Collaborative human-object interaction shows dynamic and complex movements that require mutual anticipation and continuous adjustment between participants and the shared object. Understanding and modeling such collaborative multi-human object interaction (MHOI) scenarios requires high-quality data acquisition as a foundational step, however, this is a challenging task due to the inherent complexity of MHOI scenarios where human-human and human-object interactions occur simultaneously. Such complexity leads to noisy MHOI captures characterized by several artifacts: contact misalignment between hands and objects, motion jitter and temporal inconsistencies in the captured sequences, and missing or incomplete finger-level articulation details. To address these challenges, we present MOCHI (MOtion Enhancement of Collaborative Human-object Interactions), a two-stage framework for enhancing noisy MHOI data. Our approach first generates physically plausible hand grasps through optimization from noisy body input, producing grasps that are both physically plausible and semantically consistent with the body pose, where these optimized grasps are extended into complete hand-object interaction sequences. Consequently, the full-body motion for all participants are refined through a diffusion-based noise optimization framework that uses single-person motion priors. During the optimization process, we introduce optimization objectives to encode human-object and human-human interaction information within these single-person priors. Experimental results demonstrate the effectiveness of our pipeline across diverse MHOI data, either acquired by existing capture methods or synthesized by generative models. We further show robustness of our system across varying numbers of participants and types of interactions, and demonstrate various applications including keyframe-based MHOI creation and data augmentation through varying object geometries.
论文检索
输入标题、作者或关键词，从 3,655 篇学术成果中精准定位
JGS2 is a Jacobi-like GPU simulation algorithm. It avoids the overshooting issue by augmenting each subproblem with a perturbation subspace that predicts the global influence of the local solve. The efficiency of JGS2 is due to Cubature-based subspace integration at each subproblem. Being a data-driven method, Cubature requires a set of representative deformed poses that cover deformations likely to occur in the simulation. This requirement is unlikely for high-resolution deformation with rich local details. Therefore, simulation performance and convergence degenerate when Cubature extrapolates. This paper proposes a training-free subspace integration algorithm based on classic Gaussian quadrature (GQ). We leverage the fact that the subproblem's subspace bases can be well-approximated by a low-degree multivariable polynomial, which suggests GQ an excellent candidate for Cubature substitute. To this end, we introduce a novel algorithm that adaptively generates the integration region for each subproblem. As a result, GQ integration can be analytically retrieved without cumbersome data generation and training. We also show how to handle frictional contact by modifying the pre-computed perturbation subspace. The resulting JGS2-GQ framework is more versatile than the vanilla JGS2 method. It is more stable for large and novel deformations, and is free of data generation and expensive training, while maintaining a near second-order convergence that is comparable to Newton. Performance-wise, JGS2-GQ is as efficient as JGS2, which is three orders faster than classic CPU methods and up to two orders faster than classic GPU algorithms. When novel deformation occurs, JGS2-GQ outperforms JGS2 over 50%.
Being able to relight human performance is a fundamental task for post production and content creation. We present BodyReLux, a subject-specific video diffusion-based framework for relighting full-body human performances in a temporally consistent way. Our model is trained on a hybrid dataset of pixel-aligned video relighting pairs, covering a diverse combination of lighting conditions, performances and viewpoints. To acquire such dataset, we combine traditional static One-Light-at-a-Time (OLAT) capture and a novel dynamic performance capture in which two smoothly varying lighting sequences are rapidly interleaved. Because the lighting operates above the human flicker-fusion threshold, the interleaving does not appears to strobe. We train our video relighting model from a pretrained text-to-video model to fully leverage the generative priors for producing high quality videos. To achieve accurate lighting control, we introduce a new lighting conditioning method that represents each light source as a token. We further condition on sequences of lighting using masked attention to support dynamic lighting control. Together with a carefully designed data augmentation pipeline, we achieve photorealistic, robust, and temporally consistent video relighting of subject-specific human performances.
College of Computing and Data Science, Nanyang Technological University, Singapore Multi-layer perceptrons (MLPs) are a standard tool for learning and function approximation, but they inherently produce globally smooth outputs. Consequently, they struggle to represent functions that are continuous yet intentionally non-differentiable (i.e., functions with prescribed C0 sharp features) without ad hoc post-processing. We present SharpNet, a modified MLP architecture that encodes user-specified sharp features by augmenting the network with an auxiliary feature function defined as the solution to Poisson's equation with jump Neumann boundary conditions. This feature function is evaluated via an efficient local integral and is fully differentiable with respect to the feature locations, allowing us to jointly optimize both the feature locations and the MLP parameters to recover the target function or geometry. This construction provides precise control over where non-differentiability occurs, enforcing the desired C0 behavior at feature locations while preserving smoothness elsewhere. We validate SharpNet on 2D problems and 3D CAD reconstruction, and compare it with several state-of-the-art baselines. In both settings, SharpNet accurately recovers sharp edges and corners while remaining smooth away from them, whereas existing methods tend to blur gradient discontinuities. Qualitative and quantitative results demonstrate the effectiveness of our approach. Our project page, code and models are publicly available at https://sharpnettech.github.io.
We propose a new framework to systematically incorporate data uncertainty in Gaussian Splatting. Being the new paradigm of neural rendering, Gaussian Splatting has been investigated in many applications, with the main effort in extending its representation, improving its optimization process, and accelerating its speed. However, one orthogonal, much needed, but under-explored area is data uncertainty. In standard 4D Gaussian Splatting, data uncertainty can manifest as view sparsity, missing frames, camera asynchronization, etc. So far, there has been little research to holistically incorporating various types of data uncertainty under a single framework. To this end, we propose Graphical X Splatting, or GraphiXS, a new probabilistic framework that considers multiple types of data uncertainty, aiming for a fundamental augmentation of the current 4D Gaussian Splatting paradigm into a probabilistic setting. GraphiXS is general and can be instantiated with a range of primitives, e.g. Gaussians, Student’s-t. Furthermore, GraphiXS can be used to ‘upgrade’ existing methods to accommodate data uncertainty. Through exhaustive evaluation and comparison, we demonstrate that GraphiXS can systematically model various uncertainties in data, outperform existing methods in many settings where data are missing or polluted in space and time, and therefore is a major generalization of the current 4D Gaussian Splatting research.
Recovering high-quality video from sparse event streams is a challenging task. Regression methods often blur textures, while existing generative models struggle with long-term stability. We propose LongE2V, a novel approach that leverages pre-trained video diffusion priors to jointly handle event-based video reconstruction, prediction, and frame interpolation. By fine-tuning a foundational video model, our approach achieves high data efficiency and superior perceptual quality. We introduce Autoregressive Unrolling and Adaptive Context Switching to mitigate temporal drift in extremely long sequences. We also propose Reencoding Alignment with Cross Residual Correction to ensure precise bidirectional consistency during frame interpolation. Furthermore, Event Voxel Density Augmentation ensures robustness across varying sensor resolutions. Extensive experiments on real-world benchmarks demonstrate that LongE2V outperforms state-of-the-art methods across all three tasks, exhibiting exceptional temporal coherence and zero-shot generalization.
Generative models for material creation are fundamentally limited by the quality and expressivity of available training data. Simple physically based rendering (PBR) materials, which combine a diffuse term with a single-lobe specular component, are commonly used for training but are insufficient to capture many important visual effects present in real materials. We present a method that enhances such simple PBR materials to more expressive ones, by augmenting the single GGX specular lobe into a layered model that captures a broader range of non-diffuse effects. Starting from a simple material, we procedurally construct a corresponding multi-lobe non-diffuse component guided by physical priors, enabling effects such as dust, clearcoat, and layered scattering. To provide a compact representation for downstream applications, we encode this non-diffuse component as a neural material with a shared 6D latent space, where each material instance is represented by two latent textures and decoded by a pretrained universal MLP. We further regularize the latent space to support material generation. The resulting neural material dataset enables training generative models for richer material creation. To demonstrate this application, we finetune a video diffusion model to produce neural latent textures that encode our multi-lobe material, and present generative results as proof of feasibility. Our procedural data enhancement approach is an important step toward improving expressivity in material generation.
Trying different fabrics on existing garments is a widely applicable problem in digital fashion and computer graphics. A comprehensive transformation involves both material reflectance and geometric deformation from fabric drape. In this work, we focus on the visual aspects of this challenge and simplify fabric try-on to a re-texturing task that replaces garment materials while preserving the original geometry and illumination. Prior approaches perform garment re-texturing via 3D or UV-space reconstruction and rendering, making them sensitive to reconstruction accuracy and rendering fidelity. Recent diffusion-based material transfer methods either lack fine-grained geometric and material control or suffer from domain gaps due to training on synthetic rendered data. We propose a fabric try-on framework that leverages the generative priors of modern image editing models. Motivated by the in-context generation capability of Multimodal Diffusion Transformers, we reformulate garment re-texturing as a two-stage process consisting of fabric removal and fabric application via an intermediate material-normalized image. We further introduce a real-image data curation pipeline and a context-aware tile augmentation strategy, enabling coherent and photorealistic fabric try-on from a single image. Extensive experiments show that our method achieves high-quality, controllable fabric transfer while preserving garment geometry and illumination, without requiring costly reconstruction or rendering pipelines. Our project is available at: https://style3d.github.io/fabric_tryon.
WED-Net: A Weather-Effect Disentanglement Network with Causal Augmentation for Urban Flow Prediction
Urban spatio-temporal prediction under extreme conditions (e.g., heavy rain) is challenging due to event rarity and dynamics. Existing data-driven approaches that incorporate weather as auxiliary input often rely on coarse-grained descriptors and lack dedicated mechanisms to capture fine-grained spatio-temporal effects. Although recent methods adopt causal techniques to improve out-of-distribution generalization, they typically overlook temporal dynamics or depend on fixed confounder stratification. To address these limitations, we propose WED-Net (Weather-Effect Disentanglement Network), a dual-branch Transformer architecture that separates intrinsic and weather-induced traffic patterns via self- and cross-attention, enhanced with memory banks and fused through adaptive gating. To further promote disentanglement, we introduce a discriminator that explicitly distinguishes weather conditions. Additionally, we design a causal data augmentation strategy that perturbs non-causal parts while preserving causal structures, enabling improved generalization under rare scenarios. Experiments on taxi-flow datasets from three cities demonstrate that WED-Net delivers robust performance under extreme weather conditions, highlighting its potential to support safer mobility, disaster preparedness, and urban resilience in real-world settings. The code is publicly available at https://github.com/HQ-LV/WED-Net.
Text classification is vital for Web for Good applications like hate speech and misinformation detection. However, traditional models (e.g., BERT) often fail in dynamic few-shot settings where labeled data are scarce, and target labels frequently evolve. While Large Language Models (LLMs) show promise in few-shot settings, their performance is often hindered by increased input size in dynamic evolving scenarios. To address these issues, we propose GORAG, a Graph-based Online Retrieval-Augmented Generation framework for dynamic few-shot text classification. GORAG constructs and maintains a weighted graph of keywords and text labels, representing their correlations as edges. To model these correlations, GORAG employs an edge weighting mechanism to prioritize the importance and reliability of extracted information and dynamically retrieves relevant context using a tailored minimum-cost spanning tree for each input. Empirical evaluations show GORAG outperforms existing approaches by providing more comprehensive and precise contextual information. Our code is released at: https://github.com/Wyb0627/GORAG.
Mental manipulation on social media poses a covert yet serious threat to individuals' psychological well-being and the integrity of online interactions. Detecting such behavior is challenging due to the difficult-to-annotate training data, its highly covert and multi-turn nature, and the lack of real-world datasets. To address these challenges, we propose MentalMAD, a framework that enhances large language models for mental manipulation detection. Our approach consists of three key components: EvoSA, an annotation-free data augmentation method that combines evolutionary operations with speech-act-aware prompting; teacher-model-generated complementary-task supervision; and Complementary-Convergent Distillation, a phase-wise strategy for transferring manipulation-specific knowledge to student models. We then constructed the ReaMent dataset, comprising 5,000 real-world-sourced dialogues. Extensive experiments show that MentalMAD improves accuracy by 14.0%, macro-F1 by 27.3%, and weighted F1 by 15.1% over the strongest baseline. The code and the dataset are publicly available at https://github.com/Yuansheng-Gao/MentalMAD.
Graph anomaly detection (GAD), which aims to identify abnormal nodes that deviate from the majority, has become increasingly important in high-stakes Web domains. However, existing GAD methods follow a ''one model per dataset'' paradigm, leading to high computational costs, substantial data demands, and poor generalization when transferred to new datasets. This calls for a foundation model that enables a ''one-for-all'' GAD solution capable of detecting anomalies across diverse graphs without retraining. Yet, achieving this is challenging due to the large structural and feature heterogeneity across domains. In this paper, we propose TFM4GAD, a simple yet effective framework that adapts tabular foundation models (TFMs) for graph anomaly detection. Our key insight is that the core challenges of foundation GAD, handling heterogeneous features, generalizing across domains, and operating with scarce labels, are the exact problems that modern TFMs are designed to solve via synthetic pre-training and powerful in-context learning. The primary challenge thus becomes structural: TFMs are agnostic to graph topology. TFM4GAD bridges this gap by ''flattening'' the graph, constructing an augmented feature table that enriches raw node features with Laplacian embeddings, local and global structural characteristics, and anomaly-sensitive neighborhood aggregations. This augmented table is processed by a TFM in a fully in-context regime. Extensive experiments on multiple datasets with various TFM backbones reveal that TFM4GAD surprisingly achieves significant performance gains over specialized GAD models trained from scratch. Our work offers a new perspective and a practical paradigm for leveraging TFMs as powerful, generalist graph anomaly detectors.
Retrieval-Augmented Generation (RAG) systems are increasingly deployed in web-based educational environments, yet transparency can be seen as a primarily ethical, and, too often, optional, concern, rather than foundational. This paper presents design patterns for building transparent RAG systems, derived from developing and deploying SAGE-RAI, an advanced multi-purpose RAG system, in an educational context. Through systematic evaluation combining quantitative rating data (n=26, mean rating=4.62/5) and qualitative interviews (n=4), we demonstrate that transparency serves dual pedagogical and ethical functions. Our empirical findings reveal high user satisfaction (92.3% rating 4-5 stars) while identifying critical tensions between AI assistance and learning independence. Our findings suggest that as RAG systems increasingly mediate access to web-based knowledge, transparency must evolve from an optional feature to an architectural requirement.
Retrieval-augmented generation (RAG) systems increasingly ground responses in user-generated Web content, expanding both usefulness and attack surface. Two web-native threats are especially concerning: indirect prompt injection and retrieval poisoning, where malicious instructions or biased content survive ingestion and influence retrieval or generation. We introduce OpenRAG-Soc, a compact, reproducible benchmark and harness for evaluating web-facing RAG pipelines under these threats as a discrete data package. The suite pairs a social corpus with interchangeable sparse and dense retrievers and deployable mitigations, including HTML/Markdown sanitization, Unicode normalization, and attribution-gated answering. OpenRAG-Soc standardizes end-to-end evaluation from ingestion to generation and reports attack success at answer time, rank shifts in both sparse and dense retrievers, as well as utility and latency. It targets practitioners who need fast, realistic tests to measure risk and harden RAG deployments.
In modern e-commerce search systems, dense retrieval has become an indispensable component. By computing similarities between query and item (product) embeddings, it efficiently selects candidate products from large-scale repositories. With the breakthroughs in large language models (LLMs), mainstream embedding models have gradually shifted from BERT to LLMs for more accurate text modeling. However, these models still adopt direct-embedding methods, and the semantic accuracy of embeddings remains inadequate. Therefore, contrastive learning is heavily employed to achieve tight semantic alignment between positive pairs. Consequently, such models tend to capture statistical co-occurrence patterns in the training data, biasing them toward shallow lexical and semantic matches. For difficult queries exhibiting notable lexical disparity from target items, the performance degrades significantly. In this work, we propose the Large Reasoning Embedding Model (LREM), which novelly integrates reasoning processes into representation learning. For difficult queries, LREM first conducts reasoning to achieve a deep understanding of the original query, and then produces a reasoning-augmented query embedding for retrieval. This reasoning process effectively bridges the semantic gap between original queries and target items, significantly improving retrieval accuracy. Specifically, we adopt a two-stage training process: the first stage optimizes the LLM on carefully curated Query-CoT-Item triplets with SFT and InfoNCE losses to establish preliminary reasoning and embedding capabilities, and the second stage further refines the reasoning trajectories via reinforcement learning (RL). Extensive offline and online experiments validate the effectiveness of LREM, leading to its deployment on China's largest e-commerce platform since August 2025.
Online financial systems for stock prediction, portfolio optimization, and algorithmic trading must remain robust against rare and volatile market events, but historical data often fails to capture diverse unprecedented financial risks, creating a major bottleneck for systematic stress testing. To address this, we propose Financial Wind Tunnel (FWT), a deployable, retrieval-augmented market simulator that generates realistic, controllable, and adaptable financial dynamics for industrial-scale training and testing. FWT integrates both macro- and micro-level market patterns through a retrieval mechanism that conditions diffusion on relevant trends, supporting real-time and interpretable generation. Unlike existing methods that lack transferability across markets and scales, FWT supports large-scale cross-market pattern synthesis and what-if causal generation, enabling generalizable simulation beyond local historical regimes. We further introduce a simulation-driven optimizer for downstream models, enabling continuous improvement of online quantitative strategies. Deployed in production pipelines on CSI300 and HKSE components, FWT demonstrates measurable gains in stock prediction and portfolio optimization performance while maintaining scalability and operational reliability, offering a practical system for quantitative finance and stress testing.
Large language models (LLMs) have been incorporated into numerous industrial applications. Meanwhile, a vast array of API assets is scattered across various functions in the financial domain. An online financial question-answering system can leverage both LLMs and private APIs to provide timely financial analysis and information. The key is equipping the LLM model with function calling capability tailored to a financial scenario. However, a generic LLM requires customized financial APIs to call and struggles to adapt to the financial domain. Additionally, online user queries are diverse and contain out-of-distribution parameters compared with the required function input parameters, which makes it more difficult for a generic LLM to serve online users. In this paper, we propose a data-driven pipeline to enhance function calling in LLM for our online, deployed financial QA, comprising dataset construction, data augmentation, and model training. Specifically, we construct a dataset based on a previous study and update it periodically, incorporating queries and an augmentation method named AugFC. The addition of user query-related samples will exploit our financial toolset in a data-driven manner, and AugFC explores the possible parameter values to enhance the diversity of our updated dataset. Then, we train an LLM with a two-step method, which enables the use of our financial functions. Extensive experiments on existing offline datasets, as well as the deployment of an online scenario, illustrate the superiority of our pipeline. The related pipeline has been adopted in the financial QA of YuanBao. https://yuanbao.tencent.com/chat/, one of the largest chat platforms in China.
Retrieval-Augmented Generation (RAG) is becoming increasingly essential for Question Answering (QA) in the financial sector, where accurate and contextually grounded insights from complex public disclosures are crucial. However, existing financial RAG systems face two significant challenges: (1) they struggle to process heterogeneous data formats, such as text, tables, and figures; and (2) they encounter difficulties in balancing general-domain applicability with company-specific adaptation. To overcome these challenges, we present VeritasFi, an innovative hybrid RAG framework that incorporates a multi-modal preprocessing pipeline alongside a cutting-edge two-stage training strategy for its re-ranking component. VeritasFi enhances financial QA through three key innovations: (1) A multi-modal preprocessing pipeline that seamlessly transforms heterogeneous data into a coherent, machine-readable format. (2) A tripartite hybrid retrieval engine that operates in parallel, combining deep multi-path retrieval over a semantically indexed document corpus, real-time data acquisition through tool utilization, and an expert-curated memory bank for high-frequency questions, ensuring comprehensive scope, accuracy, and efficiency. (3) A two-stage training strategy for the document re-ranker, which initially constructs a general, domain-specific model using anonymized data, followed by rapid fine-tuning on company-specific data for targeted applications. By integrating our proposed designs, VeritasFi presents a novel framework that greatly enhances the adaptability and robustness of financial RAG systems, providing a scalable solution for both general-domain and company-specific QA tasks. Code accompanying this work is available at https://github.com/simplew4y/VeritasFi.git.
Zero-shot stance detection (ZSSD) aims to classify stances towards previously unseen targets without direct supervision on those topics during training. While recent approaches have explored various strategies, they often suffer from limited linguistic diversity or unstable semantic representations, restricting generalization to new domains. To address these challenges, we propose DPSD , a dynamic framework that integrates LLM-assisted data augmentation, multi-granularity feature fusion with contrastive learning, and adaptive prototype updating. Our method enriches the training data with both diverse targets and stylistically varied texts. A gate-controlled fusion mechanism combines deep contextualized features from BERT with shallow lexical patterns via TF-IDF, while contrastive learning refines the feature space by pulling similar instances closer and pushing dissimilar ones apart, thereby improving representation discriminability. Furthermore, we introduce a sliding-window prototype pool that dynamically maintains class-specific prototypes while preserving historical knowledge, ensuring stable and interpretable inference over time. We also incorporate LLM-calibrated semantic similarity as an auxiliary scorer for controlled reasoning. Experimental results on three benchmark datasets -SEM16, P-Stance, and VAST - show that DPSD achieves strong performance in various zero-shot settings, especially in cross-dataset and unseen target scenarios.
Cross-domain recommendation (CDR) offers an effective strategy for improving recommendation quality in a target domain by leveraging auxiliary signals from source domains. Nonetheless, emerging evidence shows that CDR can inadvertently heighten group-level unfairness. In this work, we conduct a comprehensive theoretical and empirical analysis to uncover why these fairness issues arise. Specifically, we identify two key challenges: (i) Cross-Domain Disparity Transfer, wherein existing group-level disparities in the source domain are systematically propagated to the target domain; and (ii) Unfairness from Cross-Domain Information Gain, where the benefits derived from cross-domain knowledge are unevenly allocated among distinct groups. To address these two challenges, we propose a Cross-Domain Fairness Augmentation (CDFA) framework composed of two key components. Firstly, it mitigates cross-domain disparity transfer by adaptively integrating unlabeled data to equilibrate the informativeness of training signals across groups. Secondly, it redistributes cross-domain information gains via an information-theoretic approach to ensure equitable benefit allocation across groups. Extensive experiments on multiple datasets and baselines demonstrate that our framework significantly reduces unfairness in CDR without sacrificing overall recommendation performance, while even enhancing it. Our source code is publicly available at https://github.com/weixinchen98/CDFA.