arXiv subjects

Bingyan Liu

Publications and source records attributed to Bingyan Liu.

At least 19 recordsLinked to original sources

arXiv2026

Room-temperature ferroelectrically switchable quantum geometry in few-layer WTe2 for complementary in-memory computing

Quantum geometry, describing the inherent geometric structure of electron wavefunctions in momentum space, transcends the traditional charge degree of freedom and provides a novel physical basis for information encoding and processing. The key to such new computing paradigms is the non-volatile electrical programming of quantum geometric states at room temperature, which, however, has not been established. Here, we demonstrate ferroelectrically switchable quantum geometry in few-layer WTe2, which uniquely enables complementary convolutional processing. By employing the intrinsic coupling between ferroelectric polarization and quantum geometry in few-layer WTe2, we show that the second- and third-order nonlinear anomalous Hall effects (NLAHE) can be deterministically and electrically switched in a nonvolatile and correlated manner. The switching is robust at room temperature for ~104 cycles and retention of ~105 s. Furthermore, leveraging the opposite switching behaviors of second- and third-order NLAHE at room temperature, we demonstrate complementary in-memory computing and implement a hardware-level complementary convolution kernel. This kernel overcomes the inherent directional specificity of conventional convolutional networks and achieves a texture recognition accuracy of 98%, thereby illustrating a viable pathway towards physics-native computing through exploiting exotic physics in quantum materials.

cond-mat.mtrl-sci↗

arXiv2026

Reflex: Real-Time VLA Control through Streaming Inference

Flow matching Vision-Language-Action (VLA) models promise precise continuous control, but their iterative denoising nature introduces fundamental incompatibilities with real-time robotics: global timestep injection invalidates KV-caching, forcing a choice between slow $O(N^2)$ re-computation or mathematically incorrect cache reuse. We present \textbf{Reflex}, a framework that enables \textit{real-time streaming inference} for flow matching policies by exploiting the \textit{Timestep-Invariance Property} -- that perception encoders are functionally independent of the denoising loop. Reflex partitions the attention context into static, sliding, and dynamic regions, enabling $O(1)$ incremental cache updates while preserving full-batch-equivalent attention outputs for fixed inputs. To ensure stability under continuous high-frequency inference, we introduce \textit{AdaRMSNorm}, an adaptive normalization layer that prevents BFloat16 numerical collapse by gating on flow phase. We further maximize throughput through an \textit{async pipeline} that decouples visual encoding from action generation, combined with \textit{operator fusion} that reduces kernel overhead. On LIBERO and Kinetix benchmarks, Reflex achieves a 2.58$\times$ inference speedup and 50Hz stable streaming, reducing reaction latency by up to 54\% and enabling efficient deployment without performance degradation.

cs.RO↗

arXiv2026

MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation

While video foundation models excel at single-shot generation, real-world cinematic storytelling inherently relies on complex multi-shot sequencing. Further progress is constrained by the absence of datasets that address three core challenges: authentic narrative logic, spatiotemporal text-video alignment conflicts, and the "copy-paste" dilemma prevalent in Subject-to-Video (S2V) generation. To bridge this gap, we introduce MuSS, a large-scale, dual-track dataset tailored for multi-shot video and S2V generation. Sourced from over 3,000 movies, MuSS explicitly supports both complex montage transitions and subject-centric narratives. To construct this dataset, we pioneer a progressive captioning pipeline that eliminates contextual conflicts by ensuring local shot-level accuracy before enforcing global narrative coherence. Crucially, we implement a cross-shot matching mechanism to fundamentally eradicate the S2V copy-paste shortcut. Alongside the dataset, we propose the Cinematic Narrative Benchmark, featuring a visual-logic-driven paradigm and a novel Anti-Copy-Paste Variance (ACP-Var) metric to rigorously assess continuous storytelling and 3D structural consistency. Extensive experiments demonstrate that while current baselines struggle with continuous narrative logic or degenerate into trivial 2D sticker generators, our MuSS-augmented model achieves state-of-the-art narrative effectiveness and cross-shot identity preservation.

cs.CV↗

arXiv2026

Discrete Poincare and Bogovskii operators on cochains and Whitney forms

Smooth Poincare operators are a tool used to show the vanishing of smooth de Rham cohomology on contractible manifolds and have found use in the analysis of finite element methods based on the Finite Element Exterior Calculus (FEEC). We construct analogous discrete Poincare operators acting on cochains and Whitney forms. We provide explicit, constructive realizations of these operators under various assumptions on the underlying domain or simplicial complex. In particular, we provide simple constructions for the discrete Poincare operators on simplicial complexes which are collapsible and those with underlying domain being star-shaped with respect to a point. We then provide more abstract constructions on simplicial complexes which are discrete contractible and domains which are Lipschitz contractible. We also modify the discrete Poincare operator on star-shaped domains to construct a discrete Bogovskii operator which satisfies the requisite homotopy identity while preserving homogeneous boundary conditions. Applications arise in the construction of discrete scalar and vector potentials and in the discrete wedge product of Discrete Exterior Calculus (DEC).

math.NA↗

arXiv2025

PracMHBench: Re-evaluating Model-Heterogeneous Federated Learning Based on Practical Edge Device Constraints

Federating heterogeneous models on edge devices with diverse resource constraints has been a notable trend in recent years. Compared to traditional federated learning (FL) that assumes an identical model architecture to cooperate, model-heterogeneous FL is more practical and flexible since the model can be customized to satisfy the deployment requirement. Unfortunately, no prior work ever dives into the existing model-heterogeneous FL algorithms under the practical edge device constraints and provides quantitative analysis on various data scenarios and metrics, which motivates us to rethink and re-evaluate this paradigm. In our work, we construct the first system platform \textbf{PracMHBench} to evaluate model-heterogeneous FL on practical constraints of edge devices, where diverse model heterogeneity algorithms are classified and tested on multiple data tasks and metrics. Based on the platform, we perform extensive experiments on these algorithms under the different edge constraints to observe their applicability and the corresponding heterogeneity pattern.

cs.LG↗

arXiv2025

Encapsulated Composition of Text-to-Image and Text-to-Video Models for High-Quality Video Synthesis

In recent years, large text-to-video (T2V) synthesis models have garnered considerable attention for their abilities to generate videos from textual descriptions. However, achieving both high imaging quality and effective motion representation remains a significant challenge for these T2V models. Existing approaches often adapt pre-trained text-to-image (T2I) models to refine video frames, leading to issues such as flickering and artifacts due to inconsistencies across frames. In this paper, we introduce EVS, a training-free Encapsulated Video Synthesizer that composes T2I and T2V models to enhance both visual fidelity and motion smoothness of generated videos. Our approach utilizes a well-trained diffusion-based T2I model to refine low-quality video frames by treating them as out-of-distribution samples, effectively optimizing them with noising and denoising steps. Meanwhile, we employ T2V backbones to ensure consistent motion dynamics. By encapsulating the T2V temporal-only prior into the T2I generation process, EVS successfully leverages the strengths of both types of models, resulting in videos of improved imaging and motion quality. Experimental results validate the effectiveness of our approach compared to previous approaches. Our composition process also leads to a significant improvement of 1.6x-4.5x speedup in inference time. Source codes: https://github.com/Tonniia/EVS.

cs.CV↗

arXiv2025

Understanding Attention Mechanism in Video Diffusion Models

Text-to-video (T2V) synthesis models, such as OpenAI's Sora, have garnered significant attention due to their ability to generate high-quality videos from a text prompt. In diffusion-based T2V models, the attention mechanism is a critical component. However, it remains unclear what intermediate features are learned and how attention blocks in T2V models affect various aspects of video synthesis, such as image quality and temporal consistency. In this paper, we conduct an in-depth perturbation analysis of the spatial and temporal attention blocks of T2V models using an information-theoretic approach. Our results indicate that temporal and spatial attention maps affect not only the timing and layout of the videos but also the complexity of spatiotemporal elements and the aesthetic quality of the synthesized videos. Notably, high-entropy attention maps are often key elements linked to superior video quality, whereas low-entropy attention maps are associated with the video's intra-frame structure. Based on our findings, we propose two novel methods to enhance video quality and enable text-guided video editing. These methods rely entirely on lightweight manipulation of the attention matrices in T2V models. The efficacy and effectiveness of our methods are further validated through experimental evaluation across multiple datasets.

cs.CV↗

arXiv2025

BTFL: A Bayesian-based Test-Time Generalization Method for Internal and External Data Distributions in Federated learning

Federated Learning (FL) enables multiple clients to collaboratively develop a global model while maintaining data privacy. However, online FL deployment faces challenges due to distribution shifts and evolving test samples. Personalized Federated Learning (PFL) tailors the global model to individual client distributions, but struggles with Out-Of-Distribution (OOD) samples during testing, leading to performance degradation. In real-world scenarios, balancing personalization and generalization during online testing is crucial and existing methods primarily focus on training-phase generalization. To address the test-time trade-off, we introduce a new scenario: Test-time Generalization for Internal and External Distributions in Federated Learning (TGFL), which evaluates adaptability under Internal Distribution (IND) and External Distribution (EXD). We propose BTFL, a Bayesian-based test-time generalization method for TGFL, which balances generalization and personalization at the sample level during testing. BTFL employs a two-head architecture to store local and global knowledge, interpolating predictions via a dual-Bayesian framework that considers both historical test data and current sample characteristics with theoretical guarantee and faster speed. Our experiments demonstrate that BTFL achieves improved performance across various datasets and models with less time cost. The source codes are made publicly available at https://github.com/ZhouYuCS/BTFL .

cs.LG↗

arXiv2025

A Separable Self-attention Inspired by the State Space Model for Computer Vision

Mamba is an efficient State Space Model (SSM) with linear computational complexity. Although SSMs are not suitable for handling non-causal data, Vision Mamba (ViM) methods still demonstrate good performance in tasks such as image classification and object detection. Recent studies have shown that there is a rich theoretical connection between state space models and attention variants. We propose a novel separable self attention method, for the first time introducing some excellent design concepts of Mamba into separable self-attention. To ensure a fair comparison with ViMs, we introduce VMINet, a simple yet powerful prototype architecture, constructed solely by stacking our novel attention modules with the most basic down-sampling layers. Notably, VMINet differs significantly from the conventional Transformer architecture. Our experiments demonstrate that VMINet has achieved competitive results on image classification and high-resolution dense prediction tasks.Code is available at: https://github.com/yws-wxs/VMINet.

cs.CV↗

arXiv2024

Multimodal Diffusion Transformer with Memory Bank for Scalable Long-Duration Talking Video Generation

Long-duration talking video synthesis faces enduring challenges in achieving high video quality, portrait consistency, temporal coherence, and computational efficiency. As video length increases, issues such as visual degradation, portrait drift, temporal artifacts, and error accumulation become increasingly problematic, severely affecting the realism and reliability of the results. To address these challenges, we present LetsTalk, a diffusion transformer framework equipped with multimodal guidance and a novel memory bank mechanism, explicitly maintaining contextual continuity and enabling robust, high-quality, and efficient generation of long-duration talking videos. In particular, LetsTalk introduces a noise-regularized memory bank to alleviate error accumulation and sampling artifacts during extended video generation. To further improve efficiency and spatiotemporal modeling, LetsTalk employs a deep compression autoencoder and a spatiotemporal-aware transformer with linear attention for effective multimodal fusion. We systematically analyze three fusion schemes and show that combining deep (Symbiotic Fusion) for portrait features and shallow (Direct Fusion) for audio achieves superior visual realism and precise speech-driven motion, while preserving diversity of movements. Extensive experiments demonstrate that LetsTalk establishes new state-of-the-art in generation quality, producing temporally coherent and realistic talking videos with enhanced diversity and liveliness, and maintains remarkable efficiency with 8x fewer parameters than previous approaches.

cs.CV↗

arXiv2024

Slow, Nanometer Light Confinement Observed in Atomically Thin TaS2

Extreme light confinement down to the atomic scale has been theoretically predicted for ultrathin, Ta-based transition metal dichalcogenides (TMDs). In this work, we experimentally demonstrate in 2H-TaS$_2$ monolayers and bilayers a lateral confinement ratio up to 300 at large wave vectors of $q = 0.15 \, \r{A}^{-1}$, and slow light behaviour with a group velocity $\sim 10^{-4}c$. Quantitative momentum-resolved electron energy loss spectroscopy (q-EELS) with a momentum resolution of $0.0056 \, \r{A}^{-1}$ was used as a platform for the nanoscale optical measurements. With it, momentum-dispersed, two-dimensional (2D) plasmon resonances were experimentally observed, showing a transition from 2D to 3D Coulomb interaction in the high-momentum regime, equivalent to light confinement volumes of $1\text{-}2 \, \text{nm}^3$. Remarkably, the resonant modes do not enter the electron-hole continuum, predicting even further enhanced optical field confinements for this material at cryogenic temperatures.

cond-mat.mtrl-sci↗

arXiv2024

An Information Geometry Interpretation for Approximate Message Passing

In this paper, we propose an information geometry (IG) framework to solve the standard linear regression problem. The proposed framework is an extension of the one for computing the mean of complex multivariate Gaussian distribution. By applying the proposed framework, the information geometry approach (IGA) and the approximate information geometry approach (AIGA) for basis pursuit de-noising (BPDN) in standard linear regression are derived. The framework can also be applied to other standard linear regression problems. With the transformations of natural and expectation parameters of Gaussian distributions, we then show the relationship between the IGA and the message passing (MP) algorithm. Finally, we prove that the AIGA is equivalent to the approximate message passing (AMP) algorithm. These intrinsic results offer a new perspective for the AMP algorithm, and clues for understanding and improving stochastic reasoning methods.

cs.IT↗

arXiv2024

Interference Cancellation Information Geometry Approach for Massive MIMO Channel Estimation

In this paper, the interference cancellation information geometry approaches (IC-IGAs) for massive MIMO channel estimation are proposed. The proposed algorithms are low-complexity approximations of the minimum mean square error (MMSE) estimation. To illustrate the proposed algorithms, a unified framework of the information geometry approach for channel estimation and its geometric explanation are described first. Then, a modified form that has the same mean as the MMSE estimation is constructed. Based on this, the IC-IGA algorithm and the interference cancellation simplified information geometry approach (IC-SIGA) are derived by applying the information geometry framework. The a posteriori means on the equilibrium of the proposed algorithms are proved to be equal to the mean of MMSE estimation, and the complexity of the IC-SIGA algorithm in practical massive MIMO systems is further reduced by considering the beam-based statistical channel model (BSCM) and fast Fourier transform (FFT). Simulation results show that the proposed methods achieve similar performance as the existing information geometry approach (IGA) with lower complexity.

cs.IT↗

arXiv2024

Vim-F: Visual State Space Model Benefiting from Learning in the Frequency Domain

In recent years, State Space Models (SSMs) with efficient hardware-aware designs, known as the Mamba deep learning models, have made significant progress in modeling long sequences such as language understanding. Therefore, building efficient and general-purpose visual backbones based on SSMs is a promising direction. Compared to traditional convolutional neural networks (CNNs) and Vision Transformers (ViTs), the performance of Vision Mamba (ViM) methods is not yet fully competitive. To enable SSMs to process image data, ViMs typically flatten 2D images into 1D sequences, inevitably ignoring some 2D local dependencies, thereby weakening the model's ability to interpret spatial relationships from a global perspective. We use Fast Fourier Transform (FFT) to obtain the spectrum of the feature map and add it to the original feature map, enabling ViM to model a unified visual representation in both frequency and spatial domains. The introduction of frequency domain information enables ViM to have a global receptive field during scanning. We propose a novel model called Vim-F, which employs pure Mamba encoders and scans in both the frequency and spatial domains. Moreover, we question the necessity of position embedding in ViM and remove it accordingly in Vim-F, which helps to fully utilize the efficient long-sequence modeling capability of ViM. Finally, we redesign a patch embedding for Vim-F, leveraging a convolutional stem to capture more local correlations, further improving the performance of Vim-F. Code is available at: https://github.com/yws-wxs/Vim-F.

cs.CV↗

arXiv2024

Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing

Deep Text-to-Image Synthesis (TIS) models such as Stable Diffusion have recently gained significant popularity for creative Text-to-image generation. Yet, for domain-specific scenarios, tuning-free Text-guided Image Editing (TIE) is of greater importance for application developers, which modify objects or object properties in images by manipulating feature components in attention layers during the generation process. However, little is known about what semantic meanings these attention layers have learned and which parts of the attention maps contribute to the success of image editing. In this paper, we conduct an in-depth probing analysis and demonstrate that cross-attention maps in Stable Diffusion often contain object attribution information that can result in editing failures. In contrast, self-attention maps play a crucial role in preserving the geometric and shape details of the source image during the transformation to the target image. Our analysis offers valuable insights into understanding cross and self-attention maps in diffusion models. Moreover, based on our findings, we simplify popular image editing methods and propose a more straightforward yet more stable and efficient tuning-free procedure that only modifies self-attention maps of the specified attention layers during the denoising process. Experimental results show that our simplified method consistently surpasses the performance of popular approaches on multiple datasets.

cs.CV↗

arXiv2023

BeautifulPrompt: Towards Automatic Prompt Engineering for Text-to-Image Synthesis

Recently, diffusion-based deep generative models (e.g., Stable Diffusion) have shown impressive results in text-to-image synthesis. However, current text-to-image models often require multiple passes of prompt engineering by humans in order to produce satisfactory results for real-world applications. We propose BeautifulPrompt, a deep generative model to produce high-quality prompts from very simple raw descriptions, which enables diffusion-based models to generate more beautiful images. In our work, we first fine-tuned the BeautifulPrompt model over low-quality and high-quality collecting prompt pairs. Then, to ensure that our generated prompts can generate more beautiful images, we further propose a Reinforcement Learning with Visual AI Feedback technique to fine-tune our model to maximize the reward values of the generated prompts, where the reward values are calculated based on the PickScore and the Aesthetic Scores. Our results demonstrate that learning from visual AI feedback promises the potential to improve the quality of generated prompts and images significantly. We further showcase the integration of BeautifulPrompt to a cloud-native AI platform to provide better text-to-image generation service in the cloud.

cs.CL↗

arXiv2023

No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML

On-device ML introduces new security challenges: DNN models become white-box accessible to device users. Based on white-box information, adversaries can conduct effective model stealing (MS) and membership inference attack (MIA). Using Trusted Execution Environments (TEEs) to shield on-device DNN models aims to downgrade (easy) white-box attacks to (harder) black-box attacks. However, one major shortcoming is the sharply increased latency (up to 50X). To accelerate TEE-shield DNN computation with GPUs, researchers proposed several model partition techniques. These solutions, referred to as TEE-Shielded DNN Partition (TSDP), partition a DNN model into two parts, offloading the privacy-insensitive part to the GPU while shielding the privacy-sensitive part within the TEE. This paper benchmarks existing TSDP solutions using both MS and MIA across a variety of DNN models, datasets, and metrics. We show important findings that existing TSDP solutions are vulnerable to privacy-stealing attacks and are not as safe as commonly believed. We also unveil the inherent difficulty in deciding optimal DNN partition configurations (i.e., the highest security with minimal utility cost) for present TSDP solutions. The experiments show that such ``sweet spot'' configurations vary across datasets and models. Based on lessons harvested from the experiments, we present TEESlice, a novel TSDP method that defends against MS and MIA during DNN inference. TEESlice follows a partition-before-training strategy, which allows for accurate separation between privacy-related weights from public weights. TEESlice delivers the same security protection as shielding the entire DNN model inside TEE (the ``upper-bound'' security guarantees) with over 10X less overhead (in both experimental and real-world environments) than prior TSDP solutions and no accuracy loss.

cs.CR↗

arXiv2023

PAI-Diffusion: Constructing and Serving a Family of Open Chinese Diffusion Models for Text-to-image Synthesis on the Cloud

Text-to-image synthesis for the Chinese language poses unique challenges due to its large vocabulary size, and intricate character relationships. While existing diffusion models have shown promise in generating images from textual descriptions, they often neglect domain-specific contexts and lack robustness in handling the Chinese language. This paper introduces PAI-Diffusion, a comprehensive framework that addresses these limitations. PAI-Diffusion incorporates both general and domain-specific Chinese diffusion models, enabling the generation of contextually relevant images. It explores the potential of using LoRA and ControlNet for fine-grained image style transfer and image editing, empowering users with enhanced control over image generation. Moreover, PAI-Diffusion seamlessly integrates with Alibaba Cloud's Machine Learning Platform for AI, providing accessible and scalable solutions. All the Chinese diffusion model checkpoints, LoRAs, and ControlNets, including domain-specific ones, are publicly available. A user-friendly Chinese WebUI and the diffusers-api elastic inference toolkit, also open-sourced, further facilitate the easy deployment of PAI-Diffusion models in various environments, making it a valuable resource for Chinese text-to-image synthesis.

cs.CL↗