Searcharxiv⌕ Search

arXiv subjects

Xing Wang

Publications and source records attributed to Xing Wang.

At least 37 records · Page 2Linked to original sources
arXiv2026

Motion-Aware Caching for Efficient Autoregressive Video Generation

Autoregressive video generation paradigms offer theoretical promise for long video synthesis, yet their practical deployment is hindered by the computational burden of sequential iterative denoising. While cache reuse strategies can accelerate generation by skipping redundant denoising steps, existing methods rely on coarse-grained chunk-level skipping that fails to capture fine-grained pixel dynamics. This oversight is critical: pixels with high motion require more denoising steps to prevent error accumulation, while static pixels tolerate aggressive skipping. We formalize this insight theoretically by linking cache errors to residual instability, and propose MotionCache, a motion-aware cache framework that exploits inter-frame differences as a lightweight proxy for pixel-level motion characteristics. MotionCache employs a coarse-to-fine strategy: an initial warm-up phase establishes semantic coherence, followed by motion-weighted cache reuse that dynamically adjusts update frequencies per token. Extensive experiments on state-of-the-art models like SkyReels-V2 and MAGI-1 demonstrate that MotionCache achieves significant speedups of $\textbf{6.28}\times$ and $\textbf{1.64}\times$ respectively, while effectively preserving generation quality (VBench: $1\%\downarrow$ and $0.01\%\downarrow$ respectively). The code is available at https://github.com/ywlq/MotionCache.

cs.CV↗
arXiv2026

New algorithms for Feynman integral reduction and $\varepsilon$-factorised differential equations

In this paper, we give a detailed account of the algorithm outlined in [1] for Feynman integral reduction and $\varepsilon$-factorised differential equations. The algorithm consists of two steps. In the first step, we use a new geometric order relation in the integration-by-parts reduction to obtain a basis of master integrals, whose differential equations on the maximal cut are of a Laurent polynomial form in the regularisation parameter $\varepsilon$ and compatible with a filtration. This step works entirely with rational functions. In a second step, we provide a method to $\varepsilon$-factorise the aforementioned Laurent differential equations. The second step may introduce algebraic and transcendental functions. We illustrate the versatility of the algorithm by applying it to different examples with a wide range of complexity.

hep-th↗
arXiv2026

S2O: Early Stopping for Sparse Attention via Online Permutation

Attention scales quadratically with sequence length, fundamentally limiting long-context inference. Existing block-granularity sparsification can reduce latency, but coarse blocks impose an intrinsic sparsity ceiling, making further improvements difficult even with carefully engineered designs. We present S2O, which performs early stopping for sparse attention via online permutation. Inspired by virtual-to-physical address mapping in memory systems, S2O revisits and factorizes FlashAttention execution, enabling inference to load non-contiguous tokens rather than a contiguous span in the original order. Motivated by fine-grained structures in attention heatmaps, we transform explicit permutation into an online, index-guided, discrete loading policy; with extremely lightweight preprocessing and index-remapping overhead, it concentrates importance on a small set of high-priority blocks. Building on this importance-guided online permutation for loading, S2O further introduces an early-stopping rule: computation proceeds from high to low importance; once the current block score falls below a threshold, S2O terminates early and skips the remaining low-contribution blocks, thereby increasing effective sparsity and reducing computation under a controlled error budget. As a result, S2O substantially raises the practical sparsity ceiling. On Llama-3.1-8B under a 128K context, S2O reduces single-operator MSE by 3.82$\times$ at matched sparsity, and reduces prefill compute density by 3.31$\times$ at matched MSE; meanwhile, it preserves end-to-end accuracy and achieves 7.51$\times$ attention and 3.81$\times$ end-to-end speedups.

cs.LG↗
arXiv2026

Multi-output Extreme Spatial Model for Complex Aircraft Production Systems

Problem definition: Data-driven models in machine learning have enabled efficient management of production systems. However, a majority of machine learning models are devoted to modeling the mean response or average pattern, which is inappropriate for studying abnormal extreme events that are often of primary interest in aircraft manufacturing. Since extreme events from heavy-tailed distributions give rise to prohibitive expenditures in system management, sophisticated extreme models are urgently needed to analyze complex extreme risks. Engineering applications of extreme models usually focus on individual extreme events, which is insufficient for complex systems with correlations. Methodology/results: We introduce an extreme spatial model for multi-output response control systems that efficiently captures the dynamics using a bilinear function on two spatial domains for control variables and measurement locations. Marginal parameter modeling and extremal dependence have been investigated. In addition, an efficient graph-assisted composite likelihood estimation and corresponding computational algorithms are developed to cope with high-dimensional outputs. The application to composite aircraft production shows that the proposed model enables comprehensive analyses with superior predictive performance on extreme events compared to canonical methods. Managerial implications: Our method shows how to use an extreme spatial model for predicting extreme events and managing extreme risks in complex production systems such as aircraft. This can help achieve better quality management and operation safety in aircraft production systems and beyond.

stat.AP↗
arXiv2026

A Real-World Grasping-in-Clutter Performance Evaluation Benchmark for Robotic Food Waste Sorting

Food waste management is critical for sustainability, yet inorganic contaminants hinder recycling potential. Robotic automation accelerates sorting through automated contaminant removal. Nevertheless, the diverse and unpredictable nature of contaminants introduces major challenges for reliable robotic grasping. Grasp performance benchmarking provides a rigorous methodology for evaluating these challenges in underexplored field contexts like food waste sorting. However, existing approaches suffer from limited simulation datasets, over-reliance on simplistic metrics like success rate, inability to account for object-related pre-grasp conditions, and lack of comprehensive failure analysis. To address these gaps, this work introduces GRAB, a real-world grasping-in-clutter (GIC) performance benchmark incorporating: (1) diverse deformable object datasets, (2) advanced 6D grasp pose estimation, and (3) explicit evaluation of pre-grasp conditions through graspability metrics. The benchmark compares industrial grasping across three gripper modalities through 1,750 grasp attempts across four randomized clutter levels. Results reveal a clear hierarchy among graspability parameters, with object quality emerging as the dominant factor governing grasp performance across modalities. Failure mode analysis shows that physical interaction constraints, rather than perception or control limitations, constitute the primary source of grasp failures in cluttered environments. By enabling identification of dominant factors influencing grasp performance, GRAB provides a principled foundation for designing robust, adaptive grasping systems for complex, cluttered food waste sorting.

cs.RO↗
arXiv2026

Error Propagation Mechanisms and Compensation Strategies for Quantized Diffusion

Diffusion models have transformed image synthesis by establishing unprecedented quality and creativity benchmarks. Nevertheless, their large-scale deployment faces challenges due to computationally intensive iterative denoising processes. Although post-training quantization (PTQ) provides an effective pathway for accelerating sampling, the iterative nature of diffusion models causes stepwise quantization errors to accumulate progressively during generation, inevitably compromising output fidelity. To address this challenge, we develop a theoretical framework that mathematically formulates error propagation in Diffusion Models (DMs), deriving per-step quantization error propagation equations and establishing the first closed-form solution for cumulative error. Building on this theoretical foundation, we propose a timestep-aware cumulative error compensation scheme. Extensive experiments on multiple image datasets demonstrate that our compensation strategy effectively mitigates error propagation, significantly enhancing existing PTQ methods. Specifically, it achieves a 1.2 PSNR improvement over SVDQuant on SDXL W4A4, while incurring only an additional $<$ 0.5\% time overhead.

cs.CV↗
arXiv2026

The geometric bookkeeping guide to Feynman integral reduction and $\varepsilon$-factorised differential equations

We report on three improvements in the context of Feynman integral reduction and $\varepsilon$-factorised differential equations: Firstly, we show that with a specific choice of prefactors, we trivialise the $\varepsilon$-dependence of the integration-by-parts identities. Secondly, we observe that with a specific choice of order relation in the Laporta algorithm, we directly obtain a basis of master integrals, whose differential equation on the maximal cut is in Laurent polynomial form with respect to $\varepsilon$ and compatible with a particular filtration. Thirdly, we prove that such a differential equation can always be transformed to an $\varepsilon$-factorised form. This provides a systematic algorithm to obtain an $\varepsilon$-factorised differential equation for any Feynman integral. Furthermore, the choices for the prefactors and the order relation significantly improve the efficiency of the reduction algorithm.

hep-th↗
arXiv2026

Train Short, Inference Long: Training-free Horizon Extension for Autoregressive Video Generation

Autoregressive video diffusion models have emerged as a scalable paradigm for long video generation. However, they often suffer from severe extrapolation failure, where rapid error accumulation leads to significant temporal degradation when extending beyond training horizons. We identify that this failure primarily stems from the spectral bias of 3D positional embeddings and the lack of dynamic priors in noise sampling. To address these issues, we propose FLEX (Frequency-aware Length EXtension), a training-free inference-time framework that bridges the gap between short-term training and long-term inference. FLEX introduces Frequency-aware RoPE Modulation to adaptively interpolate under-trained low-frequency components while extrapolating high-frequency ones to preserve multi-scale temporal discriminability. This is integrated with Antiphase Noise Sampling (ANS) to inject high-frequency dynamic priors and Inference-only Attention Sink to anchor global structure. Extensive evaluations on VBench demonstrate that FLEX significantly outperforms state-of-the-art models at 6x extrapolation (30s duration) and matches the performance of long-video fine-tuned baselines at 12x scale (60s duration). As a plug-and-play augmentation, FLEX seamlessly integrates into existing inference pipelines for horizon extension. It effectively pushes the generation limits of models such as LongLive, supporting consistent and dynamic video synthesis at a 4-minute scale. Project page is available at https://ga-lee.github.io/FLEX_demo.

cs.CV↗
arXiv2026

An algorithm towards $\varepsilon$-factorising Feynman Integrals

In this talk, we use several examples to elaborate on how a recently proposed algorithm can turn non-trivial Feynman integrals into an $\varepsilon $-factorised manner, regardless of their hidden geometric essence. In particular, some extra details about three-loop banana integrals with unequal-mass configuration are provided.

hep-th↗
arXiv2026

TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration

Diffusion models achieve strong generative performance but remain slow at inference due to the need for repeated full-model denoising passes. We present Token-Adaptive Predictor (TAP), a training-free, probe-driven framework that adaptively selects a predictor for each token at every sampling step. TAP uses a single full evaluation of the model's first layer as a low-cost probe to compute proxy losses for a compact family of candidate predictors (instantiated primarily with Taylor expansions of varying order and horizon), then assigns each token the predictor with the smallest proxy error. This per-token "probe-then-select" strategy exploits heterogeneous temporal dynamics, requires no additional training, and is compatible with various predictor designs. TAP incurs negligible overhead while enabling large speedups with little or no perceptual quality loss. Extensive experiments across multiple diffusion architectures and generation tasks show that TAP substantially improves the accuracy-efficiency frontier compared to fixed global predictors and caching-only baselines.

cs.CV↗
arXiv2026

Network Topology Optimization via Deep Reinforcement Learning

Topology impacts important network performance metrics, including link utilization, throughput and latency, and is of central importance to network operators. However, due to the combinatorial nature of network topology, it is extremely difficult to obtain an optimal solution, especially since topology planning in networks also often comes with management-specific constraints. As a result, local optimization with hand-tuned heuristic methods from human experts is often adopted in practice. Yet, heuristic methods cannot cover the global topology design space while taking into account constraints, and cannot guarantee to find good solutions. In this paper, we propose a novel deep reinforcement learning (DRL) algorithm for graph searching, called DRL-GS, for network topology optimization. DRL-GS consists of three novel components, including a verifier to validate the correctness of a generated network topology, a graph neural network (GNN) to efficiently approximate topology rating, and a DRL agent to conduct a topology search. DRL-GS can efficiently search over relatively large topology space and output topology with satisfactory performance. We conduct a case study based on a real-world network scenario, and our experimental results demonstrate the superior performance of DRL-GS in terms of both efficiency and performance.

cs.NI↗
arXiv2026

Improving integration-by-parts and differential equations

In this talk, we discuss how ideas from geometry help to improve Feynman integral reduction and the construction of $\varepsilon$-factorised differential equations. In particular, we outline a systematic procedure to obtain an $\varepsilon$-factorised differential equation for any Feynman integral.

hep-th↗
arXiv2026

Flow caching for autoregressive video generation

Autoregressive models, often built on Transformer architectures, represent a powerful paradigm for generating ultra-long videos by synthesizing content in sequential chunks. However, this sequential generation process is notoriously slow. While caching strategies have proven effective for accelerating traditional video diffusion models, existing methods assume uniform denoising across all frames-an assumption that breaks down in autoregressive models where different video chunks exhibit varying similarity patterns at identical timesteps. In this paper, we present FlowCache, the first caching framework specifically designed for autoregressive video generation. Our key insight is that each video chunk should maintain independent caching policies, allowing fine-grained control over which chunks require recomputation at each timestep. We introduce a chunkwise caching strategy that dynamically adapts to the unique denoising characteristics of each chunk, complemented by a joint importance-redundancy optimized KV cache compression mechanism that maintains fixed memory bounds while preserving generation quality. Our method achieves remarkable speedups of 2.38 times on MAGI-1 and 6.7 times on SkyReels-V2, with negligible quality degradation (VBench: 0.87 increase and 0.79 decrease respectively). These results demonstrate that FlowCache successfully unlocks the potential of autoregressive models for real-time, ultra-long video generation-establishing a new benchmark for efficient video synthesis at scale. The code is available at https://github.com/mikeallen39/FlowCache.

cs.CV↗
arXiv2026

ERTACache: Error Rectification and Timesteps Adjustment for Efficient Diffusion

Diffusion models suffer from substantial computational overhead due to their inherently iterative inference process. While feature caching offers a promising acceleration strategy by reusing intermediate outputs across timesteps, naive reuse often incurs noticeable quality degradation. In this work, we formally analyze the cumulative error introduced by caching and decompose it into two principal components: feature shift error, caused by inaccuracies in cached outputs, and step amplification error, which arises from error propagation under fixed timestep schedules. To address these issues, we propose ERTACache, a principled caching framework that jointly rectifies both error types. Our method employs an offline residual profiling stage to identify reusable steps, dynamically adjusts integration intervals via a trajectory-aware correction coefficient, and analytically approximates cache-induced errors through a closed-form residual linearization model. Together, these components enable accurate and efficient sampling under aggressive cache reuse. Extensive experiments across standard image and video generation benchmarks show that ERTACache achieves up to 2x inference speedup while consistently preserving or even improving visual quality. Notably, on the state-of-the-art Wan2.1 video diffusion model, ERTACache delivers 2x acceleration with minimal VBench degradation, effectively maintaining baseline fidelity while significantly improving efficiency. The code is available at https://github.com/bytedance/ERTACache.

cs.CV↗
arXiv2026

FlowAct-R1: Towards Interactive Humanoid Video Generation

Interactive humanoid video generation aims to synthesize lifelike visual agents that can engage with humans through continuous and responsive video. Despite recent advances in video synthesis, existing methods often grapple with the trade-off between high-fidelity synthesis and real-time interaction requirements. In this paper, we propose FlowAct-R1, a framework specifically designed for real-time interactive humanoid video generation. Built upon a MMDiT architecture, FlowAct-R1 enables the streaming synthesis of video with arbitrary durations while maintaining low-latency responsiveness. We introduce a chunkwise diffusion forcing strategy, complemented by a novel self-forcing variant, to alleviate error accumulation and ensure long-term temporal consistency during continuous interaction. By leveraging efficient distillation and system-level optimizations, our framework achieves a stable 25fps at 480p resolution with a time-to-first-frame (TTFF) of only around 1.5 seconds. The proposed method provides holistic and fine-grained full-body control, enabling the agent to transition naturally between diverse behavioral states in interactive scenarios. Experimental results demonstrate that FlowAct-R1 achieves exceptional behavioral vividness and perceptual realism, while maintaining robust generalization across diverse character styles.

cs.CV↗
arXiv2026

Data-Driven Flow Initialization Framework for CFD Acceleration of Underwater Vehicle in Vertical-Plane Oblique Motion

Accurate prediction of flow fields around underwater vehicles undergoing vertical-plane oblique motions is critical for hydrodynamic analysis, but it often requires computationally expensive CFD simulations. This study proposes a Data-Driven Flow Initialization (DDFI) framework that accelerates CFD simulation by integrating deep neural network (DNN) to predict full-domain flow fields. Using the suboff hull under various inlet velocities and angles of attack as an example, a DNN is trained to predict velocity, pressure, and turbulent quantities based on mesh geometry, operating conditions, and hybrid vectors. The DNN can provide reasonably accurate predictions with a relative error about 3.3%. To enhance numerical accuracy while maintaining physical consistency, the DNN-predicted flow fields are utilized as initial solutions for the CFD solver, achieving up to 3.5-fold and 2.0-fold speedup at residual thresholds of 5*10^(-6)and 5*10^(-8), respectively. This method maintains physical consistency by refining neural network outputs via traditional CFD solvers, balancing computational efficiency and accuracy. Notably, reducing the size of training set does not exert an essential impact on acceleration performance. Besides, this method exhibits cross-mesh generalization capability. In general, this proposed hybrid approach offers a new pathway for high-fidelity and efficient full-domain flow field predictions around complex underwater vehicles.

physics.flu-dyn↗
arXiv2026

NL2Dashboard: A Lightweight and Controllable Framework for Generating Dashboards with LLMs

While Large Language Models (LLMs) have demonstrated remarkable proficiency in generating standalone charts, synthesizing comprehensive dashboards remains a formidable challenge. Existing end-to-end paradigms, which typically treat dashboard generation as a direct code generation task (e.g., raw HTML), suffer from two fundamental limitations: representation redundancy due to massive tokens spent on visual rendering, and low controllability caused by the entanglement of analytical reasoning and presentation. To address these challenges, we propose NL2Dashboard, a lightweight framework grounded in the principle of Analysis-Presentation Decoupling. We introduce a structured intermediate representation (IR) that encapsulates the dashboard's content, layout, and visual elements. Therefore, it confines the LLM's role to data analysis and intent translation, while offloading visual synthesis to a deterministic rendering engine. Building upon this framework, we develop a multi-agent system in which the IR-driven algorithm is instantiated as a suite of tools. Comprehensive experiments conducted with this system demonstrate that NL2Dashboard significantly outperforms state-of-the-art baselines across diverse domains, achieving superior visual quality, significantly higher token efficiency, and precise controllability in both generation and modification tasks.

cs.AI↗
arXiv2025

High Dimensional Data Decomposition for Anomaly Detection of Textured Images

In the realm of diverse high-dimensional data, images play a significant role across various processes of manufacturing systems where efficient image anomaly detection has emerged as a core technology of utmost importance. However, when applied to textured defect images, conventional anomaly detection methods have limitations including non-negligible misidentification, low robustness, and excessive reliance on large-scale and structured datasets. This paper proposes a texture basis integrated smooth decomposition (TBSD) approach, which is targeted at efficient anomaly detection in textured images with smooth backgrounds and sparse anomalies. Mathematical formulation of quasi-periodicity and its theoretical properties are investigated for image texture estimation. TBSD method consists of two principal processes: the first process learns the texture basis functions to effectively extract quasi-periodic texture patterns; the subsequent anomaly detection process utilizes that texture basis as prior knowledge to prevent texture misidentification and capture potential anomalies with high accuracy.The proposed method surpasses benchmarks with less misidentification, smaller training dataset requirement, and superior anomaly detection performance on both simulation and real-world datasets.

cs.CV↗