arXiv subjects

Rui Zhao

Publications and source records attributed to Rui Zhao.

At least 73 records · Page 4Linked to original sources

arXiv2026

RoamScene3D: Immersive Text-to-3D Scene Generation via Adaptive Object-aware Roaming

Generating immersive 3D scenes from texts is a core task in computer vision, crucial for applications in virtual reality and game development. Despite the promise of leveraging 2D diffusion priors, existing methods suffer from spatial blindness and rely on predefined trajectories that fail to exploit the inner relationships among salient objects. Consequently, these approaches are unable to comprehend the semantic layout, preventing them from exploring the scene adaptively to infer occluded content. Moreover, current inpainting models operate in 2D image space, struggling to plausibly fill holes caused by camera motion. To address these limitations, we propose RoamScene3D, a novel framework that bridges the gap between semantic guidance and spatial generation. Our method reasons about the semantic relations among objects and produces consistent and photorealistic scenes. Specifically, we employ a vision-language model (VLM) to construct a scene graph that encodes object relations, guiding the camera to perceive salient object boundaries and plan an adaptive roaming trajectory. Furthermore, to mitigate the limitations of static 2D priors, we introduce a Motion-Injected Inpainting model that is fine-tuned on a synthetic panoramic dataset integrating authentic camera trajectories, making it adaptive to camera motion. Extensive experiments demonstrate that with semantic reasoning and geometric constraints, our method significantly outperforms state-of-the-art approaches in producing consistent and photorealistic scenes. Our code is available at https://github.com/JS-CHU/RoamScene3D.

cs.CV↗

arXiv2026

Performance-guided Reinforced Active Learning for Object Detection

Active learning (AL) strategies aim to train high-performance models with minimal labeling efforts, only selecting the most informative instances for annotation. Current approaches to evaluating data informativeness predominantly focus on the data's distribution or intrinsic information content and do not directly correlate with downstream task performance, such as mean average precision (mAP) in object detection. Thus, we propose Performance-guided (i.e. mAP-guided) Reinforced Active Learning for Object Detection (MGRAL), a novel approach that leverages the concept of expected model output changes as informativeness. To address the combinatorial explosion challenge of batch sample selection and the non-differentiable correlation between model performance and selected batches, MGRAL skillfully employs a reinforcement learning-based sampling agent that optimizes selection using policy gradient with mAP improvement as reward. Moreover, to reduce the computational overhead of mAP estimation with unlabeled samples, MGRAL utilizes an unsupervised way with fast look-up tables, ensuring feasible deployment. We evaluate MGRAL's active learning performance on detection tasks over PASCAL VOC and COCO benchmarks. Our approach demonstrates the highest AL curve with convincing visualizations, establishing a new paradigm in reinforcement learning-driven active object detection.

cs.CV↗

arXiv2026

"They've Stolen My GPL-Licensed Model!": Toward Standardized and Transparent Model Licensing

As model parameter sizes scale into the billions and training consumes zettaFLOPs of computation, the reuse of Machine Learning (ML) assets and collaborative development have become increasingly prevalent in the ML community. These ML assets, including models, datasets, and software, may originate from various sources and be published under different licenses, which govern the use and distribution of licensed works and their derivatives. However, commonly chosen licenses, such as GPL and Apache, are software-specific and are not clearly defined or bounded in the context of model publishing. Meanwhile, the reused assets may also be under free-content licenses and model licenses, which pose a potential risk of license noncompliance and rights infringement within the model production workflow. In this paper, we address these challenges along two lines: 1) For ML workflow compliance, we propose ModelGo (MG) Analyzer, a tool that incorporates a vocabulary for ML workflow management and encoded license rules, enabling ontological reasoning to analyze rights granting and compliance issues. 2) For standardized model publishing, we introduce ModelGo Licenses, a set of modell-specific licenses that provide flexible options to meet the diverse needs of the ML community. MG Analyzer is built on Turtle language and Notation3 reasoning engine, envisioned as a first step toward Linked Open Data for ML workflow management. We have also encoded our proposed model licenses into rules and demonstrated the effects of GPL and other commonly used licenses in model publishing, along with the flexibility advantages of our licenses, through comparisons and experiments.

cs.CY↗

arXiv2025

TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage

With recent advancements in natural language processing, Large Language Models (LLMs) have emerged as powerful tools for various real-world applications. Despite their prowess, the intrinsic generative abilities of LLMs may prove insufficient for handling complex tasks which necessitate a combination of task planning and the usage of external tools. In this paper, we first propose a structured framework tailored for LLM-based AI Agents and discuss the crucial capabilities necessary for tackling intricate problems. Within this framework, we design two distinct types of agents (i.e., one-step agent and sequential agent) to execute the inference process. Subsequently, we instantiate the framework using various LLMs and evaluate their Task Planning and Tool Usage (TPTU) abilities on typical tasks. By highlighting key findings and challenges, our goal is to provide a helpful resource for researchers and practitioners to leverage the power of LLMs in their AI applications. Our study emphasizes the substantial potential of these models, while also identifying areas that need more investigation and improvement.

cs.AI↗

arXiv2025

MatDecompSDF: High-Fidelity 3D Shape and PBR Material Decomposition from Multi-View Images

We present MatDecompSDF, a novel framework for recovering high-fidelity 3D shapes and decomposing their physically-based material properties from multi-view images. The core challenge of inverse rendering lies in the ill-posed disentanglement of geometry, materials, and illumination from 2D observations. Our method addresses this by jointly optimizing three neural components: a neural Signed Distance Function (SDF) to represent complex geometry, a spatially-varying neural field for predicting PBR material parameters (albedo, roughness, metallic), and an MLP-based model for capturing unknown environmental lighting. The key to our approach is a physically-based differentiable rendering layer that connects these 3D properties to the input images, allowing for end-to-end optimization. We introduce a set of carefully designed physical priors and geometric regularizations, including a material smoothness loss and an Eikonal loss, to effectively constrain the problem and achieve robust decomposition. Extensive experiments on both synthetic and real-world datasets (e.g., DTU) demonstrate that MatDecompSDF surpasses state-of-the-art methods in geometric accuracy, material fidelity, and novel view synthesis. Crucially, our method produces editable and relightable assets that can be seamlessly integrated into standard graphics pipelines, validating its practical utility for digital content creation.

cs.CV↗

arXiv2025

Scalable and Privacy-Preserving Synthetic Data Generation on Decentralised Web

Data on the Web has fueled much of the recent progress in AI. As more high-quality data becomes difficult to access, synthetic data is emerging as a promising solution for privacy-friendly data release and complementing real datasets in developing robust and safe AI. But there is limited work on decentralised, scalable and contributor-centric synthetic data generation systems. A recent proposal, called Libertas, allows data contributors to autonomously participate in joint computations over their Web data without relying on a trusted centre. Libertas uses Solid (Social Linked Data) and MPC (Secure Multi-Party Computation) to achieve this goal. Solid is a decentralised Web specification that lets anyone store their data securely in their personal decentralised data stores called Pods and control which applications have access to their data. MPC refers to the set of cryptographic methods for different parties to jointly compute a function over their inputs while keeping those inputs private. Thus, Libertas can also be used to generate synthetic data from otherwise inaccessible Web data in a responsible way, by ensuring contributor autonomy, decentralisation and privacy. However, the scalability of this system remains limited due to the high computation and communication costs in MPC. In this paper, we show how one can improve Libertas using secure enclaves (in addition to MPC) to address the scalability challenge. Secure enclaves such as Intel SGX rely on hardware based features for confidentiality and integrity of code and data. We discuss a principled approach for integrating SGX within the Libertas architecture for scalable differentially private synthetic data generation, and support our analysis with rigorous empirical results on simulated and real datasets and different synthetic data generation algorithms.

cs.CR↗

arXiv2025

What Happens Next? Next Scene Prediction with a Unified Video Model

Recent unified models for joint understanding and generation have significantly advanced visual generation capabilities. However, their focus on conventional tasks like text-to-video generation has left the temporal reasoning potential of unified models largely underexplored. To address this gap, we introduce Next Scene Prediction (NSP), a new task that pushes unified video models toward temporal and causal reasoning. Unlike text-to-video generation, NSP requires predicting plausible futures from preceding context, demanding deeper understanding and reasoning. To tackle this task, we propose a unified framework combining Qwen-VL for comprehension and LTX for synthesis, bridged by a latent query embedding and a connector module. This model is trained in three stages on our newly curated, large-scale NSP dataset: text-to-video pre-training, supervised fine-tuning, and reinforcement learning (via GRPO) with our proposed causal consistency reward. Experiments demonstrate our model achieves state-of-the-art performance on our benchmark, advancing the capability of generalist multimodal systems to anticipate what happens next.

cs.CV↗

arXiv2025

Glance: Accelerating Diffusion Models with 1 Sample

Diffusion models have achieved remarkable success in image generation, yet their deployment remains constrained by the heavy computational cost and the need for numerous inference steps. Previous efforts on fewer-step distillation attempt to skip redundant steps by training compact student models, yet they often suffer from heavy retraining costs and degraded generalization. In this work, we take a different perspective: we accelerate smartly, not evenly, applying smaller speedups to early semantic stages and larger ones to later redundant phases. We instantiate this phase-aware strategy with two experts that specialize in slow and fast denoising phases. Surprisingly, instead of investing massive effort in retraining student models, we find that simply equipping the base model with lightweight LoRA adapters achieves both efficient acceleration and strong generalization. We refer to these two adapters as Slow-LoRA and Fast-LoRA. Through extensive experiments, our method achieves up to 5 acceleration over the base model while maintaining comparable visual quality across diverse benchmarks. Remarkably, the LoRA experts are trained with only 1 samples on a single V100 within one hour, yet the resulting models generalize strongly on unseen prompts.

cs.CV↗

arXiv2025

Language-Instructed Reasoning for Group Activity Detection via Multimodal Large Language Model

Group activity detection (GAD) aims to simultaneously identify group members and categorize their collective activities within video sequences. Existing deep learning-based methods develop specialized architectures (e.g., transformer networks) to model the dynamics of individual roles and semantic dependencies between individuals and groups. However, they rely solely on implicit pattern recognition from visual features and struggle with contextual reasoning and explainability. In this work, we propose LIR-GAD, a novel framework of language-instructed reasoning for GAD via Multimodal Large Language Model (MLLM). Our approach expand the original vocabulary of MLLM by introducing an activity-level token and multiple cluster-specific tokens. We process video frames alongside two specially designed tokens and language instructions, which are then integrated into the MLLM. The pretrained commonsense knowledge embedded in the MLLM enables the token and tokens to effectively capture the semantic information of collective activities and learn distinct representational features of different groups, respectively. Also, we introduce a multi-label classification loss to further enhance the token's ability to learn discriminative semantic representations. Then, we design a Multimodal Dual-Alignment Fusion (MDAF) module that integrates MLLM's hidden embeddings corresponding to the designed tokens with visual features, significantly enhancing the performance of GAD. Both quantitative and qualitative experiments demonstrate the superior performance of our proposed method in GAD taks.

cs.CV↗

arXiv2025

Observation of Custodial Chiral Symmetry in Memristive Topological Insulators

The concept of custodial symmetry, a residual symmetry that protects physical observables from large quantum corrections, has been a cornerstone of high-energy physics, but its experimental observation has remained unexplored. Building on recent theoretical work [Phys. Rev. Lett. 128, 097701 (2022)], we report the first experimental observation of classical analog of custodial chiral symmetry in a memristive Su-Schrieffer-Heeger (SSH) circuit. We provide direct experimental evidence for custodial symmetry through the measurement of the correction to the Lagrangian. This Lagrangian correction, which mimics a mass term in field theory, vanishes smoothly as the perturbation is reduced. We also demonstrate that topological edge states in the memristive SSH circuit remain localized at the boundary, protected by custodial chiral symmetry. This work opens new avenues for emulating field-theoretic symmetries and nonlinear dynamics in memristive platforms.

cond-mat.mes-hall↗

arXiv2025

A Spectral Localization Method for Time-Fractional Integro-Differential Equations with Nonsmooth Data

In this work, we develop a localized numerical scheme with low regularity requirements for solving time-fractional integro-differential equations. First, a fully discrete numerical scheme is constructed. Specifically, for temporal discretization, we employ the contour integral method (CIM) with parameterized hyperbolic contours to approximate the nonlocal operators. For spatial discretization, the standard piecewise linear Galerkin finite element method (FEM) is used. We then provide a rigorous error analysis, demonstrating that the proposed scheme achieves high accuracy even for problems with nonsmooth/vanishing initial values or low-regularity solutions, featuring spectral accuracy in time and second-order convergence in space. Finally, a series of numerical experiments in both 1-D and 2-D validate the theoretical findings and confirm that the algorithm combines the advantages of spectral accuracy, low computational cost, and efficient memory usage.

math.NA↗

arXiv2025

CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model

Autonomous driving represents a prominent application of artificial intelligence. Recent approaches have shifted from focusing solely on common scenarios to addressing complex, long-tail situations such as subtle human behaviors, traffic accidents, and non-compliant driving patterns. Given the demonstrated capabilities of large language models (LLMs) in understanding visual and natural language inputs and following instructions, recent methods have integrated LLMs into autonomous driving systems to enhance reasoning, interpretability, and performance across diverse scenarios. However, existing methods typically rely either on real-world data, which is suitable for industrial deployment, or on simulation data tailored to rare or hard case scenarios. Few approaches effectively integrate the complementary advantages of both data sources. To address this limitation, we propose a novel VLM-guided, end-to-end adversarial transfer framework for autonomous driving that transfers long-tail handling capabilities from simulation to real-world deployment, named CoC-VLA. The framework comprises a teacher VLM model, a student VLM model, and a discriminator. Both the teacher and student VLM models utilize a shared base architecture, termed the Chain-of-Causality Visual-Language Model (CoC VLM), which integrates temporal information via an end-to-end text adapter. This architecture supports chain-of-thought reasoning to infer complex driving logic. The teacher and student VLM models are pre-trained separately on simulated and real-world datasets. The discriminator is trained adversarially to facilitate the transfer of long-tail handling capabilities from simulated to real-world environments by the student VLM model, using a novel backpropagation strategy.

cs.RO↗

arXiv2025

Active Secure Neighbor Selection in Multi-Agent Systems with Byzantine Attacks

This paper investigates the problem of resilient control for multi-agent systems in the presence of Byzantine adversaries via an active secure neighbor selection framework. A pre-discriminative graph is first constructed to characterize the admissible set of candidate neighbors for each agent. Based on this graph, a dynamic in-neighbor selection strategy is proposed, wherein each agent actively selects a subset of its pre-discriminative neighbors. The number of selected neighbors is adjustable, allowing for a trade-off between communication overhead and robustness, with the minimal case requiring only a single in-neighbor. The proposed strategy facilitates the reconstruction of a directed spanning tree among normal agents following the detection and isolation of Byzantine agents. It achieves resilient consensus without imposing any assumptions on the initial connectivity among normal agents. Moreover, the approach significantly reduces communication burden while maintaining resilience to adversarial behavior. A numerical example is provided to illustrate the effectiveness of the proposed method.

eess.SY↗

arXiv2025

Reasoning Guided Embeddings: Leveraging MLLM Reasoning for Improved Multimodal Retrieval

Multimodal embeddings are widely used in downstream tasks such as multimodal retrieval, enabling alignment of interleaved modalities in a shared representation space. While recent studies show that Multimodal Large Language Models (MLLMs) can serve as strong embedding extractors, existing approaches treat embedding extraction as a direct encoding step, overlooking the fact that MLLMs possess the generative capability for reasoning that could be leveraged to enhance representation quality. In this work, we explore how to explicitly incorporate reasoning into the embedding process. To this end, we propose Reasoning Guided Embeddings (RGE), which preserves the generative rationale process of MLLMs and couples it with contrastive training. Our method first enables the model to perform structured rationale generation conditioned on the instruction, and then extracts representations after reasoning has unfolded. This simple design enhances the context-conditional inference signals within the embedding, leading to improved multimodal representation quality. Experiments on the MMEB benchmark show that reasoning-guided conditioning improves multimodal retrieval performance by 4.9% over the non-reasoning baseline, confirming that explicit reasoning can effectively enhance embedding quality.

cs.CV↗

arXiv2025

Hyperbolic Hierarchical Alignment Reasoning Network for Text-3D Retrieval

With the daily influx of 3D data on the internet, text-3D retrieval has gained increasing attention. However, current methods face two major challenges: Hierarchy Representation Collapse (HRC) and Redundancy-Induced Saliency Dilution (RISD). HRC compresses abstract-to-specific and whole-to-part hierarchies in Euclidean embeddings, while RISD averages noisy fragments, obscuring critical semantic cues and diminishing the model's ability to distinguish hard negatives. To address these challenges, we introduce the Hyperbolic Hierarchical Alignment Reasoning Network (H$^{2}$ARN) for text-3D retrieval. H$^{2}$ARN embeds both text and 3D data in a Lorentz-model hyperbolic space, where exponential volume growth inherently preserves hierarchical distances. A hierarchical ordering loss constructs a shrinking entailment cone around each text vector, ensuring that the matched 3D instance falls within the cone, while an instance-level contrastive loss jointly enforces separation from non-matching samples. To tackle RISD, we propose a contribution-aware hyperbolic aggregation module that leverages Lorentzian distance to assess the relevance of each local feature and applies contribution-weighted aggregation guided by hyperbolic geometry, enhancing discriminative regions while suppressing redundancy without additional supervision. We also release the expanded T3DR-HIT v2 benchmark, which contains 8,935 text-to-3D pairs, 2.6 times the original size, covering both fine-grained cultural artefacts and complex indoor scenes. Our codes are available at https://github.com/liwrui/H2ARN.

cs.CV↗

arXiv2025

UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback

Relighting is a crucial task with both practical demand and artistic value, and recent diffusion models have shown strong potential by enabling rich and controllable lighting effects. However, as they are typically optimized in semantic latent space, where proximity does not guarantee physical correctness in visual space, they often produce unrealistic results, such as overexposed highlights, misaligned shadows, and incorrect occlusions. We address this with UniLumos, a unified relighting framework for both images and videos that brings RGB-space geometry feedback into a flow matching backbone. By supervising the model with depth and normal maps extracted from its outputs, we explicitly align lighting effects with the scene structure, enhancing physical plausibility. Nevertheless, this feedback requires high-quality outputs for supervision in visual space, making standard multi-step denoising computationally expensive. To mitigate this, we employ path consistency learning, allowing supervision to remain effective even under few-step training regimes. To enable fine-grained relighting control and supervision, we design a structured six-dimensional annotation protocol capturing core illumination attributes. Building upon this, we propose LumosBench, a disentangled attribute-level benchmark that evaluates lighting controllability via large vision-language models, enabling automatic and interpretable assessment of relighting precision across individual dimensions. Extensive experiments demonstrate that UniLumos achieves state-of-the-art relighting quality with significantly improved physical consistency, while delivering a 20x speedup for both image and video relighting. Code is available at https://github.com/alibaba-damo-academy/Lumos-Custom.

cs.CV↗

arXiv2025

Human-in-the-loop Online Rejection Sampling for Robotic Manipulation

Reinforcement learning (RL) is widely used to produce robust robotic manipulation policies, but fine-tuning vision-language-action (VLA) models with RL can be unstable due to inaccurate value estimates and sparse supervision at intermediate steps. In contrast, imitation learning (IL) is easy to train but often underperforms due to its offline nature. In this paper, we propose Hi-ORS, a simple yet effective post-training method that utilizes rejection sampling to achieve both training stability and high robustness. Hi-ORS stabilizes value estimation by filtering out negatively rewarded samples during online fine-tuning, and adopts a reward-weighted supervised training objective to provide dense intermediate-step supervision. For systematic study, we develop an asynchronous inference-training framework that supports flexible online human-in-the-loop corrections, which serve as explicit guidance for learning error-recovery behaviors. Across three real-world tasks and two embodiments, Hi-ORS fine-tunes a pi-base policy to master contact-rich manipulation in just 1.5 hours of real-world training, outperforming RL and IL baselines by a substantial margin in both effectiveness and efficiency. Notably, the fine-tuned policy exhibits strong test-time scalability by reliably executing complex error-recovery behaviors to achieve better performance.

cs.RO↗

arXiv2025

Can an Individual Manipulate the Collective Decisions of Multi-Agents?

Individual Large Language Models (LLMs) have demonstrated significant capabilities across various domains, such as healthcare and law. Recent studies also show that coordinated multi-agent systems exhibit enhanced decision-making and reasoning abilities through collaboration. However, due to the vulnerabilities of individual LLMs and the difficulty of accessing all agents in a multi-agent system, a key question arises: If attackers only know one agent, could they still generate adversarial samples capable of misleading the collective decision? To explore this question, we formulate it as a game with incomplete information, where attackers know only one target agent and lack knowledge of the other agents in the system. With this formulation, we propose M-Spoiler, a framework that simulates agent interactions within a multi-agent system to generate adversarial samples. These samples are then used to manipulate the target agent in the target system, misleading the system's collaborative decision-making process. More specifically, M-Spoiler introduces a stubborn agent that actively aids in optimizing adversarial samples by simulating potential stubborn responses from agents in the target system. This enhances the effectiveness of the generated adversarial samples in misleading the system. Through extensive experiments across various tasks, our findings confirm the risks posed by the knowledge of an individual agent in multi-agent systems and demonstrate the effectiveness of our framework. We also explore several defense mechanisms, showing that our proposed attack framework remains more potent than baselines, underscoring the need for further research into defensive strategies.

cs.CL↗