arXiv subjects

Sheng Liu

Publications and source records attributed to Sheng Liu.

At least 55 records · Page 3Linked to original sources

arXiv2026

Practical continuous-variable quantum key distribution using dynamic digital signal processing: security proof and experimental demonstration

Digital signal processing technology has paved the way for the realization of high-speed continuous-variable quantum key distribution systems. However, existing security proofs are limited to static digital signal processing algorithms, while practical systems rely on dynamic multiple-input multiple-output algorithms to compensate for time-varying channel impairments. Our analysis reveals that the conventional dynamic algorithm, due to its non-unitary nature, systematically underestimates the excess noise, which in turn leads to security issues and the generation of insecure keys. To close this gap, we propose a secure algorithm model, mapping the dynamic algorithm to an equivalent physical optical model whose security can be rigorously assessed. Simulations illustrate the algorithm's non-unitary property and provide a quantitative analysis of the excess noise underestimation caused by the conventional algorithm. We further experimentally validate the necessity of the proposed modeling for dynamic digital signal processing, achieving a secret key rate of 14.4 Mbps based on estimated excess noise of 0.07 shot noise unit; whereas the conventional algorithm would have dangerously overestimated the key rate to 28.2 Mbps with noise of 0.008 shot noise unit. This work provides the essential security framework for dynamic digital signal processing, overcoming a critical impediment for the development of high-performance continuous-variable quantum key distribution systems.

quant-ph↗

arXiv2026

Generalizable Geometric Prior and Recurrent Spiking Feature Learning for Humanoid Robot Manipulation

Humanoid robot manipulation is a crucial research area for executing diverse human-level tasks, involving high-level semantic reasoning and low-level action generation. However, precise scene understanding and sample-efficient learning from human demonstrations remain critical challenges, severely hindering the applicability and generalizability of existing frameworks. This paper presents a novel RGMP-S, Recurrent Geometric-prior Multimodal Policy with Spiking features, facilitating both high-level skill reasoning and data-efficient motion synthesis. To ground high-level reasoning in physical reality, we leverage lightweight 2D geometric inductive biases to enable precise 3D scene understanding within the vision-language model. Specifically, we construct a Long-horizon Geometric Prior Skill Selector that effectively aligns the semantic instructions with spatial constraints, ultimately achieving robust generalization in unseen environments. For the data efficiency issue in robotic action generation, we introduce a Recursive Adaptive Spiking Network. We parameterize robot-object interactions via recursive spiking for spatiotemporal consistency, fully distilling long-horizon dynamic features while mitigating the overfitting issue in sparse demonstration scenarios. Extensive experiments are conducted across the Maniskill simulation benchmark and three heterogeneous real-world robotic systems, encompassing a custom-developed humanoid, a desktop manipulator, and a commercial robotic platform. Empirical results substantiate the superiority of our method over state-of-the-art baselines and validate the efficacy of the proposed modules in diverse generalization scenarios. To facilitate reproducibility, the source code and video demonstrations are publicly available at https://github.com/xtli12/RGMP-S.git.

cs.RO↗

arXiv2026

Anisotropic Kinetics of Ion-Irradiation-Induced Phase Transition in Gallium Oxide

Radiation-tolerant semiconductors have traditionally been engineered by the principle of suppressing defect accumulation and amorphization, based on the assumption that radiation damage is inherently stochastic. Here we show that, in monoclinic $β$-\ce{Ga2O3}, a promising ultrawide-bandgap semiconductor, surface crystallographic orientation deterministically governs radiation tolerance through highly anisotropic kinetics of the $β$-to-$γ$ phase transition. Using machine-learning molecular dynamics coupled with a local configurational-entropy descriptor, we quantitatively map anisotropic $β$-to-$γ$ transition kinetics, showing that the critical dose, transition-layer depth, and kinetic stability of the $γ$-phase are fundamentally governed by surface orientation. Under ion irradiation, non-channeling surfaces such as (100), (001), and (-201) undergo severe surface amorphization, whereas the strongly channeling (010) surface resists damage accumulation and promotes subsurface $γ$-phase nucleation. During thermal annealing recovery process, these initial states follow two distinct recovery pathways: the channeling (010) surface reverts directly from $γ$-to-$β$, whereas non-channeling surfaces follow a sequential amorphous-to-$γ$-to-$β$ transition pathway. This work establishes surface orientation as a fundamental design principle for achieving radiation tolerance through controlled polymorphic transitions, providing a universal framework for engineering functional materials capable of withstanding extreme irradiation environments.

cond-mat.mtrl-sci↗

arXiv2025

Data-regularized Reinforcement Learning for Diffusion Models at Scale

Aligning generative diffusion models with human preferences via reinforcement learning (RL) is critical yet challenging. Most existing algorithms are often vulnerable to reward hacking, such as quality degradation, over-stylization, or reduced diversity. Our analysis demonstrates that this can be attributed to the inherent limitations of their regularization, which provides unreliable penalties. We introduce Data-regularized Diffusion Reinforcement Learning (DDRL), a novel framework that uses the forward KL divergence to anchor the policy to an off-policy data distribution. Theoretically, DDRL enables robust, unbiased integration of RL with standard diffusion training. Empirically, this translates into a simple yet effective algorithm that combines reward maximization with diffusion loss minimization. With over a million GPU hours of experiments and ten thousand double-blind human evaluations, we demonstrate on high-resolution video generation tasks that DDRL significantly improves rewards while alleviating the reward hacking seen in baselines, achieving the highest human preference and establishing a robust and scalable paradigm for diffusion post-training.

cs.LG↗

arXiv2025

Discovering Influential Factors in Variational Autoencoders

In the field of machine learning, it is still a critical issue to identify and supervise the learned representation without manually intervening or intuition assistance to extract useful knowledge or serve for the downstream tasks. In this work, we focus on supervising the influential factors extracted by the variational autoencoder(VAE). The VAE is proposed to learn independent low dimension representation while facing the problem that sometimes pre-set factors are ignored. We argue that the mutual information of the input and each learned factor of the representation plays a necessary indicator of discovering the influential factors. We find the VAE objective inclines to induce mutual information sparsity in factor dimension over the data intrinsic dimension and therefore result in some non-influential factors whose function on data reconstruction could be ignored. We show mutual information also influences the lower bound of the VAE's reconstruction error and downstream classification task. To make such indicator applicable, we design an algorithm for calculating the mutual information for the VAE and prove its consistency. Experimental results on MNIST, CelebA and DEAP datasets show that mutual information can help determine influential factors, of which some are interpretable and can be used to further generation and classification tasks, and help discover the variant that connects with emotion on DEAP dataset.

cs.LG↗

arXiv2025

DEFEND: Poisoned Model Detection and Malicious Client Exclusion Mechanism for Secure Federated Learning-based Road Condition Classification

Federated Learning (FL) has drawn the attention of the Intelligent Transportation Systems (ITS) community. FL can train various models for ITS tasks, notably camera-based Road Condition Classification (RCC), in a privacy-preserving collaborative way. However, opening up to collaboration also opens FL-based RCC systems to adversaries, i.e., misbehaving participants that can launch Targeted Label-Flipping Attacks (TLFAs) and threaten transportation safety. Adversaries mounting TLFAs poison training data to misguide model predictions, from an actual source class (e.g., wet road) to a wrongly perceived target class (e.g., dry road). Existing countermeasures against poisoning attacks cannot maintain model performance under TLFAs close to the performance level in attack-free scenarios, because they lack specific model misbehavior detection for TLFAs and neglect client exclusion after the detection. To close this research gap, we propose DEFEND, which includes a poisoned model detection strategy that leverages neuron-wise magnitude analysis for attack goal identification and Gaussian Mixture Model (GMM)-based clustering. DEFEND discards poisoned model contributions in each round and adapts accordingly client ratings, eventually excluding malicious clients. Extensive evaluation involving various FL-RCC models and tasks shows that DEFEND can thwart TLFAs and outperform seven baseline countermeasures, with at least 15.78% improvement, with DEFEND remarkably achieving under attack the same performance as in attack-free scenarios.

cs.CR↗

arXiv2025

SRAM: Shape-Realism Alignment Metric for No Reference 3D Shape Evaluation

3D generation and reconstruction techniques have been widely used in computer games, film, and other content creation areas. As the application grows, there is a growing demand for 3D shapes that look truly realistic. Traditional evaluation methods rely on a ground truth to measure mesh fidelity. However, in many practical cases, a shape's realism does not depend on having a ground truth reference. In this work, we propose a Shape-Realism Alignment Metric that leverages a large language model (LLM) as a bridge between mesh shape information and realism evaluation. To achieve this, we adopt a mesh encoding approach that converts 3D shapes into the language token space. A dedicated realism decoder is designed to align the language model's output with human perception of realism. Additionally, we introduce a new dataset, RealismGrading, which provides human-annotated realism scores without the need for ground truth shapes. Our dataset includes shapes generated by 16 different algorithms on over a dozen objects, making it more representative of practical 3D shape distributions. We validate our metric's performance and generalizability through k-fold cross-validation across different objects. Experimental results show that our metric correlates well with human perceptions and outperforms existing methods, and has good generalizability.

cs.CV↗

arXiv2025

Textured Geometry Evaluation: Perceptual 3D Textured Shape Metric via 3D Latent-Geometry Network

Textured high-fidelity 3D models are crucial for games, AR/VR, and film, but human-aligned evaluation methods still fall behind despite recent advances in 3D reconstruction and generation. Existing metrics, such as Chamfer Distance, often fail to align with how humans evaluate the fidelity of 3D shapes. Recent learning-based metrics attempt to improve this by relying on rendered images and 2D image quality metrics. However, these approaches face limitations due to incomplete structural coverage and sensitivity to viewpoint choices. Moreover, most methods are trained on synthetic distortions, which differ significantly from real-world distortions, resulting in a domain gap. To address these challenges, we propose a new fidelity evaluation method that is based directly on 3D meshes with texture, without relying on rendering. Our method, named Textured Geometry Evaluation TGE, jointly uses the geometry and color information to calculate the fidelity of the input textured mesh with comparison to a reference colored shape. To train and evaluate our metric, we design a human-annotated dataset with real-world distortions. Experiments show that TGE outperforms rendering-based and geometry-only methods on real-world distortion dataset.

cs.CV↗

arXiv2025

FORGE-Tree: Diffusion-Forcing Tree Search for Long-Horizon Robot Manipulation

Long-horizon robot manipulation tasks remain challenging for Vision-Language-Action (VLA) policies due to drift and exposure bias, often denoise the entire trajectory with fixed hyperparameters, causing small geometric errors to compound across stages and offering no mechanism to allocate extra test-time compute where clearances are tight. To address these challenges, we introduce FORGE-Tree, a plug-in control layer that couples a stage-aligned Diffusion Forcing (DF) head with test-time Monte Carlo Tree Diffusion (MCTD). With a frozen VLA encoder, DF aligns timesteps to subtask stages; during inference we partially denoise only a target segment while keeping other tokens frozen, turning trajectory refinement into a sequence of local edits. We then apply Monte Carlo Tree Diffusion to select the next segment to refine. A scene graph supplies priors for expansion and geometry relation-aware scoring for rollouts, yielding tree-structured denoising whose performance scales with search budget while preserving the executed prefix. Evaluation on LIBERO, FORGE-Tree improves success rate by 13.4 to 17.2 pp over the native VLA baselines with both OpenVLA and Octo-Base. Gains remain consistent under comparable compute budgets, especially on long-horizon variants. Videos available at: https://taco-group.github.io/FORGE-Tree/

cs.RO↗

arXiv2025

Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute

Test-time compute has emerged as a powerful paradigm for improving the performance of large language models (LLMs), where generating multiple outputs or refining individual chains can significantly boost answer accuracy. However, existing methods like Best-of-N, majority voting, and self-reflection typically apply reasoning in a uniform way across inputs, overlooking the fact that different problems may require different levels of reasoning depth. In this work, we propose Fractional Reasoning, a training-free and model-agnostic framework that enables continuous control over reasoning intensity at inference time, going beyond the limitations of fixed instructional prompts. Our method operates by extracting the latent steering vector associated with deeper reasoning and reapplying it with a tunable scaling factor, allowing the model to tailor its reasoning process to the complexity of each input. This supports two key modes of test-time scaling: (1) improving output quality in breadth-based strategies (e.g., Best-of-N, majority voting), and (2) enhancing the correctness of individual reasoning chains in depth-based strategies (e.g., self-reflection). Experiments on GSM8K, MATH500, and GPQA demonstrate that Fractional Reasoning consistently improves performance across diverse reasoning tasks and models.

cs.LG↗

arXiv2025

DAOpt: Modeling and Evaluation of Data-Driven Optimization under Uncertainty with LLMs

Recent advances in large language models (LLMs) have accelerated research on automated optimization modeling. While real-world decision-making is inherently uncertain, most existing work has focused on deterministic optimization with known parameters, leaving the application of LLMs in uncertain settings largely unexplored. To that end, we propose the DAOpt framework including a new dataset OptU, a multi-agent decision-making module, and a simulation environment for evaluating LLMs with a focus on out-of-sample feasibility and robustness. Additionally, we enhance LLMs' modeling capabilities by incorporating few-shot learning with domain knowledge from stochastic and robust optimization.

cs.LG↗

arXiv2025

Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks

Despite advances in improving large language model (LLM) to refuse to answer malicious instructions, widely used LLMs remain vulnerable to jailbreak attacks where attackers generate instructions with distributions differing from safety alignment corpora. New attacks expose LLMs' inability to recognize unseen malicious instructions, highlighting a critical distributional mismatch between training data and real-world attacks that forces developers into reactive patching cycles. To tackle this challenge, we propose IMAGINE, a synthesis framework that leverages embedding space distribution analysis to generate jailbreak-like instructions. This approach effectively fills the distributional gap between authentic jailbreak patterns and safety alignment corpora. IMAGINE follows an iterative optimization process that dynamically evolves text generation distributions across iterations, thereby augmenting the coverage of safety alignment data distributions through synthesized data examples. Based on the safety-aligned corpus enhanced through IMAGINE, our framework demonstrates significant decreases in attack success rate on Qwen2.5, Llama3.1, and Llama3.2 without compromising their utility.

cs.CL↗

arXiv2025

Topological resilience of optical skyrmions in local decoherence

The topologically protected configuration embedded in skyrmions has prompted some investigations into their fundamental properties and versatile applications, sparking interest and guiding ongoing development. The topological protection associated with skyrmions was initially observed in systems with interactions. It is widely believed that skyrmions are stable yet relevant confirmation and empirical research remain limited. A pertinent question is whether skyrmion configurations formed by a single classical beam with two coupled degrees of freedom also exhibit topological stability. In this study, we affirm this hypothesis by investigating the effects of local decoherence. We analytically and numerically demonstrate the topological resilience of skyrmions and the occurrence of transition points of skyrmion numbers in local decoherence across three typical decoherence channels. On the other hand, we show that these qualities are independent of the initial state. From the numerical results, we find that inhomogeneous but continuous decoherence channels also have the same behaviors and maintain topological stability of skyrmions as homogeneous decoherence channels do. These properties of skyrmions contribute to further applications in various areas, including communication and imaging.

physics.optics↗

arXiv2025

Revealing Neurocognitive and Behavioral Patterns by Unsupervised Manifold Learning from Dynamic Brain Data

Dynamic brain data, teeming with biological and functional insights, are becoming increasingly accessible through advanced measurements, providing a gateway to understanding the inner workings of the brain in living subjects. However, the vast size and intricate complexity of the data also pose a daunting challenge in reliably extracting meaningful information across various data sources. This paper introduces a generalizable unsupervised deep manifold learning for exploration of neurocognitive and behavioral patterns. Unlike existing methods that extract patterns directly from the input data as in the existing methods, the proposed Brain-dynamic Convolutional-Network-based Embedding (BCNE) seeks to capture the brain-state trajectories by deciphering the temporospatial correlations within the data and subsequently applying manifold learning to this correlative representation. The performance of BCNE is showcased through the analysis of several important dynamic brain datasets. The results, both visual and quantitative, reveal a diverse array of intriguing and interpretable patterns. BCNE effectively delineates scene transitions, underscores the involvement of different brain regions in memory and narrative processing, distinguishes various stages of dynamic learning processes, and identifies differences between active and passive behaviors. BCNE provides an effective tool for exploring general neuroscience inquiries or individual-specific patterns.

q-bio.NC↗

arXiv2025

VISO-Grasp: Vision-Language Informed Spatial Object-centric 6-DoF Active View Planning and Grasping in Clutter and Invisibility

We propose VISO-Grasp, a novel vision-language-informed system designed to systematically address visibility constraints for grasping in severely occluded environments. By leveraging Foundation Models (FMs) for spatial reasoning and active view planning, our framework constructs and updates an instance-centric representation of spatial relationships, enhancing grasp success under challenging occlusions. Furthermore, this representation facilitates active Next-Best-View (NBV) planning and optimizes sequential grasping strategies when direct grasping is infeasible. Additionally, we introduce a multi-view uncertainty-driven grasp fusion mechanism that refines grasp confidence and directional uncertainty in real-time, ensuring robust and stable grasp execution. Extensive real-world experiments demonstrate that VISO-Grasp achieves a success rate of $87.5\%$ in target-oriented grasping with the fewest grasp attempts outperforming baselines. To the best of our knowledge, VISO-Grasp is the first unified framework integrating FMs into target-aware active view planning and 6-DoF grasping in environments with severe occlusions and entire invisibility constraints. Code is available at: https://github.com/YitianShi/vMF-Contact

cs.RO↗

arXiv2025

Spin light-emitting devices in a 2D magnet

Emerging two-dimensional (2D) magnetic semiconductors represent transformative platforms to explore magneto-optics and opto-spintronic applications. Though 2D opto-spintronics has attracted tremendous research efforts in spin-dependent photodetectors and non-volatile memory components, the realization of one core application - spin-modulated light-emitting device (spin-LED) - remains elusive so far. Here we successfully realize prototype spin-LED integrated with a 2D semiconducting magnet CrSBr, demonstrating considerable electroluminescence (EL) down to bilayers. Intriguingly, the EL of the spin-LED is discovered to be directly manipulated by spin-flip and spin-canting transitions. Notably, spin-flip transitions enable unprecedented hysteretic behaviors of EL characteristics, while spin-canting transitions induce EL continuous modulation with robust anisotropy. This versatile manipulation is originated from the synergy of magnetic-order mediated excitonic transitions and spintronic transport. The prototype demonstration of spin-LED establishes an indispensable scheme of opto-spintronic devices leveraging 2D spin transitions and strong excitonic effects, presenting a critical step towards integrated 2D opto-spintronics.

physics.app-ph↗

arXiv2025

Safeguarding Federated Learning-based Road Condition Classification

Federated Learning (FL) has emerged as a promising solution for privacy-preserving autonomous driving, specifically camera-based Road Condition Classification (RCC) systems, harnessing distributed sensing, computing, and communication resources on board vehicles without sharing sensitive image data. However, the collaborative nature of FL-RCC frameworks introduces new vulnerabilities: Targeted Label Flipping Attacks (TLFAs), in which malicious clients (vehicles) deliberately alter their training data labels to compromise the learned model inference performance. Such attacks can, e.g., cause a vehicle to mis-classify slippery, dangerous road conditions as pristine and exceed recommended speed. However, TLFAs for FL-based RCC systems are largely missing. We address this challenge with a threefold contribution: 1) we disclose the vulnerability of existing FL-RCC systems to TLFAs; 2) we introduce a novel label-distance-based metric to precisely quantify the safety risks posed by TLFAs; and 3) we propose FLARE, a defensive mechanism leveraging neuron-wise analysis of the output layer to mitigate TLFA effects. Extensive experiments across three RCC tasks, four evaluation metrics, six baselines, and three deep learning models demonstrate both the severity of TLFAs on FL-RCC systems and the effectiveness of FLARE in mitigating the attack impact.

cs.CR↗

arXiv2025

Diffusion Models for Robotic Manipulation: A Survey

Diffusion generative models have demonstrated remarkable success in visual domains such as image and video generation. They have also recently emerged as a promising approach in robotics, especially in robot manipulations. Diffusion models leverage a probabilistic framework, and they stand out with their ability to model multi-modal distributions and their robustness to high-dimensional input and output spaces. This survey provides a comprehensive review of state-of-the-art diffusion models in robotic manipulation, including grasp learning, trajectory planning, and data augmentation. Diffusion models for scene and image augmentation lie at the intersection of robotics and computer vision for vision-based tasks to enhance generalizability and data scarcity. This paper also presents the two main frameworks of diffusion models and their integration with imitation learning and reinforcement learning. In addition, it discusses the common architectures and benchmarks and points out the challenges and advantages of current state-of-the-art diffusion-based methods.

cs.RO↗