheng are with The Chinese University of Hong Kong, Hong Kong, China. M. Y an is with the University of Science and Technology of China, Hefei, China. Qiu, and T. Chua are with the National University of Singapore, Singapore.

We introduce mpLLM, a prompt-conditioned hierarchical mixture-of-experts (MoE) architecture for visual question answering over multi-parametric 3D brain MRI (mpMRI). mpLLM routes across modality-level and token-level projection experts to fuse multiple interrelated 3D modalities, enabling efficient training without image-report pretraining. To address limited image-text paired supervision, mpLLM integrates a synthetic visual question answering (VQA) protocol that generates medically relevant VQA from segmentation annotations, and we collaborate with medical experts for clinical validation. mpLLM outperforms strong medical VLM baselines by 5.3% on average across multiple mpMRI datasets. Our study features three main contributions: (1) the first clinically validated VQA dataset for 3D brain mpMRI, (2) a novel multimodal LLM that handles multiple interrelated 3D modalities, and (3) strong empirical results that demonstrate the medical utility of our methodology. Ablations highlight the importance of modality-level and token-level experts and prompt-conditioned routing.