arXiv subjects

Ye Yuan

Publications and source records attributed to Ye Yuan.

At least 73 records · Page 4Linked to original sources

arXiv2026

StreamTGN: A GPU-Efficient Serving System for Streaming Temporal Graph Neural Networks

Temporal Graph Neural Networks (TGNs) achieve state-of-the-art performance on dynamic graph tasks, yet existing systems focus exclusively on accelerating training -- at inference time, every new edge triggers $O(|V|)$ embedding updates even though only a small fraction of nodes are affected. We present \textbf{StreamTGN}, the first streaming TGN inference system exploiting the inherent locality of temporal graph updates: in an $L$-layer TGN, a new edge affects only nodes within $L$ hops of the endpoints, typically less than 0.2\% on million-node graphs. StreamTGN maintains persistent GPU-resident node memory and uses dirty-flag propagation to identify the affected set $\mathcal{A}$, reducing per-batch complexity from $O(|V|)$ to $O(|\mathcal{A}|)$ with zero accuracy loss. Drift-aware adaptive rebuild scheduling and batched streaming with relaxed ordering further maximize throughput. Experiments on eight temporal graphs (2K--2.6M nodes) show 4.5$\times$--739$\times$ speedup for TGN and up to 4,207$\times$ for TGAT, with identical accuracy. StreamTGN is orthogonal to training optimizations: combining SWIFT with StreamTGN yields 24$\times$ end-to-end speedup across three architectures (TGN, TGAT, DySAT).

cs.DB↗

arXiv2026

Kimodo: Scaling Controllable Human Motion Generation

High-quality human motion data is becoming increasingly important for applications in robotics, simulation, and entertainment. Recent generative models offer a potential data source, enabling human motion synthesis through intuitive inputs like text prompts or kinematic constraints on poses. However, the small scale of public mocap datasets has limited the motion quality, control accuracy, and generalization of these models. In this work, we introduce Kimodo, an expressive and controllable kinematic motion diffusion model trained on 700 hours of optical motion capture data. Our model generates high-quality motions while being easily controlled through text and a comprehensive suite of kinematic constraints including full-body keyframes, sparse joint positions/rotations, 2D waypoints, and dense 2D paths. This is enabled through a carefully designed motion representation and two-stage denoiser architecture that decomposes root and body prediction to minimize motion artifacts while allowing for flexible constraint conditioning. Experiments on the large-scale mocap dataset justify key design decisions and analyze how the scaling of dataset size and model size affect performance.

cs.CV↗

arXiv2026

Embedding-Based Context-Aware Reranker

Retrieval-Augmented Generation (RAG) systems rely on retrieving relevant evidence from a corpus to support downstream generation. The common practice of splitting a long document into multiple shorter passages enables finer-grained and targeted information retrieval. However, it also introduces challenges when a correct retrieval would require inference across passages, such as resolving coreference, disambiguating entities, and aggregating evidence scattered across multiple sources. Many state-of-the-art (SOTA) reranking methods, despite utilizing powerful large pretrained language models with potentially high inference costs, still neglect the aforementioned challenges. Therefore, we propose Embedding-Based Context-Aware Reranker (EBCAR), a lightweight reranking framework operating directly on embeddings of retrieved passages with enhanced cross-passage understandings through the structural information of the passages and a hybrid attention mechanism, which captures both high-level interactions across documents and low-level relationships within each document. We evaluate EBCAR against SOTA rerankers on the ConTEB benchmark, demonstrating its effectiveness for information retrieval requiring cross-passage inference and its advantages in both accuracy and efficiency.

cs.CL↗

arXiv2026

Referring Layer Decomposition

Precise, object-aware control over visual content is essential for advanced image editing and compositional generation. Yet, most existing approaches operate on entire images holistically, limiting the ability to isolate and manipulate individual scene elements. In contrast, layered representations, where scenes are explicitly separated into objects, environmental context, and visual effects, provide a more intuitive and structured framework for interpreting and editing visual content. To bridge this gap and enable both compositional understanding and controllable editing, we introduce the Referring Layer Decomposition (RLD) task, which predicts complete RGBA layers from a single RGB image, conditioned on flexible user prompts, such as spatial inputs (e.g., points, boxes, masks), natural language descriptions, or combinations thereof. At the core is the RefLade, a large-scale dataset comprising 1.11M image-layer-prompt triplets produced by our scalable data engine, along with 100K manually curated, high-fidelity layers. Coupled with a perceptually grounded, human-preference-aligned automatic evaluation protocol, RefLade establishes RLD as a well-defined and benchmarkable research task. Building on this foundation, we present RefLayer, a simple baseline designed for prompt-conditioned layer decomposition, achieving high visual fidelity and semantic alignment. Extensive experiments show our approach enables effective training, reliable evaluation, and high-quality image decomposition, while exhibiting strong zero-shot generalization capabilities.

cs.CV↗

arXiv2026

CHIP: Adaptive Compliance for Humanoid Control through Hindsight Perturbation

Recent progress in humanoid robots has unlocked agile locomotion skills, including backflipping, running, and crawling. Yet it remains challenging for a humanoid robot to perform forceful manipulation tasks such as moving objects, wiping, and pushing a cart. We propose adaptive Compliance Humanoid control through hIsight Perturbation (CHIP), a plug-and-play module that enables controllable end-effector stiffness while preserving agile tracking of dynamic reference motions. CHIP is easy to implement and requires neither data augmentation nor additional reward tuning. We show that a generalist motion-tracking controller trained with CHIP can perform a diverse set of forceful manipulation tasks that require different end-effector compliance, such as multi-robot collaboration, wiping, box delivery, and door opening.

cs.RO↗

arXiv2026

Astro: Activation-guided Structured Regularization for Outlier-Robust LLM Post-Training Quantization

Weight-only post-training quantization (PTQ) is crucial for efficient Large Language Model (LLM) deployment but suffers from accuracy degradation caused by weight and activation outliers. Existing mitigation strategies often face critical limitations: they either yield insufficient outlier suppression or incur significant deployment inefficiencies, such as inference latency, heavy preprocessing, or reliance on complex operator fusion. To resolve these limitations, we leverage a key insight: over-parameterized LLMs often converge to Flat Minima, implying a vast equivalent solution space where weights can be adjusted without compromising accuracy. Building on this, we propose Astro, an Activation-guided Structured Regularization framework designed to suppress the negative effects of outliers in a hardware-friendly and efficient manner. Leveraging the activation-guided regularization objective, Astro actively reconstructs intrinsically robust weights, aggressively suppressing weight outliers corresponding to high-magnitude activations without sacrificing model accuracy. Crucially, Astro introduces zero inference latency and is orthogonal to mainstream quantization methods like GPTQ. Extensive experiments show that Astro achieves highly competitive performance; notably, on LLaMA-2-7B, it achieves better performance than complex learning-based rotation methods with almost 1/3 of the quantization time.

cs.LG↗

arXiv2026

ICON: Invariant Counterfactual Optimization with Neuro-Symbolic Priors for Text-Based Person Search

Text-Based Person Search (TBPS) holds unique value in real-world surveillance bridging visual perception and language understanding, yet current paradigms utilizing pre-training models often fail to transfer effectively to complex open-world scenarios. The reliance on "Passive Observation" leads to multifaceted spurious correlations and spatial semantic misalignment, causing a lack of robustness against distribution shifts. To fundamentally resolve these defects, this paper proposes ICON (Invariant Counterfactual Optimization with Neuro-symbolic priors), a framework integrating causal and topological priors. First, we introduce Rule-Guided Spatial Intervention to strictly penalize sensitivity to bounding box noise, forcibly severing location shortcuts to achieve geometric invariance. Second, Counterfactual Context Disentanglement is implemented via semantic-driven background transplantation, compelling the model to ignore background interference for environmental independence. Then, we employ Saliency-Driven Semantic Regularization with adaptive masking to resolve local saliency bias and guarantee holistic completeness. Finally, Neuro-Symbolic Topological Alignment utilizes neuro-symbolic priors to constrain feature matching, ensuring activated regions are topologically consistent with human structural logic. Experimental results demonstrate that ICON not only maintains leading performance on standard benchmarks but also exhibits exceptional robustness against occlusion, background interference, and localization noise. This approach effectively advances the field by shifting from fitting statistical co-occurrences to learning causal invariance.

cs.AI↗

arXiv2026

Vidi2.5: Large Multimodal Models for Video Understanding and Creation

Video has emerged as the primary medium for communication and creativity on the Internet, driving strong demand for scalable, high-quality video production. Vidi models continue to evolve toward next-generation video creation and have achieved state-of-the-art performance in multimodal temporal retrieval (TR). In its second release, Vidi2 advances video understanding with fine-grained spatio-temporal grounding (STG) and extends its capability to video question answering (Video QA), enabling comprehensive multimodal reasoning. Given a text query, Vidi2 can identify not only the corresponding timestamps but also the bounding boxes of target objects within the output time ranges. To enable comprehensive evaluation of STG, we introduce a new benchmark, VUE-STG, which offers critical improvements over existing STG datasets. In addition, we upgrade the previous VUE-TR benchmark to VUE-TR-V2, achieving a more balanced duration and query distribution. Remarkably, the Vidi2 model substantially outperforms leading proprietary systems, such as Gemini 3 Pro Preview and GPT-5, on both VUE-TR-V2 and VUE-STG, while achieving competitive results with popular open-source models with similar scale on video QA benchmarks. The latest Vidi2.5 offers significantly stronger STG capability and slightly better TR and Video QA performance over Vidi2. This update also introduces a Vidi2.5-Think model to handle plot understanding with complex plot reasoning. To comprehensively evaluate the performance of plot understanding, we propose VUE-PLOT benchmark with two tracks, Character and Reasoning. Notably, Vidi2.5-Think outperforms Gemini 3 Pro Preview on fine-grained character understanding with comparable performance on complex plot reasoning. Furthermore, we demonstrate the effectiveness of Vidi2.5 on a challenging real-world application, video editing planning.

cs.CV↗

arXiv2026

Diffusion Large Language Models for Black-Box Optimization

Offline black-box optimization (BBO) aims to find optimal designs based solely on an offline dataset of designs and their labels. Such scenarios frequently arise in domains like DNA sequence design and robotics, where only a few labeled data points are available. Traditional methods typically rely on task-specific proxy or generative models, overlooking the in-context learning capabilities of pre-trained large language models (LLMs). Recent efforts have adapted autoregressive LLMs to BBO by framing task descriptions and offline datasets as natural language prompts, enabling direct design generation. However, these designs often contain bidirectional dependencies, which left-to-right models struggle to capture. In this paper, we explore diffusion LLMs for BBO, leveraging their bidirectional modeling and iterative refinement capabilities. This motivates our in-context denoising module: we condition the diffusion LLM on the task description and the offline dataset, both formatted in natural language, and prompt it to denoise masked designs into improved candidates. To guide the generation toward high-performing designs, we introduce masked diffusion tree search, which casts the denoising process as a step-wise Monte Carlo Tree Search that dynamically balances exploration and exploitation. Each node represents a partially masked design, each denoising step is an action, and candidates are evaluated via expected improvement under a Gaussian Process trained on the offline dataset. Our method, dLLM, achieves state-of-the-art results in few-shot settings on design-bench.

cs.CE↗

arXiv2026

VENENA: A Deceptive Visual Encryption Framework for Wireless Semantic Secrecy

Eavesdropping has been a long-standing threat to the security and privacy of wireless communications, since it is difficult to detect and costly to prevent. As networks evolve towards Sixth Generation (6G) and semantic communication becomes increasingly central to next-generation wireless systems, securing semantic information transmission emerges as a critical challenge. While classical physical layer security (PLS) focuses on passive security, the recently proposed concept of physical layer deception (PLD) offers a semantic encryption measure to actively deceive eavesdroppers. Yet the existing studies of PLD have been dominantly information-theoretical and link-level oriented, lacking considerations of system-level design and practical implementation. In this work we propose Visual ENcryption for Eavesdropping NegAtion (VENENA), an artificial intelligence-enabled framework for secure image-based communication. VENENA protects confidential messages by encoding them visually while actively deceiving eavesdroppers: legitimate receivers use artificial intelligence (AI)-based classifiers to extract true message semantics, while interceptors perceive only falsified content. The framework transmits two superimposed image components with different power levels - a high-power decoy image and a low-power correction mask - ensuring only authorized receivers with favorable channel conditions can reconstruct the true message. Experimental validation demonstrates over 93% accuracy for legitimate users while limiting eavesdropper success to 52% even when system design is fully known, validating VENENA's active defense capability for 6G semantic communication.

cs.CR↗

arXiv2026

Offline Model-Based Optimization: Comprehensive Review

Offline optimization is a fundamental challenge in science and engineering, where the goal is to optimize black-box functions using only offline datasets. This setting is particularly relevant when querying the objective function is prohibitively expensive or infeasible, with applications spanning protein engineering, material discovery, neural architecture search, and beyond. The main difficulty lies in accurately estimating the objective landscape beyond the available data, where extrapolations are fraught with significant epistemic uncertainty. This uncertainty can lead to objective hacking(reward hacking), exploiting model inaccuracies in unseen regions, or other spurious optimizations that yield misleadingly high performance estimates outside the training distribution. Recent advances in model-based optimization(MBO) have harnessed the generalization capabilities of deep neural networks to develop offline-specific surrogate and generative models. Trained with carefully designed strategies, these models are more robust against out-of-distribution issues, facilitating the discovery of improved designs. Despite its growing impact in accelerating scientific discovery, the field lacks a comprehensive review. To bridge this gap, we present the first thorough review of offline MBO. We begin by formalizing the problem for both single-objective and multi-objective settings and by reviewing recent benchmarks and evaluation metrics. We then categorize existing approaches into two key areas: surrogate modeling, which emphasizes accurate function approximation in out-of-distribution regions, and generative modeling, which explores high-dimensional design spaces to identify high-performing designs. Finally, we examine the key challenges and propose promising directions for advancement in this rapidly evolving field including safe control of superintelligent systems.

cs.LG↗

arXiv2025

Jensen-Shannon Divergence Message-Passing for Rich-Text Graph Representation Learning

In this paper, we investigate how the widely existing contextual and structural divergence may influence the representation learning in rich-text graphs. To this end, we propose Jensen-Shannon Divergence Message-Passing (JSDMP), a new learning paradigm for rich-text graph representation learning. Besides considering similarity regarding structure and text, JSDMP further captures their corresponding dissimilarity by Jensen-Shannon divergence. Similarity and dissimilarity are then jointly used to compute new message weights among text nodes, thus enabling representations to learn with contextual and structural information from truly correlated text nodes. With JSDMP, we propose two novel graph neural networks, namely Divergent message-passing graph convolutional network (DMPGCN) and Divergent message-passing Page-Rank graph neural networks (DMPPRG), for learning representations in rich-text graphs. DMPGCN and DMPPRG have been extensively texted on well-established rich-text datasets and compared with several state-of-the-art baselines. The experimental results show that DMPGCN and DMPPRG can outperform other baselines, demonstrating the effectiveness of the proposed Jensen-Shannon Divergence Message-Passing paradigm

cs.LG↗

arXiv2025

A Novel Graph-Sequence Learning Model for Inductive Text Classification

Text classification plays an important role in various downstream text-related tasks, such as sentiment analysis, fake news detection, and public opinion analysis. Recently, text classification based on Graph Neural Networks (GNNs) has made significant progress due to their strong capabilities of structural relationship learning. However, these approaches still face two major limitations. First, these approaches fail to fully consider the diverse structural information across word pairs, e.g., co-occurrence, syntax, and semantics. Furthermore, they neglect sequence information in the text graph structure information learning module and can not classify texts with new words and relations. In this paper, we propose a Novel Graph-Sequence Learning Model for Inductive Text Classification (TextGSL) to address the previously mentioned issues. More specifically, we construct a single text-level graph for all words in each text and establish different edge types based on the diverse relationships between word pairs. Building upon this, we design an adaptive multi-edge message-passing paradigm to aggregate diverse structural information between word pairs. Additionally, sequential information among text data can be captured by the proposed TextGSL through the incorporation of Transformer layers. Therefore, TextGSL can learn more discriminative text representations. TextGSL has been comprehensively compared with several strong baselines. The experimental results on diverse benchmarking datasets demonstrate that TextGSL outperforms these baselines in terms of accuracy.

cs.CL↗

arXiv2025

Modular Layout Synthesis (MLS): Front-end Code via Structure Normalization and Constrained Generation

Automated front-end engineering drastically reduces development cycles and minimizes manual coding overhead. While Generative AI has shown promise in translating designs to code, current solutions often produce monolithic scripts, failing to natively support modern ecosystems like React, Vue, or Angular. Furthermore, the generated code frequently suffers from poor modularity, making it difficult to maintain. To bridge this gap, we introduce Modular Layout Synthesis (MLS), a hierarchical framework that merges visual understanding with structural normalization. Initially, a visual-semantic encoder maps the screen capture into a serialized tree topology, capturing the essential layout hierarchy. Instead of simple parsing, we apply heuristic deduplication and pattern recognition to isolate reusable blocks, creating a framework-agnostic schema. Finally, a constraint-based generation protocol guides the LLM to synthesize production-ready code with strict typing and component props. Evaluations show that MLS significantly outperforms existing baselines, ensuring superior code reusability and structural integrity across multiple frameworks

cs.IR↗

arXiv2025

An AI-driven Assessment of Bone Density as a Biomarker Leading to the Aging Law

As global population aging intensifies, there is growing interest in the study of biological age. Bones have long been used to evaluate biological age, and the decline in bone density with age is a well-recognized phenomenon in adults. However, the pattern of this decline remains controversial, making it difficult to serve as a reliable indicator of the aging process. Here we present a novel AI-driven statistical method to assess the bone density, and a discovery that the bone mass distribution in trabecular bone of vertebrae follows a non-Gaussian, unimodal, and skewed distribution in CT images. The statistical mode of the distribution is defined as the measure of bone mass, which is a groundbreaking assessment of bone density, named Trabecular Bone Density (TBD). The dataset of CT images are collected from 1,719 patients who underwent PET/CT scans in three hospitals, in which a subset of the dataset is used for AI model training and generalization. Based upon the cases, we demonstrate that the pattern of bone density declining with aging exhibits a consistent trend of exponential decline across sexes and age groups using TBD assessment. The developed AI-driven statistical method blazes a trail in the field of AI for reliable quantitative computation and AI for medicine. The findings suggest that human aging is a gradual process, with the rate of decline slowing progressively over time, which will provide a valuable basis for scientific prediction of life expectancy.

physics.med-ph↗

arXiv2025

A Multi-scale Fused Graph Neural Network with Inter-view Contrastive Learning for Spatial Transcriptomics Data Clustering

Spatial transcriptomics enables genome-wide expression analysis within native tissue context, yet identifying spatial domains remains challenging due to complex gene-spatial interactions. Existing methods typically process spatial and feature views separately, fusing only at output level - an "encode-separately, fuse-late" paradigm that limits multi-scale semantic capture and cross-view interaction. Accordingly, stMFG is proposed, a multi-scale interactive fusion graph network that introduces layer-wise cross-view attention to dynamically integrate spatial and gene features after each convolution. The model combines cross-view contrastive learning with spatial constraints to enhance discriminability while maintaining spatial continuity. On DLPFC and breast cancer datasets, stMFG outperforms state-of-the-art methods, achieving up to 14% ARI improvement on certain slices.

cs.LG↗

arXiv2025

Condensation-Concatenation Framework for Dynamic Graph Continual Learning

Dynamic graphs are prevalent in real-world scenarios, where continuous structural changes induce catastrophic forgetting in graph neural networks (GNNs). While continual learning has been extended to dynamic graphs, existing methods overlook the effects of topological changes on existing nodes. To address it, we propose a novel framework for continual learning on dynamic graphs, named Condensation-Concatenation-based Continual Learning (CCC). Specifically, CCC first condenses historical graph snapshots into compact semantic representations while aiming to preserve the original label distribution and topological properties. Then it concatenates these historical embeddings with current graph representations selectively. Moreover, we refine the forgetting measure (FM) to better adapt to dynamic graph scenarios by quantifying the predictive performance degradation of existing nodes caused by structural updates. CCC demonstrates superior performance over state-of-the-art baselines across four real-world datasets in extensive experiments.

cs.LG↗

arXiv2025

VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation

A key barrier to the real-world deployment of humanoid robots is the lack of autonomous loco-manipulation skills. We introduce VIRAL, a visual sim-to-real framework that learns humanoid loco-manipulation entirely in simulation and deploys it zero-shot to real hardware. VIRAL follows a teacher-student design: a privileged RL teacher, operating on full state, learns long-horizon loco-manipulation using a delta action space and reference state initialization. A vision-based student policy is then distilled from the teacher via large-scale simulation with tiled rendering, trained with a mixture of online DAgger and behavior cloning. We find that compute scale is critical: scaling simulation to tens of GPUs (up to 64) makes both teacher and student training reliable, while low-compute regimes often fail. To bridge the sim-to-real gap, VIRAL combines large-scale visual domain randomization over lighting, materials, camera parameters, image quality, and sensor delays--with real-to-sim alignment of the dexterous hands and cameras. Deployed on a Unitree G1 humanoid, the resulting RGB-based policy performs continuous loco-manipulation for up to 54 cycles, generalizing to diverse spatial and appearance variations without any real-world fine-tuning, and approaching expert-level teleoperation performance. Extensive ablations dissect the key design choices required to make RGB-based humanoid loco-manipulation work in practice.

cs.RO↗