arXiv subjects

Xiao Yang

Publications and source records attributed to Xiao Yang.

At least 109 records · Page 6Linked to original sources

arXiv2025

R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization

Financial markets pose fundamental challenges for asset return prediction due to their high dimensionality, non-stationarity, and persistent volatility. Despite advances in large language models and multi-agent systems, current quantitative research pipelines suffer from limited automation, weak interpretability, and fragmented coordination across key components such as factor mining and model innovation. In this paper, we propose R&D-Agent for Quantitative Finance, in short RD-Agent(Q), the first data-centric multi-agent framework designed to automate the full-stack research and development of quantitative strategies via coordinated factor-model co-optimization. RD-Agent(Q) decomposes the quant process into two iterative stages: a Research stage that dynamically sets goal-aligned prompts, formulates hypotheses based on domain priors, and maps them to concrete tasks, and a Development stage that employs a code-generation agent, Co-STEER, to implement task-specific code, which is then executed in real-market backtests. The two stages are connected through a feedback stage that thoroughly evaluates experimental outcomes and informs subsequent iterations, with a multi-armed bandit scheduler for adaptive direction selection. Empirically, RD-Agent(Q) achieves up to 2X higher annualized returns than classical factor libraries using 70% fewer factors, and outperforms state-of-the-art deep time-series models on real markets. Its joint factor-model optimization delivers a strong balance between predictive accuracy and strategy robustness. Our code is available at: https://github.com/microsoft/RD-Agent.

q-fin.CP↗

arXiv2025

A Challenging Benchmark of Anime Style Recognition

Given two images of different anime roles, anime style recognition (ASR) aims to learn abstract painting style to determine whether the two images are from the same work, which is an interesting but challenging problem. Unlike biometric recognition, such as face recognition, iris recognition, and person re-identification, ASR suffers from a much larger semantic gap but receives less attention. In this paper, we propose a challenging ASR benchmark. Firstly, we collect a large-scale ASR dataset (LSASRD), which contains 20,937 images of 190 anime works and each work at least has ten different roles. In addition to the large-scale, LSASRD contains a list of challenging factors, such as complex illuminations, various poses, theatrical colors and exaggerated compositions. Secondly, we design a cross-role protocol to evaluate ASR performance, in which query and gallery images must come from different roles to validate an ASR model is to learn abstract painting style rather than learn discriminative features of roles. Finally, we apply two powerful person re-identification methods, namely, AGW and TransReID, to construct the baseline performance on LSASRD. Surprisingly, the recent transformer model (i.e., TransReID) only acquires a 42.24% mAP on LSASRD. Therefore, we believe that the ASR task of a huge semantic gap deserves deep and long-term research. We will open our dataset and code at https://github.com/nkjcqvcpi/ASR.

cs.CV↗

arXiv2025

KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering

Retrieval-Augmented Generation (RAG) mitigates hallucination in Large Language Models (LLMs) by incorporating external data, with Knowledge Graphs (KGs) offering crucial information for question answering. Traditional Knowledge Graph Question Answering (KGQA) methods rely on semantic parsing, which typically retrieves knowledge strictly necessary for answer generation, thus often suffer from low coverage due to rigid schema requirements and semantic ambiguity. We present KERAG, a novel KG-based RAG pipeline that enhances QA coverage by retrieving a broader subgraph likely to contain relevant information. Our retrieval-filtering-summarization approach, combined with fine-tuned LLMs for Chain-of-Thought reasoning on knowledge sub-graphs, reduces noises and improves QA for both simple and complex questions. Experiments demonstrate that KERAG surpasses state-of-the-art solutions by about 7% in quality and exceeds GPT-4o (Tool) by 10-21%.

cs.CL↗

arXiv2025

Deep Reinforcement Learning for Ranking Utility Tuning in the Ad Recommender System at Pinterest

The ranking utility function in an ad recommender system, which linearly combines predictions of various business goals, plays a central role in balancing values across the platform, advertisers, and users. Traditional manual tuning, while offering simplicity and interpretability, often yields suboptimal results due to its unprincipled tuning objectives, the vast amount of parameter combinations, and its lack of personalization and adaptability to seasonality. In this work, we propose a general Deep Reinforcement Learning framework for Personalized Utility Tuning (DRL-PUT) to address the challenges of multi-objective optimization within ad recommender systems. Our key contributions include: 1) Formulating the problem as a reinforcement learning task: given the state of an ad request, we predict the optimal hyperparameters to maximize a pre-defined reward. 2) Developing an approach to directly learn an optimal policy model using online serving logs, avoiding the need to estimate a value function, which is inherently challenging due to the high variance and unbalanced distribution of immediate rewards. We evaluated DRL-PUT through an online A/B experiment in Pinterest's ad recommender system. Compared to the baseline manual utility tuning approach, DRL-PUT improved the click-through rate by 9.7% and the long click-through rate by 7.7% on the treated segment. We conducted a detailed ablation study on the impact of different reward definitions and analyzed the personalization aspect of the learned policy model.

cs.LG↗

arXiv2025

Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation

The trustworthiness of Multimodal Large Language Models (MLLMs) remains an intense concern despite the significant progress in their capabilities. Existing evaluation and mitigation approaches often focus on narrow aspects and overlook risks introduced by the multimodality. To tackle these challenges, we propose MultiTrust-X, a comprehensive benchmark for evaluating, analyzing, and mitigating the trustworthiness issues of MLLMs. We define a three-dimensional framework, encompassing five trustworthiness aspects which include truthfulness, robustness, safety, fairness, and privacy; two novel risk types covering multimodal risks and cross-modal impacts; and various mitigation strategies from the perspectives of data, model architecture, training, and inference algorithms. Based on the taxonomy, MultiTrust-X includes 32 tasks and 28 curated datasets, enabling holistic evaluations over 30 open-source and proprietary MLLMs and in-depth analysis with 8 representative mitigation methods. Our extensive experiments reveal significant vulnerabilities in current models, including a gap between trustworthiness and general capabilities, as well as the amplification of potential risks in base LLMs by both multimodal training and inference. Moreover, our controlled analysis uncovers key limitations in existing mitigation strategies that, while some methods yield improvements in specific aspects, few effectively address overall trustworthiness, and many introduce unexpected trade-offs that compromise model utility. These findings also provide practical insights for future improvements, such as the benefits of reasoning to better balance safety and performance. Based on these insights, we introduce a Reasoning-Enhanced Safety Alignment (RESA) approach that equips the model with chain-of-thought reasoning ability to discover the underlying risks, achieving state-of-the-art results.

cs.CL↗

arXiv2025

Asymmetric Diffusion Recommendation Model

Recently, motivated by the outstanding achievements of diffusion models, the diffusion process has been employed to strengthen representation learning in recommendation systems. Most diffusion-based recommendation models typically utilize standard Gaussian noise in symmetric forward and reverse processes in continuous data space. Nevertheless, the samples derived from recommendation systems inhabit a discrete data space, which is fundamentally different from the continuous one. Moreover, Gaussian noise has the potential to corrupt personalized information within latent representations. In this work, we propose a novel and effective method, named Asymmetric Diffusion Recommendation Model (AsymDiffRec), which learns forward and reverse processes in an asymmetric manner. We define a generalized forward process that simulates the missing features in real-world recommendation samples. The reverse process is then performed in an asymmetric latent feature space. To preserve personalized information within the latent representation, a task-oriented optimization strategy is introduced. In the serving stage, the raw sample with missing features is regarded as a noisy input to generate a denoising and robust representation for the final prediction. By equipping base models with AsymDiffRec, we conduct online A/B tests, achieving improvements of +0.131% and +0.166% in terms of users' active days and app usage duration respectively. Additionally, the extended offline experiments also demonstrate improvements. AsymDiffRec has been implemented in the Douyin Music App.

cs.IR↗

arXiv2025

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation

Text-to-image (T2I) models have demonstrated remarkable generative capabilities but remain vulnerable to producing not-safe-for-work (NSFW) content, such as violent or explicit imagery. While recent moderation efforts have introduced soft prompt-guided tuning by appending defensive tokens to the input, these approaches often rely on large-scale curated image-text datasets and apply static, one-size-fits-all defenses at inference time. However, this results not only in high computational cost and degraded benign image quality, but also in limited adaptability to the diverse and nuanced safety requirements of real-world prompts. To address these challenges, we propose PromptSafe, a gated prompt tuning framework that combines a lightweight, text-only supervised soft embedding with an inference-time gated control network. Instead of training on expensive image-text datasets, we first rewrite unsafe prompts into semantically aligned but safe alternatives using an LLM, constructing an efficient text-only training corpus. Based on this, we optimize a universal soft prompt that repels unsafe and attracts safe embeddings during the diffusion denoising process. To avoid over-suppressing benign prompts, we introduce a gated mechanism that adaptively adjusts the defensive strength based on estimated prompt toxicity, thereby aligning defense intensity with prompt risk and ensuring strong protection for harmful inputs while preserving benign generation quality. Extensive experiments across multiple benchmarks and T2I models show that PromptSafe achieves a SOTA unsafe generation rate (2.36%), while preserving high benign fidelity. Furthermore, PromptSafe demonstrates strong generalization to unseen harmful categories, robust transferability across diffusion model architectures, and resilience under adaptive adversarial attacks, highlighting its practical value for safe and scalable deployment.

cs.CV↗

arXiv2025

From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models

Hallucinations in large vision-language models (LVLMs) are a significant challenge, i.e., generating objects that are not presented in the visual input, which impairs their reliability. Recent studies often attribute hallucinations to a lack of understanding of visual input, yet ignore a more fundamental issue: the model's inability to effectively extract or decouple visual features. In this paper, we revisit the hallucinations in LVLMs from an architectural perspective, investigating whether the primary cause lies in the visual encoder (feature extraction) or the modal alignment module (feature decoupling). Motivated by our findings on the preliminary investigation, we propose a novel tuning strategy, PATCH, to mitigate hallucinations in LVLMs. This plug-and-play method can be integrated into various LVLMs, utilizing adaptive virtual tokens to extract object features from bounding boxes, thereby addressing hallucinations caused by insufficient decoupling of visual features. PATCH achieves state-of-the-art performance on multiple multi-modal hallucination datasets. We hope this approach provides researchers with deeper insights into the underlying causes of hallucinations in LVLMs, fostering further advancements and innovation in this field.

cs.CL↗

arXiv2025

Bioinspired Synergistic Texture and Color Modulation Enabled by Surface Instability of Cholesteric Liquid Crystal Elastomers

Certain cephalopods can dynamically camouflage by altering both skin texture and color to match their surroundings. Inspired by this capability, we present a cholesteric liquid crystal elastomer-liquid crystal elastomer (CLCE-LCE) bilayer capable of simultaneous, reversible modulation of surface texture and structural color through programmable wrinkling. By tuning the bilayer's fabrication parameters, on-demand wrinkle morphologies and color combinations are achieved. Spatially selective UV curing allows localized surface textures, while chemical patterning of the CLCE layer enables region-specific color responses, expanding the design space for multifunctional, spatially encoded optical materials. The CLCE-LCE bilayer enables dynamic thermal regulation by tuning light absorption through synergistically modulating surface morphology and color. Notably, this system achieves strain-dependent multiscale encoding via multistep selective UV curing, revealing distinct visual content under different applied strains. This work establishes a versatile platform that merges surface instabilities with tunable structural coloration, advancing intelligent materials with programmable, strain-responsive surface and optical properties.

physics.app-ph↗

arXiv2025

RankMixer: Scaling Up Ranking Models in Industrial Recommenders

Recent progress on large language models (LLMs) has spurred interest in scaling up recommendation systems, yet two practical obstacles remain. First, training and serving cost on industrial Recommenders must respect strict latency bounds and high QPS demands. Second, most human-designed feature-crossing modules in ranking models were inherited from the CPU era and fail to exploit modern GPUs, resulting in low Model Flops Utilization (MFU) and poor scalability. We introduce RankMixer, a hardware-aware model design tailored towards a unified and scalable feature-interaction architecture. RankMixer retains the transformer's high parallelism while replacing quadratic self-attention with multi-head token mixing module for higher efficiency. Besides, RankMixer maintains both the modeling for distinct feature subspaces and cross-feature-space interactions with Per-token FFNs. We further extend it to one billion parameters with a Sparse-MoE variant for higher ROI. A dynamic routing strategy is adapted to address the inadequacy and imbalance of experts training. Experiments show RankMixer's superior scaling abilities on a trillion-scale production dataset. By replacing previously diverse handcrafted low-MFU modules with RankMixer, we boost the model MFU from 4.5\% to 45\%, and scale our ranking model parameters by 100x while maintaining roughly the same inference latency. We verify RankMixer's universality with online A/B tests across two core application scenarios (Recommendation and Advertisement). Finally, we launch 1B Dense-Parameters RankMixer for full traffic serving without increasing the serving cost, which improves user active days by 0.3\% and total in-app usage duration by 1.08\%.

cs.IR↗

arXiv2025

PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning

Retrieval-augmented generation (RAG) often falls short when retrieved context includes confusing semi-relevant passages, or when answering questions require deep contextual understanding and reasoning. We propose an efficient fine-tuning framework, called PrismRAG, that (i) trains the model with distractor-aware QA pairs mixing gold evidence with subtle distractor passages, and (ii) instills reasoning-centric habits that make the LLM plan, rationalize, and synthesize without relying on extensive human engineered instructions. Evaluated across 12 open-book RAG QA benchmarks spanning diverse application domains and scenarios, PrismRAG improves average factuality by 5.4%, outperforming state-of-the-art solutions.

cs.CL↗

arXiv2025

PhysDrive: A Multimodal Remote Physiological Measurement Dataset for In-vehicle Driver Monitoring

Robust and unobtrusive in-vehicle physiological monitoring is crucial for ensuring driving safety and user experience. While remote physiological measurement (RPM) offers a promising non-invasive solution, its translation to real-world driving scenarios is critically constrained by the scarcity of comprehensive datasets. Existing resources are often limited in scale, modality diversity, the breadth of biometric annotations, and the range of captured conditions, thereby omitting inherent real-world challenges in driving. Here, we present PhysDrive, the first large-scale multimodal dataset for contactless in-vehicle physiological sensing with dedicated consideration on various modality settings and driving factors. PhysDrive collects data from 48 drivers, including synchronized RGB, near-infrared camera, and raw mmWave radar data, accompanied with six synchronized ground truths (ECG, BVP, Respiration, HR, RR, and SpO2). It covers a wide spectrum of naturalistic driving conditions, including driver motions, dynamic natural light, vehicle types, and road conditions. We extensively evaluate both signal-processing and deep-learning methods on PhysDrive, establishing a comprehensive benchmark across all modalities, and release full open-source code with compatibility for mainstream public toolboxes. We envision PhysDrive will serve as a foundational resource and accelerate research on multimodal driver monitoring and smart-cockpit systems.

cs.AI↗

arXiv2025

Reinforced Embodied Active Defense: Exploiting Adaptive Interaction for Robust Visual Perception in Adversarial 3D Environments

Adversarial attacks in 3D environments have emerged as a critical threat to the reliability of visual perception systems, particularly in safety-sensitive applications such as identity verification and autonomous driving. These attacks employ adversarial patches and 3D objects to manipulate deep neural network (DNN) predictions by exploiting vulnerabilities within complex scenes. Existing defense mechanisms, such as adversarial training and purification, primarily employ passive strategies to enhance robustness. However, these approaches often rely on pre-defined assumptions about adversarial tactics, limiting their adaptability in dynamic 3D settings. To address these challenges, we introduce Reinforced Embodied Active Defense (Rein-EAD), a proactive defense framework that leverages adaptive exploration and interaction with the environment to improve perception robustness in 3D adversarial contexts. By implementing a multi-step objective that balances immediate prediction accuracy with predictive entropy minimization, Rein-EAD optimizes defense strategies over a multi-step horizon. Additionally, Rein-EAD involves an uncertainty-oriented reward-shaping mechanism that facilitates efficient policy updates, thereby reducing computational overhead and supporting real-world applicability without the need for differentiable environments. Comprehensive experiments validate the effectiveness of Rein-EAD, demonstrating a substantial reduction in attack success rates while preserving standard accuracy across diverse tasks. Notably, Rein-EAD exhibits robust generalization to unseen and adaptive attacks, making it suitable for real-world complex tasks, including 3D object classification, face recognition and autonomous driving.

cs.CV↗

arXiv2025

Feedback-Induced Performance Decline in LLM-Based Decision-Making

The ability of Large Language Models (LLMs) to extract context from natural language problem descriptions naturally raises questions about their suitability in autonomous decision-making settings. This paper studies the behaviour of these models within a Markov Decision Process (MDPs). While traditional reinforcement learning (RL) strategies commonly employed in this setting rely on iterative exploration, LLMs, pre-trained on diverse datasets, offer the capability to leverage prior knowledge for faster adaptation. We investigate online structured prompting strategies in sequential decision making tasks, comparing the zero-shot performance of LLM-based approaches to that of classical RL methods. Our findings reveal that although LLMs demonstrate improved initial performance in simpler environments, they struggle with planning and reasoning in complex scenarios without fine-tuning or additional guidance. Our results show that feedback mechanisms, intended to improve decision-making, often introduce confusion, leading to diminished performance in intricate environments. These insights underscore the need for further exploration into hybrid strategies, fine-tuning, and advanced memory integration to enhance LLM-based decision-making capabilities.

cs.AI↗

arXiv2025

Defense-as-a-Service: Black-box Shielding against Backdoored Graph Models

With the trend of large graph learning models, business owners tend to employ a model provided by a third party to deliver business services to users. However, these models might be backdoored, and malicious users can submit trigger-embedded inputs to manipulate the model predictions. Current graph backdoor defenses have several limitations: 1) depending on model-related details, 2) requiring additional model fine-tuning, and 3) relying upon extra explainability tools, all of which are infeasible under stringent privacy policies. To address those limitations, we propose GraphProt, which allows resource-constrained business owners to rely on third parties to avoid backdoor attacks on GNN-based graph classifiers. Our GraphProt is model-agnostic and only relies on the input graph. The key insight is to leverage subgraph information for prediction, thereby mitigating backdoor effects induced by triggers. GraphProt comprises two components: clustering-based trigger elimination and robust subgraph ensemble. Specifically, we first propose feature-topology clustering that aims to remove most of the anomalous subgraphs (triggers). Moreover, we design subgraph sampling strategies based on feature-topology clustering to build a robust classifier via majority vote. Experimental results across three backdoor attacks and six benchmark datasets demonstrate that GraphProt significantly reduces the backdoor attack success rate while preserving the model accuracy on regular graph classification tasks.

cs.LG↗

arXiv2025

Cloud Computing Energy Consumption Prediction Based on Kernel Extreme Learning Machine Algorithm Improved by Vector Weighted Average Algorithm

With the rapid expansion of cloud computing infrastructure, energy consumption has become a critical challenge, driving the need for accurate and efficient prediction models. This study proposes a novel Vector Weighted Average Kernel Extreme Learning Machine (VWAA-KELM) model to enhance energy consumption prediction in cloud computing environments. By integrating a vector weighted average algorithm (VWAA) with kernel extreme learning machine (KELM), the proposed model dynamically adjusts feature weights and optimizes kernel functions, significantly improving prediction accuracy and generalization. Experimental results demonstrate the superior performance of VWAA-KELM: 94.7% of test set prediction errors fall within [0, 50] units, with only three cases exceeding 100 units, indicating strong stability. The model achieves a coefficient of determination (R2) of 0.987 in the training set (RMSE = 28.108, RPD = 8.872) and maintains excellent generalization with R2 = 0.973 in the test set (RMSE = 43.227, RPD = 6.202). Visual analysis confirms that predicted values closely align with actual energy consumption trends, avoiding overfitting while capturing nonlinear dependencies. A key innovation of this study is the introduction of adaptive feature weighting, allowing the model to dynamically assign importance to different input parameters, thereby enhancing high-dimensional data processing. This advancement provides a scalable and efficient approach for optimizing cloud data center energy consumption. Beyond cloud computing, the proposed hybrid framework has broader applications in Internet of Things (IoT) and edge computing, supporting real-time energy management and intelligent resource allocation.

cs.LG↗

arXiv2025

A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents

Recent advances in large language models (LLMs) have catalyzed the rise of autonomous AI agents capable of perceiving, reasoning, and acting in dynamic, open-ended environments. These large-model agents mark a paradigm shift from static inference systems to interactive, memory-augmented entities. While these capabilities significantly expand the functional scope of AI, they also introduce qualitatively novel security risks - such as memory poisoning, tool misuse, reward hacking, and emergent misalignment - that extend beyond the threat models of conventional systems or standalone LLMs. In this survey, we first examine the structural foundations and key capabilities that underpin increasing levels of agent autonomy, including long-term memory retention, modular tool use, recursive planning, and reflective reasoning. We then analyze the corresponding security vulnerabilities across the agent stack, identifying failure modes such as deferred decision hazards, irreversible tool chains, and deceptive behaviors arising from internal state drift or value misalignment. These risks are traced to architectural fragilities that emerge across perception, cognition, memory, and action modules. To address these challenges, we systematically review recent defense strategies deployed at different autonomy layers, including input sanitization, memory lifecycle control, constrained decision-making, structured tool invocation, and introspective reflection. We introduce the Reflective Risk-Aware Agent Architecture (R2A2), a unified cognitive framework grounded in Constrained Markov Decision Processes (CMDPs), which incorporates risk-aware world modeling, meta-policy adaptation, and joint reward-risk optimization to enable principled, proactive safety across the agent's decision-making loop.

cs.AI↗

arXiv2025

STAIR: Improving Safety Alignment with Introspective Reasoning

Ensuring the safety and harmlessness of Large Language Models (LLMs) has become equally critical as their performance in applications. However, existing safety alignment methods typically suffer from safety-performance trade-offs and the susceptibility to jailbreak attacks, primarily due to their reliance on direct refusals for malicious queries. In this paper, we propose STAIR, a novel framework that integrates SafeTy Alignment with Itrospective Reasoning. We enable LLMs to identify safety risks through step-by-step analysis by self-improving chain-of-thought (CoT) reasoning with safety awareness. STAIR first equips the model with a structured reasoning capability and then advances safety alignment via iterative preference optimization on step-level reasoning data generated using our newly proposed Safety-Informed Monte Carlo Tree Search (SI-MCTS). We further train a process reward model on this data to guide test-time searches for improved responses. Extensive experiments show that STAIR effectively mitigates harmful outputs while better preserving helpfulness, compared to instinctive alignment strategies. With test-time scaling, STAIR achieves a safety performance comparable to Claude-3.5 against popular jailbreak attacks. Relevant resources in this work are available at https://github.com/thu-ml/STAIR.

cs.CL↗