arXiv subjects

Man Luo

Publications and source records attributed to Man Luo.

At least 37 records · Page 2Linked to original sources

arXiv2025

CityVerse: A Unified Data Platform for Multi-Task Urban Computing with Large Language Models

Large Language Models (LLMs) show remarkable potential for urban computing, from spatial reasoning to predictive analytics. However, evaluating LLMs across diverse urban tasks faces two critical challenges: lack of unified platforms for consistent multi-source data access and fragmented task definitions that hinder fair comparison. To address these challenges, we present CityVerse, the first unified platform integrating multi-source urban data, capability-based task taxonomy, and dynamic simulation for systematic LLM evaluation in urban contexts. CityVerse provides: 1) coordinate-based Data APIs unifying ten categories of urban data-including spatial features, temporal dynamics, demographics, and multi-modal imagery-with over 38 million curated records; 2) Task APIs organizing 43 urban computing tasks into a four-level cognitive hierarchy: Perception, Spatial Understanding, Reasoning and Prediction, and Decision and Interaction, enabling standardized evaluation across capability levels; 3) an interactive visualization frontend supporting real-time data retrieval, multi-layer display, and simulation replay for intuitive exploration and validation. We validate the platform's effectiveness through evaluations on mainstream LLMs across representative tasks, demonstrating its capability to support reproducible and systematic assessment. CityVerse provides a reusable foundation for advancing LLMs and multi-task approaches in the urban computing domain.

cs.DB↗

arXiv2025

DDL: A Large-Scale Datasets for Deepfake Detection and Localization in Diversified Real-World Scenarios

Recent advances in AIGC have exacerbated the misuse of malicious deepfake content, making the development of reliable deepfake detection methods an essential means to address this challenge. Although existing deepfake detection models demonstrate outstanding performance in detection metrics, most methods only provide simple binary classification results, lacking interpretability. Recent studies have attempted to enhance the interpretability of classification results by providing spatial manipulation masks or temporal forgery segments. However, due to the limitations of forgery datasets, the practical effectiveness of these methods remains suboptimal. The primary reason lies in the fact that most existing deepfake datasets contain only binary labels, with limited variety in forgery scenarios, insufficient diversity in deepfake types, and relatively small data scales, making them inadequate for complex real-world scenarios.To address this predicament, we construct a novel large-scale deepfake detection and localization (\textbf{DDL}) dataset containing over $\textbf{1.4M+}$ forged samples and encompassing up to $\textbf{80}$ distinct deepfake methods. The DDL design incorporates four key innovations: (1) \textbf{Comprehensive Deepfake Methods} (covering 7 different generation architectures and a total of 80 methods), (2) \textbf{Varied Manipulation Modes} (incorporating 7 classic and 3 novel forgery modes), (3) \textbf{Diverse Forgery Scenarios and Modalities} (including 3 scenarios and 3 modalities), and (4) \textbf{Fine-grained Forgery Annotations} (providing 1.18M+ precise spatial masks and 0.23M+ precise temporal segments).Through these improvements, our DDL not only provides a more challenging benchmark for complex real-world forgeries but also offers crucial support for building next-generation deepfake detection, localization, and interpretability methods.

cs.CV↗

arXiv2025

GeoThought: A Dataset for Enhancing Mathematical Geometry Reasoning in Vision-Language Models

Large language models (LLMs) have demonstrated strong reasoning capabilities in text-based mathematical problem solving; however, when adapted to visual reasoning tasks, particularly geometric problem solving, their performance substantially declines because geometric problems present unique challenges. Specifically, these challenges stem from two key factors: first, the intrinsic complexity of geometry requiring detailed image comprehension and multi-step reasoning, and second, the limitations of existing datasets which lack sufficient scale, diversity, and explicit reasoning traces, consequently hindering effective model training. To address these challenges, we developed the GeoThoughts dataset, a comprehensive geometric reasoning corpus with two subsets: Geo-Thought-6K with 6,243 samples and its augmented version Geo-Thought-Augmented-10K containing 10,834 samples. Each entry includes visual descriptions, step-by-step solutions, explicit reasoning chains, reflection steps, and final answers. Using this dataset, we developed GeoThought-MLLM, a mathematical reasoning multimodal model that generates detailed thinking processes during problem-solving. Our model outperforms existing benchmarks in geometric tasks, demonstrating that training with our Chain-of-Thought dataset improves geometric reasoning capabilities across both in-domain and out-of-domain settings. Finally, we analyze failure cases and observe that errors primarily arise from incorrect interpretation of mathematical concepts or spatial misjudgment. By invoking CoT to correct these mistakes, the model produces correct answers.

cs.AI↗

arXiv2025

Investigating VLM Hallucination from a Cognitive Psychology Perspective: A First Step Toward Interpretation with Intriguing Observations

Hallucination is a long-standing problem that has been actively investigated in Vision-Language Models (VLMs). Existing research commonly attributes hallucinations to technical limitations or sycophancy bias, where the latter means the models tend to generate incorrect answers to align with user expectations. However, these explanations primarily focus on technical or externally driven factors, and may have neglected the possibility that hallucination behaviours might mirror cognitive biases observed in human psychology. In this work, we introduce a psychological taxonomy, categorizing VLMs' cognitive biases that lead to hallucinations, including sycophancy, logical inconsistency, and a newly identified VLMs behaviour: appeal to authority. To systematically analyze these behaviours, we design AIpsych, a scalable benchmark that reveals psychological tendencies in model response patterns. Leveraging this benchmark, we investigate how variations in model architecture and parameter size influence model behaviour when responding to strategically manipulated questions. Our experiments reveal that as model size increases, VLMs exhibit stronger sycophantic tendencies but reduced authority bias, suggesting increasing competence but a potential erosion of response integrity. A human subject study further validates our hypotheses and highlights key behavioural differences between VLMs and human respondents. This work suggests a new perspective for understanding hallucination in VLMs and highlights the importance of integrating psychological principles into model evaluation.

cs.CV↗

arXiv2025

MFFI: Multi-Dimensional Face Forgery Image Dataset for Real-World Scenarios

Rapid advances in Artificial Intelligence Generated Content (AIGC) have enabled increasingly sophisticated face forgeries, posing a significant threat to social security. However, current Deepfake detection methods are limited by constraints in existing datasets, which lack the diversity necessary in real-world scenarios. Specifically, these data sets fall short in four key areas: unknown of advanced forgery techniques, variability of facial scenes, richness of real data, and degradation of real-world propagation. To address these challenges, we propose the Multi-dimensional Face Forgery Image (\textbf{MFFI}) dataset, tailored for real-world scenarios. MFFI enhances realism based on four strategic dimensions: 1) Wider Forgery Methods; 2) Varied Facial Scenes; 3) Diversified Authentic Data; 4) Multi-level Degradation Operations. MFFI integrates $50$ different forgery methods and contains $1024K$ image samples. Benchmark evaluations show that MFFI outperforms existing public datasets in terms of scene complexity, cross-domain generalization capability, and detection difficulty gradients. These results validate the technical advance and practical utility of MFFI in simulating real-world conditions. The dataset and additional details are publicly available at {https://github.com/inclusionConf/MFFI}.

cs.CV↗

arXiv2025

REVOLVE: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization

Recent advancements in large language models (LLMs) have significantly enhanced the ability of LLM-based systems to perform complex tasks through natural language processing and tool interaction. However, optimizing these LLM-based systems for specific tasks remains challenging, often requiring manual interventions like prompt engineering and hyperparameter tuning. Existing automatic optimization methods, such as textual feedback-based techniques (e.g., TextGrad), tend to focus on immediate feedback, analogous to using immediate derivatives in traditional numerical gradient descent. However, relying solely on such feedback can be limited when the adjustments made in response to this feedback are either too small or fluctuate irregularly, potentially slowing down or even stalling the optimization process. To overcome these challenges, more adaptive methods are needed, especially in situations where the system's response is evolving slowly or unpredictably. In this paper, we introduce REVOLVE, an optimization method that tracks how "R"esponses "EVOLVE" across iterations in LLM systems. By focusing on the evolution of responses over time, REVOLVE enables more stable and effective optimization by making thoughtful, progressive adjustments at each step. Experimental results demonstrate that REVOLVE outperforms competitive baselines, achieving a 7.8% improvement in prompt optimization, a 20.72% gain in solution refinement, and a 29.17% increase in code optimization. Additionally, REVOLVE converges in fewer iterations, resulting in significant computational savings. Beyond its practical contributions, REVOLVE highlights a promising direction, where the rich knowledge from established optimization principles can be leveraged to enhance LLM systems, which paves the way for further advancements in this hybrid domain.

cs.CL↗

arXiv2025

InfoFlood: Jailbreaking Large Language Models with Information Overload

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. However, their potential to generate harmful responses has raised significant societal and regulatory concerns, especially when manipulated by adversarial techniques known as "jailbreak" attacks. Existing jailbreak methods typically involve appending carefully crafted prefixes or suffixes to malicious prompts in order to bypass the built-in safety mechanisms of these models. In this work, we identify a new vulnerability in which excessive linguistic complexity can disrupt built-in safety mechanisms-without the need for any added prefixes or suffixes-allowing attackers to elicit harmful outputs directly. We refer to this phenomenon as Information Overload. To automatically exploit this vulnerability, we propose InfoFlood, a jailbreak attack that transforms malicious queries into complex, information-overloaded queries capable of bypassing built-in safety mechanisms. Specifically, InfoFlood: (1) uses linguistic transformations to rephrase malicious queries, (2) identifies the root cause of failure when an attempt is unsuccessful, and (3) refines the prompt's linguistic structure to address the failure while preserving its malicious intent. We empirically validate the effectiveness of InfoFlood on four widely used LLMs-GPT-4o, GPT-3.5-turbo, Gemini 2.0, and LLaMA 3.1-by measuring their jailbreak success rates. InfoFlood consistently outperforms baseline attacks, achieving up to 3 times higher success rates across multiple jailbreak benchmarks. Furthermore, we demonstrate that commonly adopted post-processing defenses, including OpenAI's Moderation API, Perspective API, and SmoothLLM, fail to mitigate these attacks. This highlights a critical weakness in traditional AI safety guardrails when confronted with information overload-based jailbreaks.

cs.CR↗

arXiv2025

SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs

Multimodal retrieval augmented generation (RAG) plays a crucial role in domains such as knowledge-based visual question answering (KB-VQA), where external knowledge is needed to answer a question. However, existing multimodal LLMs (MLLMs) are not designed for context-augmented generation, limiting their effectiveness in such tasks. While synthetic data generation has recently gained attention for training MLLMs, its application for context-augmented generation remains underexplored. To address this gap, we introduce SK-VQA, a large-scale synthetic multimodal dataset containing over 2 million visual question-answer pairs, each associated with context documents containing information necessary to determine the final answer. Compared to previous datasets, SK-VQA contains 11x more unique questions, exhibits greater domain diversity, and covers a broader spectrum of image sources. Through human evaluations, we confirm the high quality of the generated question-answer pairs and their contextual relevance. Extensive experiments show that SK-VQA serves both as a challenging KB-VQA benchmark and as an effective training resource for adapting MLLMs to context-augmented generation. Our results further indicate that models trained on SK-VQA demonstrate enhanced generalization in both context-aware VQA and multimodal RAG settings. SK-VQA is publicly available via Hugging Face Hub.

cs.CL↗

arXiv2025

Inclusion 2024 Global Multimedia Deepfake Detection Challenge: Towards Multi-dimensional Face Forgery Detection

In this paper, we present the Global Multimedia Deepfake Detection held concurrently with the Inclusion 2024. Our Multimedia Deepfake Detection aims to detect automatic image and audio-video manipulations including but not limited to editing, synthesis, generation, Photoshop,etc. Our challenge has attracted 1500 teams from all over the world, with about 5000 valid result submission counts. We invite the top 20 teams to present their solutions to the challenge, from which the top 3 teams are awarded prizes in the grand finale. In this paper, we present the solutions from the top 3 teams of the two tracks, to boost the research work in the field of image and audio-video forgery detection. The methodologies developed through the challenge will contribute to the development of next-generation deepfake detection systems and we encourage participants to open source their methods.

cs.CV↗

arXiv2025

DPO Learning with LLMs-Judge Signal for Computer Use Agents

Computer use agents (CUA) are systems that automatically interact with graphical user interfaces (GUIs) to complete tasks. CUA have made significant progress with the advent of large vision-language models (VLMs). However, these agents typically rely on cloud-based inference with substantial compute demands, raising critical privacy and scalability concerns, especially when operating on personal devices. In this work, we take a step toward privacy-preserving and resource-efficient agents by developing a lightweight vision-language model that runs entirely on local machines. To train this compact agent, we introduce an LLM-as-Judge framework that automatically evaluates and filters synthetic interaction trajectories, producing high-quality data for reinforcement learning without human annotation. Experiments on the OS-World benchmark demonstrate that our fine-tuned local model outperforms existing baselines, highlighting a promising path toward private, efficient, and generalizable GUI agents.

cs.AI↗

arXiv2025

Reasoning Can Hurt the Inductive Abilities of Large Language Models

Large Language Models (LLMs) have shown remarkable progress across domains, yet their ability to perform inductive reasoning - inferring latent rules from sparse examples - remains limited. It is often assumed that chain-of-thought (CoT) prompting, as used in Large Reasoning Models (LRMs), enhances such reasoning. We investigate this assumption with creating four controlled, diagnostic game-based tasks - chess, Texas Hold'em, dice games, and blackjack - with hidden human-defined rules. We find that CoT reasoning can degrade inductive performance, with LRMs often underperforming their non-reasoning counterparts. To explain this, we present a theoretical framework that reveals how reasoning steps can amplify error through three failure modes: incorrect sub-task decomposition, incorrect sub-task solving, and incorrect final answer summarization. Based on our theoretical and empirical analysis, we introduce structured interventions that adapt CoT generation according to our identified failure types. These interventions improve inductive accuracy without retraining. Our findings suggest that effective (CoT) reasoning depends not only on taking more steps but also on ensuring those steps are well-structured.

cs.CV↗

arXiv2025

From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models

Large foundation models (LFMs) are susceptible to two distinct vulnerabilities: hallucinations and jailbreak attacks. While typically studied in isolation, we observe that defenses targeting one often affect the other, hinting at a deeper connection. We propose a unified theoretical framework that models jailbreaks as token-level optimization and hallucinations as attention-level optimization. Within this framework, we establish two key propositions: (1) \textit{Similar Loss Convergence} - the loss functions for both vulnerabilities converge similarly when optimizing for target-specific outputs; and (2) \textit{Gradient Consistency in Attention Redistribution} - both exhibit consistent gradient behavior driven by shared attention dynamics. We validate these propositions empirically on LLaVA-1.5 and MiniGPT-4, showing consistent optimization trends and aligned gradients. Leveraging this connection, we demonstrate that mitigation techniques for hallucinations can reduce jailbreak success rates, and vice versa. Our findings reveal a shared failure mode in LFMs and suggest that robustness strategies should jointly address both vulnerabilities.

cs.CV↗

arXiv2025

Probing Semantic Routing in Large Mixture-of-Expert Models

In the past year, large (>100B parameter) mixture-of-expert (MoE) models have become increasingly common in the open domain. While their advantages are often framed in terms of efficiency, prior work has also explored functional differentiation through routing behavior. We investigate whether expert routing in large MoE models is influenced by the semantics of the inputs. To test this, we design two controlled experiments. First, we compare activations on sentence pairs with a shared target word used in the same or different senses. Second, we fix context and substitute the target word with semantically similar or dissimilar alternatives. Comparing expert overlap across these conditions reveals clear, statistically significant evidence of semantic routing in large MoE models.

cs.LG↗

arXiv2025

FastRM: An efficient and automatic explainability framework for multimodal generative models

Large Vision Language Models (LVLMs) have demonstrated remarkable reasoning capabilities over textual and visual inputs. However, these models remain prone to generating misinformation. Identifying and mitigating ungrounded responses is crucial for developing trustworthy AI. Traditional explainability methods such as gradient-based relevancy maps, offer insight into the decision process of models, but are often computationally expensive and unsuitable for real-time output validation. In this work, we introduce FastRM, an efficient method for predicting explainable Relevancy Maps of LVLMs. Furthermore, FastRM provides both quantitative and qualitative assessment of model confidence. Experimental results demonstrate that FastRM achieves a 99.8% reduction in computation time and a 44.4% reduction in memory footprint compared to traditional relevancy map generation. FastRM allows explainable AI to be more practical and scalable, thereby promoting its deployment in real-world applications and enabling users to more effectively evaluate the reliability of model outputs.

cs.AI↗

arXiv2025

Federated Learning for Traffic Flow Prediction with Synthetic Data Augmentation

Deep-learning based traffic prediction models require vast amounts of data to learn embedded spatial and temporal dependencies. The inherent privacy and commercial sensitivity of such data has encouraged a shift towards decentralised data-driven methods, such as Federated Learning (FL). Under a traditional Machine Learning paradigm, traffic flow prediction models can capture spatial and temporal relationships within centralised data. In reality, traffic data is likely distributed across separate data silos owned by multiple stakeholders. In this work, a cross-silo FL setting is motivated to facilitate stakeholder collaboration for optimal traffic flow prediction applications. This work introduces an FL framework, referred to as FedTPS, to generate synthetic data to augment each client's local dataset by training a diffusion-based trajectory generation model through FL. The proposed framework is evaluated on a large-scale real world ride-sharing dataset using various FL methods and Traffic Flow Prediction models, including a novel prediction model we introduce, which leverages Temporal and Graph Attention mechanisms to learn the Spatio-Temporal dependencies embedded within regional traffic flow data. Experimental results show that FedTPS outperforms multiple other FL baselines with respect to global model performance.

cs.LG↗

arXiv2025

FiVL: A Framework for Improved Vision-Language Alignment through the Lens of Training, Evaluation and Explainability

Large Vision Language Models (LVLMs) have achieved significant progress in integrating visual and textual inputs for multimodal reasoning. However, a recurring challenge is ensuring these models utilize visual information as effectively as linguistic content when both modalities are necessary to formulate an accurate answer. We hypothesize that hallucinations arise due to the lack of effective visual grounding in current LVLMs. Furthermore, current vision-language benchmarks are not specifically measuring the degree to which the answer require the visual input. This limitation makes it challenging to confirm that the image is truly necessary, particularly in tasks like visual question answering. In this work, we introduce FiVL, a novel method for constructing datasets designed to train LVLMs for enhanced visual grounding and also evaluate their effectiveness in achieving it. We demonstrate the value of our datasets through three approaches. First, we introduce a novel training task based on our augmented training dataset, resulting in better performance than the baseline. Second, we present benchmarks to assess the model's ability to use image as substantive evidence, rather than relying solely on linguistic priors. Finally, we identify attention heads with the strongest vision-language alignment, enabling explainability on visual-driven hallucinations. The code is available at https://github.com/IntelLabs/fivl.

cs.CV↗

arXiv2025

Benchmark on Peer Review Toxic Detection: A Challenging Task with a New Dataset

Peer review is crucial for advancing and improving science through constructive criticism. However, toxic feedback can discourage authors and hinder scientific progress. This work explores an important but underexplored area: detecting toxicity in peer reviews. We first define toxicity in peer reviews across four distinct categories and curate a dataset of peer reviews from the OpenReview platform, annotated by human experts according to these definitions. Leveraging this dataset, we benchmark a variety of models, including a dedicated toxicity detection model, a sentiment analysis model, several open-source large language models (LLMs), and two closed-source LLMs. Our experiments explore the impact of different prompt granularities, from coarse to fine-grained instructions, on model performance. Notably, state-of-the-art LLMs like GPT-4 exhibit low alignment with human judgments under simple prompts but achieve improved alignment with detailed instructions. Moreover, the model's confidence score is a good indicator of better alignment with human judgments. For example, GPT-4 achieves a Cohen's Kappa score of 0.56 with human judgments, which increases to 0.63 when using only predictions with a confidence score higher than 95%. Overall, our dataset and benchmarks underscore the need for continued research to enhance toxicity detection capabilities of LLMs. By addressing this issue, our work aims to contribute to a healthy and responsible environment for constructive academic discourse and scientific collaboration.

cs.CL↗

arXiv2024

Is Your Paper Being Reviewed by an LLM? Investigating AI Text Detectability in Peer Review

Peer review is a critical process for ensuring the integrity of published scientific research. Confidence in this process is predicated on the assumption that experts in the relevant domain give careful consideration to the merits of manuscripts which are submitted for publication. With the recent rapid advancements in the linguistic capabilities of large language models (LLMs), a new potential risk to the peer review process is that negligent reviewers will rely on LLMs to perform the often time consuming process of reviewing a paper. In this study, we investigate the ability of existing AI text detection algorithms to distinguish between peer reviews written by humans and different state-of-the-art LLMs. Our analysis shows that existing approaches fail to identify many GPT-4o written reviews without also producing a high number of false positive classifications. To address this deficiency, we propose a new detection approach which surpasses existing methods in the identification of GPT-4o written peer reviews at low levels of false positive classifications. Our work reveals the difficulty of accurately identifying AI-generated text at the individual review level, highlighting the urgent need for new tools and methods to detect this type of unethical application of generative AI.

cs.CL↗