arXiv subjects

Wei Jiang

Publications and source records attributed to Wei Jiang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Projection-Free Multi-level Algorithms for Stochastic Constrained Compositional Optimization

This paper studies projection-free algorithms for stochastic constrained multi-level compositional optimization. In this context, the objective function is a nested composition of several smooth functions, and the decision set is closed and convex. Since projection onto the constraint set can be computationally expensive, we develop projection-free methods that rely on linear minimization oracles. For non-convex objectives, we propose variance-reduced projection-free algorithms and establish complexity guarantees under both the Frank-Wolfe gap and the gradient mapping criteria. We also develop momentum-based methods that achieve convergence guarantees under weaker smoothness assumptions. Additionally, by using a stage-wise design, we derive a parameter-free variant that preserves the same complexities for the Frank-Wolfe gap. Such a design can be further used to develop algorithms for convex and strongly convex functions whose rates match those of single-level projection-free counterparts. Finally, we consider finite-sum problems and derive complexities for non-convex, convex, and strongly convex objectives. Numerical experiments across multiple tasks demonstrate the effectiveness of the proposed methods.

math.OC↗

arXiv2026

Solving Finite-sum Coupled Compositional Optimization via Multi-block-Single-probe Estimator

Traditional variance reduction methods (e.g., SPIDER, SARAH, STORM) have been extensively investigated for improving the convergence rates of stochastic optimization. These techniques typically maintain a sequence of estimators for a single function (or gradient) across iterations. However, what if we need to track multiple functions, but can only access stochastic samples of $\mathcal{O}(1)$ functions at each iteration? This scenario arises in an important emerging family of finite-sum coupled compositional optimization (FCCO) problems of the form $\frac{1}{m}\sum_{i=1}^m f_i(g_i(\mathbf{w}))$, where each $g_i$ is accessible only through a stochastic oracle. The key challenge is to track $\mathbf g(\mathbf{w})=(g_1(\mathbf{w}), \ldots, g_m(\mathbf{w}))$ over time, where $\mathbf g(\mathbf{w})$ has $m$ blocks but only $\mathcal{O}(1)$ blocks can be probed for their stochastic values at each step. To address this challenge, we propose a novel Multi-block-Single-probe Variance Reduction (MSVR) estimator to efficiently trace $\mathbf g(\mathbf{w})$ under partial block sampling. Building on the MSVR estimator, we develop several algorithms for FCCO problems, achieving improved sample complexities for non-convex, convex, strongly convex, and Polyak-Łojasiewicz (PL) objectives. We further obtain an improved dependence on $m$ when the outer function gradients $\nabla f_i$ are linear. Empirical studies on multi-task deep AUC maximization further demonstrate the superior performance of the proposed estimators.

cs.LG↗

arXiv2026

Beyond Discrete Samples: High Information Density Replay for Efficient Lifelong Person Re-Identification

Lifelong Person Re-Identification (LReID) typically resists catastrophic forgetting by replaying historical samples, rehearsing domain distributions, or distilling previous model knowledge. Among these, data replay is favored for its simplicity and efficiency, as it fundamentally relies on storing discrete raw images. Although often claimed to be efficient, repeatedly training on an accumulating replay buffer with complex selection strategies across sequential domains is actually highly inefficient. Furthermore, this discrete selection severely restricts historical data coverage and results in low information density, inevitably leading to poor generalization on evolving domains and causing these methods to gradually fall behind other approaches. In this paper, we rethink LReID replay and shift the paradigm from sample selection to information compression, proposing a High Information Density Replay (HiDeR) framework. Rather than saving sparse instances, we continually consolidate historical data into a compact, fixed-budget memory. Specifically, we introduce a complexity aware allocation mechanism to dynamically assign memory quotas based on intra-class variance, alongside a metric guided condensation objective that directly preserves essential identity topologies. Furthermore, since highly compressed synthetic samples exhibit artifact styles unsuitable for current domain training, we introduce a cross modality adaptation strategy. By bidirectionally translating styles between synthetic and real samples, this strategy bridges the modality gap to mitigate optimization conflicts, while also enriching stylistic diversity for better generalization. Extensive experiments demonstrate that our framework outperforms state-of-the-art methods in retaining historical knowledge and improving overall generalization, while substantially reducing the cumulative replay cost.

cs.CV↗

arXiv2026

Symmetry Inheritance and Symmetry-Reduced Finite Element Analysis for Second-Order Linear Elliptic Problems with Robin Boundary Conditions

A symmetry framework is developed for second-order linear elliptic equations subject to Robin boundary conditions on bounded domains. Orthogonal transformations of the domain are represented through left group actions on scalar, vector, and second-order tensor fields. The corresponding transformation rules for the gradient, divergence, diffusion flux, and conormal boundary term are derived in detail. Based on these relations, symmetry groups are introduced for the principal coefficient tensor, the first-order and zeroth-order coefficients, the differential operator, the Robin coefficient, and the boundary operator. The symmetry properties of the volume and boundary source terms are then incorporated into a common symmetry group for the complete boundary value problem. Under the assumption of unique solvability, it is proved that every element of this common group is also a symmetry of the solution. For reflection symmetries, homogeneous generalized Neumann conditions are obtained on artificial symmetry boundaries, leading to an exact reduction of the computational domain. A corresponding finite element formulation is presented, and numerical results are provided to verify the theoretical symmetry properties and the validity of the resulting domain-reduction strategy. Three examples illustrate radial reduction from multiple dimensions to one dimension, reflection-based domain reduction, and a variable-coefficient problem in which all coefficients and source terms are nonzero.

math.NA↗

arXiv2026

Counter-rotating density and current structures in a partially magnetized $\mathbf{E}\times\mathbf{B}$ plasma

The first 3D kinetic simulation of a magnetron discharge reproduces the measured rotating spoke and reveals that density and current rotate in opposite directions: the $m=1$ spoke turns in the $\mathbf{E}\times\mathbf{B}$ direction at 90~kHz while $m\simeq16$ electron-cyclotron-drift-type filaments turn at 1.0~MHz, with no net propagation along $\mathbf{B}$. Magnetic drifts exchange far more energy than they deposit, yet their spoke-front heating sustains the ionization. Following helical paths, the anode-directed current is relayed by de-trapping turbulence at the sheath edge (50\%) and by the spoke channel in the bulk (97\%).

physics.plasm-ph↗

arXiv2026

Accurate Measurement of 3D and 2D Circular Centers With Application to LiDAR-Camera Extrinsic Calibration

Accurate measurement of circular centers is a fun-damental geometric sensing problem in instrumentation and measurement tasks involving cameras, LiDARs, and other spa-tial sensors. In circular-target-based LiDAR-camera extrinsic calibration, a 3D circular center measured from LiDAR and its corresponding 2D projected center measured in the image serve as cross-modal geometric observations for estimating the rigid transformation between the two sensor frames. Conven-tional pipelines can bias both measurements: the 3D center is often obtained by sequential plane fitting, point projection, and 2D circle fitting, while the image ellipse center is frequently treated as the projected circle center even though the two generally differ under perspective projection. This paper focuses on accurate 3D and 2D circular-center measurement and uses LiDAR-camera extrinsic calibration as a representative applica-tion. A conformal-geometric-algebra estimator is integrated with RANSAC to jointly recover the 3D center, normal, and radius from noisy or partially observed LiDAR points. A chord-length-variance criterion then estimates the 2D projected center, with its twofold ambiguity resolved by homography validation or a quasi-RANSAC fallback. Synthetic and real-sensor experiments show that the proposed method improves circular-center measurement accuracy and reduces extrinsic calibration error across different target and sensor configurations.

cs.CV↗

arXiv2026

Modulation of charge density waves in a twisted vortex moire superlattice

Twisted moire superlattices in van-der-Waals heterostructures provide a powerful platform for engineering correlated states through moire-band reconstruction. However, whether globally coherent electronic orders can be continuously manipulated at the nanoscale remains largely unexplored. Reconstructed moire structures in small-angle and near-commensurate regime feature continuously varying local environments, offering new opportunities for nanoscale manipulation of correlated phases. Here, we report the modulation of charge density wave (CDW) states in a twisted vortex moire superlattice formed between monolayer VTe2 and superconducting NbSe2. Scanning tunneling microscopy/spectroscopy reveals that the intrinsic long-range CDW of monolayer VTe2 is reconstructed into inequivalent local phases with distinct stability and coherence within a single moire unit cell, including suppressed CDW order and enhanced short-range CDW correlations persisting to room temperature. First-principles calculations show that the reconstructed CDW landscape originates from strong local strain variation, where compressive strain substantially stabilizes the charge order. Furthermore, the modulated CDW states exhibit competing interplay with proximity-induced superconductivity. Our results establish vortex moire superlattices as a versatile platform for nanoscale manipulation of correlated electronic orders in low-dimensional quantum materials.

cond-mat.mtrl-sci↗

arXiv2026

M$^3$ISR: A Multi-Modal Multi-View Benchmark for 3D/4D Gaussian Splatting and Feedforward Compression

High-fidelity free-viewpoint video (FVV) and interactive rendering increasingly rely on explicit Gaussian representations, yet practical deployment remains constrained by representation size, dynamic updates, and computational cost. Existing multi-view video benchmarks provide valuable real-captured content, but they make it difficult to isolate the effects of controlled camera geometry, representation efficiency, and temporal redundancy. We introduce M$^3$ISR, a controlled synthetic benchmark for 3D and 4D Gaussian Splatting (3DGS/4DGS). The benchmark contains 25 scenes from five indoor and outdoor scene groups, two camera/motion configurations, six synchronized 1080p views, and dense ground-truth annotations including RGB, camera parameters, depth, semantic and instance segmentation, and static--dynamic masks. The shared-center camera design intentionally isolates angular view variation and enables controlled evaluation of novel-view synthesis and representation efficiency. We organize M$^3$ISR into five complementary tracks covering 3DGS synthesis, 4DGS synthesis, 4DGS streaming, 3DGS compression, and 4DGS compression. Representative baseline results show small differences in static reconstruction quality but substantial differences in representation storage, while the evaluated streaming methods exhibit substantially higher reported training or reconstruction cost than the corresponding offline dynamic reconstruction baselines. We further define feedforward compression tasks for 3DGS and 4DGS and provide reference rate--distortion formulations and preliminary baseline evaluations. The benchmark is intended as a controlled and complementary testbed for systematic study of Gaussian-based FVV reconstruction, compression, and streaming.

cs.CV↗

arXiv2026

GaussVid: Sparse-View Gaussian Splatting with 3D-Aware Video Diffusion Priors

3D Gaussian Splatting (3DGS) has achieved remarkable success in novel view synthesis; however, reconstructions under sparse views often exhibit noticeable artifacts. While recent video diffusion models provide strong spatio-temporal priors for 3DGS restoration, directly fine-tuning them for restoration is suboptimal, as they lack awareness of the underlying multi-camera geometry, resulting in multi-view inconsistencies. In this work, we propose a novel 3D-aware video restoration framework designed to enhance the quality of sparse 3DGS reconstruction. Specifically, we construct a large-scale 3DGS video dataset to enable specialized fine-tuning. To bridge the gap between 2D video generation and 3D multi-view constraints, we introduce a camera-conditioned geometric prior. By using the first and last frames as boundary anchors and encoding the corresponding camera relationships, we explicitly inject spatial structure into the video generation pipeline. This boundary-anchored, camera-aware prior guides the network toward geometrically grounded restoration that remains coherent across viewpoints. Extensive experiments show that, among video-prior restoration methods, our approach attains the best pixel- and structure-level fidelity (PSNR/SSIM) and improves multi-view consistency, while remaining competitive in perceptual quality (LPIPS).

cs.CV↗

arXiv2026

COEC: Calibrated Orthogonal-Equivalence Compensation for Structured Pruning of Large Language Models

Structured pruning reduces the size and inference cost of large language models (LLMs) by removing weight columns, but the resulting output error can degrade accuracy. Existing training-free compensation methods use an additive bias or a single orthogonal rotation on the output side of the retained weight. These corrections leave its input singular frame unchanged and therefore limit how the retained weight can adapt after column removal. We propose COEC (Calibrated Orthogonal-Equivalence Compensation), a training-free compensation framework that applies alternating left and right orthogonal rotations to the retained weight. The right rotation is optimized on a reduced Stiefel manifold, while singular values are rescaled using generalized cross-validation to select the regularization strength for each layer. COEC further tempers the calibration Gram matrix to reduce the dominance of high-energy activation directions and introduces an alignment penalty that preserves the geometric relation between adjacent attention projections.All components use second-order statistics from a small calibration set and require neither backpropagation through the LLM nor retraining of the model parameters. COEC is independent of the column pruning criterion and can be applied to multiple structured pruning methods. Experiments on the Llama-3, Llama-3.1, and Qwen2.5 model families across multiple structured sparsity levels show that COEC improves perplexity on every model and zero-shot accuracy in most settings over existing compensation methods, with larger gains at higher sparsity. These results show that post-pruning compensation can recover part of the performance lost to column removal.

cs.LG↗

arXiv2026

Role-Conditioned Sub-Token Routing for Efficient Vision-Language-Action Policies

Vision-Language-Action (VLA) models process long multimodal token sequences, making inference expensive in both memory and computation. Existing efficiency methods mainly reduce visual tokens, but aggressive token pruning becomes fragile because removing a token discards its entire representation. Sub-token compression provides a complementary alternative by retaining more tokens while reducing their value width. However, directly applying sub-token compression to VLA policies is less effective because information important for perception, language understanding, and control is distributed differently across the multimodal representation. We introduce Role-Conditioned Sub-Token Routing (RoleSub), which learns how to compress the value representations of retained tokens. After visual token reduction, RoleSub partitions each retained value representation into groups in an orthogonal space and uses a lightweight router to determine which groups should be preserved. The routing decision is conditioned on the token representation, a learned latent role representation, and language context. The same mechanism can also be applied to language values, allowing visual and language representations to be compressed without removing additional tokens. We evaluate RoleSub on OpenVLA-OFT-7B across the four LIBERO suites. At matched visual-KV budgets, RoleSub outperforms a trained token-only control in 33 of 36 settings, with the largest gains under aggressive compression. Combining visual and language compression reduces total KV to 9.2--11.3% of the original while retaining strong control performance on most tasks. These results show that reducing the representation within retained tokens provides an effective complement to token pruning for aggressive VLA compression.

cs.LG↗

arXiv2026

Symmetry of Solutions and Domain-Reduction Finite Element Method for Second-Order Linear Elliptic Dirichlet Boundary Value Problems on Bounded Domains

Combining classical group theory and partial differential equation theory, this paper investigates the symmetry group $\operatorname{Sym}(u)$ of the unique solution $u$ to the second-order linear elliptic boundary value problem on an $n$-dimensional bounded domain $Ω$ $-\sum_{i,j=1}^{n} a_{ij}(x)u_{x_ix_j} + \sum_{i=1}^{n} b_i(x)u_{x_i} + c(x)u = f(x), x\in Ω$, $u(x) = h(x), x\in \partial Ω$, The following symmetry groups are defined and characterized respectively: the symmetry group $\operatorname{Sym}(A)$ of the second-order coefficient matrix function $A(x)=(a_{ij}(x))_{n\times n}$; the symmetry group $\operatorname{Sym}(b)$ of the first-order coefficient column vector function $b(x)=(b_{1}(x),b_{2}(x),\cdots,b_{n}(x))^{T}$; the symmetry group $\operatorname{Sym}(c)$ of the zero-order coefficient function $c(x)$; the symmetry group $\operatorname{Sym}(f)$ of the internal source function $f(x)$; and the symmetry group $\operatorname{Sym}(h)$ of the boundary source function $h(x)$. This paper rigorously proves that the common symmetry group $\operatorname{Sym}(A)\cap\operatorname{Sym}(b) \cap\operatorname{Sym}(c) \cap\operatorname{Sym}(f) \cap\operatorname{Sym}(h)$ is a subgroup of $\operatorname{Sym}(u)$. In addition, if the common symmetry group contains several mirror symmetry elements, the original second-order linear elliptic boundary value problem on the entire domain $Ω$ can be reduced to the corresponding boundary value problem on a certain subdomain. It is strictly proven in this paper that the new boundary condition imposed on the boundary of the subdomain is the homogeneous generalized Neumann boundary condition. The linear finite element method is used to numerically solve the second-order linear elliptic boundary value problem on the subdomain, thereby achieving domain reduction and significantly reducing the computational cost.

math.NA↗

arXiv2026

Integrated Sensing and Communications over Hierarchical Cellular and Cell-Free MIMO Systems

This paper studies integrated sensing and communications (ISAC) over a hybrid system that seamlessly combines legacy cellular base stations with distributed cell-free (CF) access points (APs). We propose a hierarchical ISAC architecture where a central base station (CBS) serves its near users and simultaneously operates as a monostatic radar for aerial target detection, while distributed APs---many idle under user-centric clustering---act as cost-free bistatic receivers. The CBS jointly handles communication processing and multi-static sensing fusion, reducing fronthaul overhead compared to conventional cell-free ISAC. To achieve this, a five-phase time-division duplexing workflow with precise ISAC role assignment is specified. Closed-form expressions for spectral efficiency and multi-static sensing signal-to-noise ratio analytically characterize the communications--sensing Pareto frontier. Numerical results confirm that the proposed hierarchical design simultaneously achieves higher sum throughput and superior sensing accuracy than conventional cell-free ISAC.

cs.IT↗

arXiv2026

BiCRVC: An Efficient Bidirectional Neural Video Compression Framework via Coupled Representation Coding

Neural video compression (NVC) has achieved strong compression performance, but practical random-access coding still faces two technical challenges: existing bidirectional NVCs (BVCs) usually require costly motion-first decoding, and reliable motion estimation is difficult under long-range bidirectional prediction. To address these issues, we present BiCRVC, an efficient bidirectional neural video compression framework based on coupled representation coding. Instead of coding motion and frame information with two separate codecs, BiCRVC transforms the motion representation and the current-frame latent into a unified latent representation for entropy coding. This design enables motion and frame information to be decoded from the same bitstream with one unified codec, while still reconstructing motion-aligned contexts for frame decoding. To improve motion accuracy, we introduce multi-candidate motion estimation (MCME), which combines multi-scale motion estimation and parallel accumulated motion estimation to better handle diverse and long-range motions. To reduce motion coding overhead, we further propose bidirectional motion feature propagation (BMFP), which reuses previously decoded motion features at both the encoder and decoder as temporal priors for conditional motion coding. In addition, coupled distortion training and random GOP structure training are used to encourage joint motion-frame coding and improve adaptation to hierarchical random-access structures. Experiments show that BiCRVC achieves better compression performance than state-of-the-art BVCs while providing about 30 times faster 1080p decoding than recent BVCs.

eess.IV↗

arXiv2026

CORAM: Coherent Orthogonal Rotation for Model Merging

Merging finetuned models combines specialized capabilities without joint training or access to the original data. Most methods operate by linear arithmetic in Euclidean weight space, which cannot carry the geometry of the update. Orthogonal Model Merging (OrthoMerge) uses a single orthogonal transform for each weight matrix, but such a transform cannot change singular values. We propose CORAM, which partitions each target matrix into row slices, represents every expert slice by its singular value decomposition in the corresponding base-model SVD frame, and merges the task-specific factors on their corresponding manifolds. Because manifold averaging contracts the merged update, CORAM applies an amplification coefficient $λ=κ\hat{c}$. The scale c_hat is estimated from the expert and merged update norms and is approximately $\sqrt{N}$ for $N$ experts with comparable update magnitudes. The restoration strength kappa is selected from the dispersion of expert updates without evaluating candidate merged models. This rule remains within 0.72 points of the best swept value on all evaluated suites. CORAM also includes spread slicing to distribute highly updated rows across slices and a residual pathway for non-target layers. Across four suites covering three model families, 3B to 9B scales, and language and vision-language experts, CORAM improves over OrthoMerge by 0.25 to 1.35 points and matches or exceeds the strongest weight-space baselines.

cs.LG↗

arXiv2026

Quantized Spin Hall Effect in Three-Dimensional Nodal-Ring Semimetal: Geometric Scaling and Symmetry-Engineered Spin Response

The anomalous Hall conductivity in magnetic Weyl semimetals scales linearly with the momentum separation between Weyl nodes, establishing a geometric paradigm for three-dimensional Hall responses. Here we discover an analogous phenomenon in the spin Hall effect: a quantized spin Hall conductivity (SHC) in nodal-ring semimetals that scales linearly with the nodal-ring radius $R$. From an ideal model with a single nodal ring, we derive analytically that the SHC inside the spin-orbit-coupled gap obeys $σ_{αβ}^{S, 3D}=σ_0^{S,2D} \cdot (πR/2 π)$, where $σ_0^{S,2D}=(e^2/h) \cdot (\hbar/2 e)$ is the two-dimensional quantum spin Hall conductance. Crucially, the symmetry of the spin-orbit coupling acts as an independent switch: Rashba coupling generates purely conventional SHC components, while Weyl coupling additionally activates unconventional ones, providing separate control over response magnitude and tensor symmetry. We validate this principle in yttrium nitride, where strain tunes $R$ and symmetry breaking toggles between response types. Our work establishes a new paradigm for engineering quantized geometric responses in three dimensions, opening pathways to tailored spin-orbit functionalities.

cond-mat.mtrl-sci↗

arXiv2026

Simple Restricted modules for $N=2$ Neveu-Schwarz algebra

In this paper, we first construct many simple restricted modules for the $N=2$ Neveu-Schwarz algebra $\mathcal{L}$. These modules contain the highest weight modules and Whittaker modules. Then we precisely characterize the simple restricted modules over $\mathcal{L}$ under certain conditions, and establish several equivalent conditions for a simple $\mathcal{L}$-module to be restricted. Finally, we prove that if one specific positive root element of $\mathcal{L}$ acts locally finitely on a simple $\mathcal{L}$-module $V$, then $V$ must be restricted.

math.RT↗

arXiv2026

SVRepair: Structured Visual Reasoning for Automated Program Repair

Large language models (LLMs) have recently been applied to Automated Program Repair (APR), yet most existing approaches remain unimodal and fail to use diagnostic signals contained in visual artifacts such as screenshots and control-flow graphs. In practice, many bug reports convey critical information visually (e.g., layout breakage or missing widgets), but directly using such dense visual inputs often causes context loss and noise, making it difficult for MLLMs to ground visual observations into precise fault localization and executable patches. To bridge this semantic gap, we propose \textbf{SVRepair}, a multimodal APR framework with Structured Visual Representation (SVR). SVRepair first fine-tunes a vision-language model, SVR, to uniformly transform heterogeneous visual artifacts into a \emph{semantic scene graph} that captures GUI elements and their structural relations (e.g., hierarchy), providing normalized, code-relevant context for downstream repair. Building on the graph, SVRepair drives a coding agent to localize faults and synthesize patches, and further introduces an iterative visual-artifact segmentation strategy that progressively narrows the input to bug-centered regions to suppress irrelevant context and reduce hallucinations. Across primary repository-level APR benchmarks, SVRepair resolves \textbf{186/517} SWE-Bench M instances (\textbf{35.98\%} over all instances; \textbf{36.47\%} over submitted runs) and \textbf{4/19} visual OmniGIRL instances (\textbf{21.05\%}). On supplementary structured multimodal code reasoning benchmarks, SVRepair reaches \textbf{38.02\%} on MMCode and \textbf{95.73\%} on CodeVision. Code is available at https://github.com/codefuse-ai/CodeFuse-SVR.

cs.SE↗