arXiv subjects

Xiang Zhang

Publications and source records attributed to Xiang Zhang.

At least 91 records · Page 5Linked to original sources

arXiv2026

DIMoE-Adapters: Dynamic Expert Evolution for Continual Learning in Vision-Language Models

Continual learning enables vision-language models to accumulate knowledge and adapt to evolving tasks without retraining from scratch. However, in multi-domain task-incremental learning, large domain shifts intensify the stability-plasticity dilemma. Most existing methods rely on fixed architectures with statically allocated parameters, which limits adaptation to new domains and aggravates catastrophic forgetting. To address these challenges, we propose DIMoE-Adapters, a Dynamic Incremental Mixture-of-Experts Adapters framework that introduces a dynamic expert evolution paradigm to balance stability and plasticity. This paradigm is implemented through two collaborative components: Self-Calibrated Expert Evolution (SCEE) and Prototype-Guided Expert Selection (PGES). SCEE constructs and evolves a sparse expert pool through expert optimization dynamics, improving plasticity while reducing redundant capacity. PGES controls expert utilization based on the pool shaped by SCEE, improving stability across both previously encountered and unseen tasks. Extensive experiments show that DIMoE-Adapters outperforms previous state-of-the-art methods across various settings.

cs.CV↗

arXiv2026

Hierarchical Dual-Subspace Decoupling for Continual Learning in Vision-Language Models

Class-incremental learning aims to continuously acquire new knowledge while preserving previously learned information, thereby mitigating catastrophic forgetting. Existing methods primarily restrict parameter updates but often overlook their structural properties in high-dimensional spaces. From a subspace perspective, updates induced by different tasks tend to lie in multiple overlapping low-rank subspaces, leading to cross-task subspace interference and severe forgetting. To address this issue, we propose HDSD, a Hierarchical Dual-Subspace Decoupling framework for continual learning in vision-language models. Specifically, we introduce a lightweight Feature Modulation Module (FMM) that explicitly decomposes the parameter space into general and task-specific subspaces. Building on this design, we develop two complementary components. First, a General Fusion Module (GFM) evaluates relative parameter changes across tasks and uses an adaptive threshold to capture stable and transferable knowledge. Second, a Hierarchical Learning Module (HLM) performs structured parameter decomposition via Singular Value Decomposition (SVD) and uses a scaling mechanism to constrain updates within distinct subspace scales. Together, these designs reduce subspace interference and parameter drift. Extensive experiments on conventional benchmarks show that HDSD achieves state-of-the-art results.

cs.CV↗

arXiv2026

Hollow-Core Fiber for Long-Span Optical Frequency Transfer: Improved Instability and Extended Single-Span Reach

Phase-coherent optical frequency transfer is essential for optical clock networking, relativistic geodesy, and distributed precision metrology. However, realizing coherent optical networks spanning thousands of kilometers in standard single-mode fiber (SMF) generally requires densely distributed amplifiers or repeater stations together with complex operational control, while long-term instability remains limited by thermally driven residual phase fluctuations. Here we show that hollow-core fiber (HCF) can simultaneously improve transfer instability and relax the reach limitation of long-span optical frequency transfer. Compared with SMF, HCF exhibits lower fiber-induced phase noise and shorter propagation delay, supporting improved short-term instability, while its much lower thermal sensitivity supports nearly one-order-of-magnitude better long-term instability. In addition, for long-haul HCF links, no observable stimulated Brillouin scattering induced saturation is found up to the maximum available injected power of 34 dBm, whereas the threshold of an equal-length SMF link remains only a few dBm. Together with the lower attenuation achievable in modern HCF, this enables ultra-long single-span optical frequency transfer. Using a 152 km HCF link with an average attenuation of 0.18 dB/km, we demonstrate single-span optical frequency transfer, achieving a fractional frequency instability of 7.3 x 10^-21 at 10,000 s and a fractional uncertainty of 1.8 x 10^-20. These results establish HCF as a transmission medium that simultaneously improves instability and extends single-span reach, opening a practical route toward future intercontinental optical frequency networks with ultrahigh precision.

physics.optics↗

arXiv2026

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning

In single-stream autoregressive interfaces, the same tokens both update the model state and constitute an irreversible public commitment. This coupling creates a silence tax: additional deliberation postpones the first task-relevant content, while naive early streaming risks premature commitments that bias subsequent generations. We introduce Side-by-Side (SxS) Interleaved Reasoning, which makes disclosure timing a controllable decision within standard autoregressive generation. SxS interleaves partial disclosures with continued private reasoning in the same context, but releases content only when it is supported by the reasoning so far. To learn such pacing without incentivizing filler, we construct entailment-aligned interleaved trajectories by matching answer prefixes to supporting reasoning prefixes, then train with SFT to acquire the dual-action semantics and RL to recover reasoning performance under the new format. Across two Qwen3 architectures/scales (MoE Qwen3-30B-A3B, dense Qwen3-4B) and both in-domain (AIME25) and out-of-domain (GPQA-Diamond) benchmarks, SxS improves accuracy--content-latency Pareto trade-offs under token-level proxies such as inter-update waiting.

cs.CL↗

arXiv2026

Optimal Communication Rate of Secure Aggregation over Ring Networks with Pairwise Keys

Information-theoretic topological secure aggregation (TSA)\cite{zhang2026information_regular} enables distributed users to compute neighborhood sums over arbitrary networks without revealing individual inputs, while remaining communication-efficient. It has broad applications, including secure model aggregation in decentralized federated learning (FL). Existing TSA formulations rely on arbitrarily correlated keys generated by a trusted key server, which introduces a single point of failure. In this paper, we instead study TSA with \tit{pairwise} secret keys, where each user pair $(i,j)$ shares an independent key $S_{i,j}$. Such keys can be established through inter-user communication, eliminating the need for a key server and improving robustness. Focusing on a ring topology with $K$ users, we characterize the minimum per-user communication rate: \tit{to securely compute one bit of the desired input sum, each user must send at least $1$ bit to its neighbors when $K=3,4$, and at least $2$ bits for all $K\ge 5$}. The higher rate in larger networks arises because each user must simultaneously satisfy two independent key-alignment constraints from its two neighborhoods, which cannot be resolved within a single broadcast symbol under pairwise key independence. We propose a linear pairwise-masking scheme that achieves these rates and prove its optimality via tight entropic converse bounds that exploit the dependency structure of the keys. Notably, for all $K\ge 4$, only a subset of the $\binom{K}{2}$ pairwise keys -- specifically, those between users at ring distance $2$ -- is sufficient to achieve optimality, revealing a nontrivial role of topological sparsity in secure aggregation.

cs.IT↗

arXiv2026

Breaking the Resolution Barrier: Arbitrary-resolution Deep Image Steganography Framework

Deep image steganography (DIS) has achieved significant results in capacity and invisibility. However, current paradigms enforce the secret image to maintain the same resolution as the cover image during hiding and revealing. This leads to two challenges: secret images with inconsistent resolutions must undergo resampling beforehand which results in detail loss during recovery, and the secret image cannot be recovered to its original resolution when the resolution value is unknown. To address these, we propose ARDIS, the first Arbitrary Resolution DIS framework, which shifts the paradigm from discrete mapping to reference-guided continuous signal reconstruction. Specifically, to minimize the detail loss caused by resolution mismatch, we first design a Frequency Decoupling Architecture in hiding stage. It disentangles the secret into a resolution-aligned global basis and a resolution-agnostic high-frequency latent to hide in a fixed-resolution cover. Second, for recovery, we propose a Latent-Guided Implicit Reconstructor to perform deterministic restoration. The recovered detail latent code modulates a continuous implicit function to accurately query and render high-frequency residuals onto the recovered global basis, ensuring faithful restoration of original details. Furthermore, to achieve blind recovery, we introduce an Implicit Resolution Coding strategy. By transforming discrete resolution values into dense feature maps and hiding them in the redundant space of the feature domain, the reconstructor can correctly decode the secret's resolution directly from the steganographic representation. Experimental results demonstrate that ARDIS significantly outperforms state-of-the-art methods in both invisibility and cross-resolution recovery fidelity.

cs.CV↗

arXiv2026

Fractional topology and multi-period re-quantization in open quantum systems

We study fractional topological numbers in open quantum systems described by the Gorin--Kossakowski--Sudarsha--Lindblad master equation. Under symmetry conditions ensuring quantization, we show that single-valued physical states in momentum space give rise to integer winding numbers that remain integer during time evolution. Fractional values arise when this condition is effectively relaxed, such that the topology is evaluated over a restricted sector or exhibits an effective multi-branch structure. In these cases, the winding number is not quantized over the fundamental Brillouin zone and can depend continuously on system parameters, with discontinuities at purity-gap closings. However, when extended over multiple momentum periods, the winding recovers integer quantization. These effects are illustrated in a Su--Schrieffer--Heeger chain with gain and loss and can be probed in long-range hopping photonic lattices with fractional fillings via Bloch state tomography. Our results provide a unified framework for understanding fractional topology in open quantum systems.

quant-ph↗

arXiv2026

Cross-Subject Generalization for EEG Decoding: A Survey of Deep Learning Methods

Deep learning for cross-subject EEG decoding is hindered by high inter-subject variability, which introduces a severe domain shift between training and unseen test subjects. This survey presents a comprehensive review of deep learning methodologies specifically engineered to address this cross-subject generalization challenge. To ground this analysis, we formalize the cross-subject setting as a multi-source domain problem and delineate the rigorous, subject-independent evaluation protocols required for valid assessment. Central to this survey is a systematic taxonomy of the current literature into discrete methodological families, including feature alignment, adversarial learning, feature disentanglement, and contrastive learning. We conclude by examining three critical elements for advancing robust, real-world decoding: the theoretical limitations of current methodologies, the structural value of subject identity, and the emergence of EEG foundation models.

cs.LG↗

arXiv2026

Multi-Server Secure Aggregation with Arbitrary Collusion and Heterogeneous Security Constraints

We study the fundamental limits of multi-server secure aggregation over a two-hop network where multiple servers, each connected to a disjoint subset of users, jointly compute the sum of all users' inputs. The goal is to ensure that no server can infer any information about prescribed subsets of inputs beyond the desired aggregate, even when colluding with an arbitrary subset of users. Existing works largely focus on homogeneous security requirements, where all inputs are protected against colluding sets up to a given size. Such formulations are insufficient to capture more general scenarios in which different subsets of inputs may require protection against different collusion patterns. In this paper, we consider a general model with heterogeneous security requirements and arbitrary user collusion. We characterize the communication rates for all parameter regimes, and determine the minimum key rate required for secure aggregation in most regimes. In particular, we establish tight information-theoretic lower bounds and matching achievable schemes in a broad class of regimes. For the remaining regime, we derive a general lower bound together with an achievable scheme that attains it within a bounded gap. Our results reveal how the interplay between network topology and heterogeneous security constraints fundamentally determines the communication and key generation requirements, and generalize existing results on secure aggregation.

cs.IT↗

arXiv2026

Inter-Stance: A Dyadic Multimodal Corpus for Conversational Stance Analysis

Social interactions dominate our perceptions of the world and shape our daily behavior by attaching social meaning to acts as simple and spontaneous as gestures, facial expressions, voice, and speech. People mimic and otherwise respond to each other's postures, facial expressions, mannerisms, and other verbal and nonverbal behavior, and form appraisals or evaluations in the process. Yet, no publicly-available dataset includes multimodal recordings and self-report measures of multiple persons in social interaction. Dyadic recordings and annotation are lacking. We present a new data corpus of multimodal dyadic interaction (45 dyads, 90 persons) that includes synchronized multi-modality behavior (2D face video, 3D face geometry, thermal spectrum dynamics, voice and speech behavior, physiology (PPG, EDA, heart-rate, blood pressure, and respiration), and self-reported affect of all participants in a communicative interaction scenario. Two types of dyads are included: persons with shared past history and strangers. Annotations include social signals, agreement, disagreement, and neutral stance. With a potent emotion induction, these multimodal data will enable novel modeling of multimodal interpersonal behavior. We present extensive experiments to evaluate multimodal dyadic communication of dyads with and without interpersonal history, and their affect. This new database will make multimodal modeling of social interaction never possible before. The dataset includes 20TB of multimodal data to share with the research community.

cs.CV↗

arXiv2026

Robust Localization for Autonomous Vehicles in Highway Scenes

Localization for autonomous vehicles on highways remains under-explored compared to urban roads, and state-of-the-art methods for urban scenes degrade when directly applied to highways. We identify key challenges including environment changes under information homogeneity, heavy occlusion, degraded GNSS signals, and stringent downstream requirements on accuracy and latency. We propose a robust localization system to address highway challenges, which uses a dual-likelihood LiDAR front end that decouples 3D geometric structures and 2D road-texture cues to handle environment changes; a Control-EKF further leverages steering and acceleration commands to reduce lag and improve closed-loop behavior. An automated offline mapping and ground-truth pipeline keep maps fresh at high cadence for optimal localization performance. To catalyze progress, we release a public dataset covering both urban roads and highways while focusing on representative challenging highway clips, totaling 163 km; benchmarking is standardized using product-oriented accuracy metrics and certified ground truth. Compared to Apollo and Autoware, our system performs similarly on urban roads but shows superior robustness on challenging highway scenarios. The system has been validated by more than one million kilometers of road testing.

cs.RO↗

arXiv2026

Spatiotemporal-Aware Bit-Flip Injection on DNN-based Advanced Driver Assistance Systems (extended version)

Modern advanced driver assistance systems (ADAS) rely on deep neural networks (DNNs) for perception and planning. Since DNNs' parameters reside in DRAM during inference, bit flips caused by cosmic radiation or low-voltage operation may corrupt DNN computations, distort driving decisions, and lead to real-world incidents. This paper presents a SpatioTemporal-Aware Fault Injection (STAFI) framework to locate critical fault sites in DNNs for ADAS efficiently. Spatially, we propose a Progressive Metric-guided Bit Search (PMBS) that efficiently identifies critical network weight bits whose corruption causes the largest deviations in driving behavior (e.g., unintended acceleration or steering). Furthermore, we develop a Critical Fault Time Identification (CFTI) mechanism that determines when to trigger these faults, taking into account the context of real-time systems and environmental states, to maximize the safety impact. Experiments on DNNs for a production ADAS demonstrate that STAFI uncovers 29.56x more hazard-inducing critical faults than the strongest baseline.

cs.CR↗

arXiv2026

Benchmarking ERP Analysis: Manual Features, Deep Learning, and Foundation Models

Event-related potential (ERP), a specialized paradigm of electroencephalographic (EEG), reflects neurological responses to external stimuli or events, generally associated with the brain's processing of specific cognitive tasks. ERP plays a critical role in cognitive analysis, the detection of neurological diseases, and the assessment of psychological states. Recent years have seen substantial advances in deep learning-based methods for spontaneous EEG and other non-time-locked task-related EEG signals. However, their effectiveness on ERP data remains underexplored, and many existing ERP studies still rely heavily on manually extracted features. In this paper, we conduct a comprehensive benchmark study that systematically compares traditional manual features (followed by a linear classifier), deep learning models, and pre-trained EEG foundation models for ERP analysis. We establish a unified data preprocessing and training pipeline and evaluate these approaches on two representative tasks, ERP stimulus classification and ERP-based brain disease detection, across 12 publicly available datasets. Furthermore, we investigate various token-embedding strategies within advanced Transformer architectures to identify embedding designs that better suit ERP data. Our study provides a landmark framework to guide method selection and tailored model design for future ERP analysis. The code is available at https://github.com/DL4mHealth/ERP-Benchmark

cs.NE↗

arXiv2026

On Secure Gradient Coding with Uncoded Groupwise Keys

This paper considers a new secure gradient coding problem with uncoded groupwise keys, formalized as a (K, N, N_r, M, S) secure gradient coding model, where a user aims to compute the sum of the gradients from K datasets with the assistance of N distributed servers. We consider arbitrary heterogeneous data assignment, where each dataset is assigned to at least M servers. The user should recover the sum of gradients from the transmissions of any N_r servers. The security constraint guarantees that even if the user receives the transmitted messages from all servers, it cannot obtain any other information about the datasets except the sum of gradients. Compared to existing secure gradient coding works, we introduce a practical constraint on secret keys, namely uncoded groupwise keys, where the keys are mutually independent and each key is shared by precisely S servers. An achievable secure gradient coding scheme with uncoded groupwise keys is proposed, which is then proven to be optimal if S > M and to be order optimal within a factor of 2 otherwise.

cs.IT↗

arXiv2026

PosterGen: Aesthetic-Aware Multi-Modal Paper-to-Poster Generation via Multi-Agent LLMs

Multi-agent systems built upon large language models (LLMs) have demonstrated remarkable capabilities in tackling complex compositional tasks. In this work, we apply this paradigm to the paper-to-poster generation problem, a practical yet time-consuming process faced by researchers preparing for conferences. While recent approaches have attempted to automate this task, most neglect core design and aesthetic principles, resulting in posters that require substantial manual refinement. To address these design limitations, we propose PosterGen, a multi-agent framework that mirrors the workflow of professional poster designers. It consists of four collaborative specialized agents: (1) Parser and Curator agents extract content from the paper and organize storyboard; (2) Layout agent maps the content into a coherent spatial layout; (3) Stylist agents apply visual design elements such as color and typography; and (4) Renderer composes the final poster. Together, these agents produce posters that are both semantically grounded and visually appealing. To evaluate design quality, we introduce a vision-language model (VLM)-based rubric that measures layout balance, readability, and aesthetic coherence. Experimental results show that PosterGen consistently matches in content fidelity, and significantly outperforms existing methods in visual designs, generating posters that are presentation-ready with minimal human refinements.

cs.AI↗

arXiv2026

Generalizable Deepfake Detection Based on Forgery-aware Layer Masking and Multi-artifact Subspace Decomposition

Deepfake detection remains highly challenging, particularly in cross-dataset scenarios and complex real-world settings. This challenge mainly arises because artifact patterns vary substantially across different forgery methods, whereas adapting pretrained models to such artifacts often overemphasizes forgery-specific cues and disturbs semantic representations, thereby weakening generalization. Existing approaches typically rely on full-parameter fine-tuning or auxiliary supervision to improve discrimination. However, they often struggle to model diverse forgery artifacts without compromising pretrained representations. To address these limitations, we propose FMSD, a deepfake detection framework built upon Forgery-aware Layer Masking and Multi-Artifact Subspace Decomposition. Specifically, Forgery-aware Layer Masking evaluates the bias-variance characteristics of layer-wise gradients to identify forgery-sensitive layers, thereby selectively updating them while reducing unnecessary disturbance to pretrained representations. Building upon this, Multi-Artifact Subspace Decomposition further decomposes the selected layer weights via Singular Value Decomposition (SVD) into a semantic subspace and multiple learnable artifact subspaces. These subspaces are optimized to capture heterogeneous and complementary forgery artifacts, enabling effective modeling of diverse forgery patterns while preserving pretrained semantic representations. Furthermore, orthogonality and spectral consistency constraints are imposed to regularize the artifact subspaces, reducing redundancy across them while preserving the overall spectral structure of pretrained weights.

cs.CV↗

arXiv2026

Semantic Manipulation Localization

Image Manipulation Localization (IML) aims to identify edited regions in an image. However, with the increasing use of modern image editing and generative models, many manipulations no longer exhibit obvious low-level artifacts. Instead, they often involve subtle but meaning-altering edits to an object's attributes, state, or relationships while remaining highly consistent with the surrounding content. This makes conventional IML methods less effective because they mainly rely on artifact detection rather than semantic sensitivity. To address this issue, we introduce Semantic Manipulation Localization (SML), a new task that focuses on localizing subtle semantic edits that significantly change image interpretation. We further construct a dedicated fine-grained benchmark for SML using a semantics-driven manipulation pipeline with pixel-level annotations. Based on this task, we propose TRACE (Targeted Reasoning of Attributed Cognitive Edits), an end-to-end framework that models semantic sensitivity through three progressively coupled components: semantic anchoring, semantic perturbation sensing, and semantic-constrained reasoning. Specifically, TRACE first identifies semantically meaningful regions that support image understanding, then injects perturbation-sensitive frequency cues to capture subtle edits under strong visual consistency, and finally verifies candidate regions through joint reasoning over semantic content and semantic scope. Extensive experiments show that TRACE consistently outperforms existing IML methods on our benchmark and produces more complete, compact, and semantically coherent localization results. These results demonstrate the necessity of moving beyond artifact-based localization and provide a new direction for image forensics in complex semantic editing scenarios.

cs.CV↗

arXiv2026

A H.265/HEVC Fine-Grained ROI Video Encryption Algorithm Based on Coding Unit and Prompt Segmentation

ROI (Region of Interest) video selective encryption based on H.265/HEVC is a technology that protects the sensitive regions of videos by perturbing the syntax elements associated with target areas. However, existing methods typically adopt Tile (with a relatively large size) as the minimum encryption unit, which suffers from problems such as inaccurate encryption regions and low encryption precision. This low-precision encryption makes them difficult to apply in sensitive fields such as medicine, military, and remote sensing. In order to address the aforementioned problem, this paper proposes a fine-grained ROI video selective encryption algorithm based on Coding Units (CUs) and prompt segmentation. First, to achieve a more precise ROI acquisition, we present a novel ROI mapping approach based on prompt segmentation. This approach enables precise mapping of ROIs to small $8\times8$ CU levels, significantly enhancing the precision of encrypted regions. Second, we propose a selective encryption scheme based on multiple syntax elements, which distorts syntax elements within high-precision ROI to effectively safeguard ROI security. Finally, we design a diffusion isolation based on Pulse Code Modulation (PCM) mode and MV restriction, applying PCM mode and MV restriction strategy to the affected CU to address encryption diffusion during prediction. The above three strategies break the inherent mechanism of using Tiles in existing ROI encryption and push the fine-grained level of ROI video encryption to the minimum $8\times8$ CU precision. The experimental results demonstrate that the proposed algorithm can accurately segment ROI regions, effectively perturb pixels within these regions, and eliminate the diffusion artifacts introduced by encryption. The method exhibits great potential for application in medical imaging, military surveillance, and remote areas.

eess.IV↗