Search arXiv⌕ Search

arXiv subjects

Liang Wu

Publications and source records attributed to Liang Wu.

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

lapanda: A Matrix-Free Differentiable Solver for Nonconvex Constrained Optimization Layers

Differentiable optimization brings the structural guarantees of mathematical optimization to network pipelines, allowing them to be trained end-to-end. However, its application remains challenging for nonconvex constrained problems, as existing differentiable solvers often suffer from limited modeling expressiveness due to their reliance on specialized problem structures, while also incurring substantial computation time and memory overhead in both the forward and backward passes. To address these challenges, we propose lapanda, a matrix-free differentiable solver for nonconvex optimization with general constraints. It reformulates the problem to a sequence of augmented Lagrangian subproblems, each handled by a first-order inner solver through a proximal averaged quasi-Newton algorithm with adaptive linesearch, thus enabling efficient forward optimization. We establish local well-posedness of the solution map and convergence of the outer iterations, and further derive a sensitivity alignment between the original problem and the final subproblem in the backward pass, demonstrating that the subproblem sensitivity, which can be computed efficiently in a matrix-free manner, provides a principled approximation to the exact optimizer sensitivity. We evaluate lapanda on nonconvex constrained Rosenbrock benchmarks, imitation learning with several representative constrained optimal control problems, and embedded robotic obstacle-avoidance tasks. Compared with state-of-the-art differentiable solvers, lapanda delivers substantial reductions in computation time and memory footprint while maintaining reliable constraint satisfaction and learning performance.

math.OC↗
arXiv2026

Accelerating Branch MPC with Two-Level Parallel Direct Solves on GPUs

Branch model predictive control optimizes multiple future trajectories coupled through shared decisions, with computational demands increasing as the number of scenarios and prediction horizon grow. We present a GPU-accelerated direct linear solver for branch MPC formulations in which all trajectories share a single root decision node and evolve independently thereafter. By operating at the linear-algebra level, the solver provides a reusable backend for multiple optimization algorithms whose reduced systems have the required symmetric positive-definite structure. The solver exploits two levels of parallelism: across scenarios and along each prediction horizon. A tailored variable ordering enables horizon-parallel Cholesky factorization while preserving a single root-tail coupling block per scenario in the factor. Numerical experiments demonstrate substantial speedups over state-of-the-art sparse direct solvers, achieving factorization speedups of up to 6.0$\times$ over cuDSS and 27.6$\times$ over eight-thread PARDISO, with triangular solve speedups of up to 3.5$\times$ and 15.8$\times$, respectively.

eess.SY↗
arXiv2026

Structural Phase Separation Couples to Charge-Density-Wave Formation in Kagome Metal FeGe

The intertwining of charge, spin, and lattice degrees of freedom underlies the emergent properties of correlated materials. A recent prominent example is the kagome metal FeGe, which hosts coexisting charge density wave (CDW) and antiferromagnetic orders, accompanied by a lattice distortion associated with partial Ge-Ge dimerization. Using temperature-dependent high-resolution X-ray diffraction measurements, we observed a robust splitting of the lattice reflection into two coexisting peaks with distinct lattice constants at the CDW transition temperature TCDW, providing direct evidence for a first-order structural phase transition that is absent in samples with suppressed CDW order. Furthermore, the long-range CDW order was found to be only commensurate with lattice structures with the compressed out-of-plane lattice constant. The Landau free energy analysis shows that strong lattice-charge coupling is a key factor in stabilizing long-range CDW order. Our work clarifies the critical role of structural transformation in the CDW formation and opens opportunities for strain control of electronic phases in FeGe.

cond-mat.mtrl-sci↗
arXiv2026

Koopman-Based Linear MPC for Safe Control using Control Barrier Functions

This paper proposes a Koopman-based linear model predictive control (LMPC) framework for safety-critical control of nonlinear discrete-time systems. Existing MPC formulations based on discrete-time control barrier functions (DCBFs) enforce safety through barrier constraints but typically result in computationally demanding nonlinear programming. To address this challenge, we construct a DCBF-augmented dynamical system and employ Koopman operator theory to lift the nonlinear dynamics into a higher-dimensional space where both the system dynamics and the barrier function admit a linear predictor representation. This enables the transformation of the nonlinear safety-constrained MPC problem into a quadratic program (QP). To improve feasibility while preserving safety, a relaxation mechanism with slack variables is introduced for the barrier constraints. The resulting approach combines the modeling capability of Koopman operators with the computational efficiency of QP. Numerical simulations on a navigation task for a robot with nonlinear dynamics demonstrate that the proposed framework achieves safe trajectory generation and efficient real-time control.

eess.SY↗
arXiv2026

HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better

We present HunyuanOCR-1.5, a lightweight end-to-end OCR-specialized vision-language model. HunyuanOCR unifies document parsing, text spotting, information extraction, text-image translation, and multi-image document understanding within a single end-to-end VLM. Building upon the lightweight architecture of HunyuanOCR-1.0, HunyuanOCR-1.5 does not redesign the backbone, but systematically improves both efficiency and capability. For efficiency, we adapt DFlash to OCR decoding, significantly reducing the latency of long structured outputs such as dense documents, tables, and formulas while preserving output distribution. Powered by DFlash, HunyuanOCR-1.5 achieves a 6.37x Transformer inference speedup and a 2.14x speedup under vLLM, delivering the fastest inference among lightweight OCR VLMs. For capability, we propose Agentic Data Flow, an agent-driven data construction system that transforms model weaknesses into executable data requirements and autonomously performs material search, quality verification, and pipeline development. It substantially improves long-tail capabilities in ancient-script OCR, fine-grained chart and table parsing, multi-image text-centric QA, low-resource multilingual parsing, and document hallucination evaluation. HunyuanOCR-1.5 ranks among the top-tier end-to-end OCR solutions on OmniDocBench v1.6 while achieving new performance milestones across these long-tail tasks. Combined with an upgraded pretraining and post-training recipe, HunyuanOCR-1.5 further extends its capability in high-resolution, long-context, and multi-task scenarios. Experiments demonstrate faster inference, broader OCR capability coverage, and the deployment advantages of a lightweight end-to-end model. We will release the model weights and training code to support future research and real-world OCR applications.

cs.CV↗
arXiv2026

DR-MPC: Fast and Feasible Dynamics-Relaxed Model-Predictive Control for Legged Locomotion

This paper presents dynamics-relaxed model predictive control (DR-MPC), a novel MPC formulation for legged locomotion, and a tailored interior-point method (IPM) solver. The formulation combines online optimization feasibility by construction with a contact-aware input parameterization. DR-MPC moves the dynamics equality and affine input constraints into quadratic penalties and retains only nonempty box constraints. The resulting box-constrained quadratic program (QP) has a block-arrow Hessian that enables the state and affine-output directions to be eliminated through a Schur complement. The solver factors only the reduced control system after swing-force elimination and contact-aligned move blocking. For the evaluated implementations using the same DR-MPC formulation, our method achieves median end-to-end MPC speedups of $16.0\times$ over HPIPM and $4.4\times$ over OSQP, with comparable locomotion performance in simulation. DR-MPC achieves a median onboard MPC end-to-end time of $4.4$ ms and is validated on a Unitree Go1 quadruped. Open-source code will be made available after publication.

cs.RO↗
arXiv2026

Spatial-Code-Domain Grouped Index Modulation: Fluid-Antenna-Assisted System Design and BER Performance Analysis

Fluid antenna systems (FASs) provide reconfigurable spatial resources within compact apertures. In this paper, we introduce code-domain grouped index modulation (CGIM) and its spatial-code-domain extension, termed SCGIM, for FA-assisted transceivers. CGIM partitions the available orthogonal spreading codes into multiple subsets and jointly maps information onto their in-phase and quadrature indices and constellation symbols. In an Rx-FAS-assisted single-input multiple-output (SIMO) link, group-wise despreading separates the orthogonal code groups for parallel detection, while receive-port selection provides spatial diversity. SCGIM further associates interleaved Tx-FA port subsets with the code subsets, with the Tx-FAS conveying spatial-index information and the Rx-FAS providing selection diversity in a multiple-input multiple-output (MIMO) link. For SCGIM, we develop maximum-likelihood (ML), staged greedy (GD), and cross-domain index message-passing (CD-IMPD) detectors. CD-IMPD exchanges soft information over a cycle-free factor graph to account for the coupling between the spatial and code indices, requiring only one inward and one outward message pass. For CGIM, the BER is derived from the joint decision regions of the despread-domain observations and averaged over the Rx-FAS selected-gain distribution under Rayleigh, Nakagami-m, and additive white Gaussian noise channels. For SCGIM, an average-BER approximation is derived from a full-pair union bound using the selected-gain density ratio and exponentially tilted quadratic-form Laplace transforms. Simulation results validate the BER analysis and show that the proposed schemes achieve lower BER and higher throughput than the considered IM schemes, while CD-IMPD achieves near-ML BER performance with lower detection complexity.

cs.IT↗
arXiv2026

UAV Fluid-Antenna Channel Acquisition under Intra-Scan Channel Aging

Sequential sounding in UAV fluid-antenna systems (FASs) provides additional spatial information but delays transmission, causing earlier channel observations to age. This paper addresses the resulting information--freshness tradeoff by jointly determining where to probe and when to stop under blockwise hardware constraints. A dynamic Karhunen--Loève estimator aligns asynchronous measurements with the transmission state, covariance information gain selects feasible probe locations, and an age-discount identity with a local one-more-slot condition characterizes the covariance-level balance between information and freshness. Paired simulations show that temporal alignment recovers most of the lower-tail reliability lost by static stacking, covariance-aware probing ranks highest numerically among the evaluated policies, and optimized one-slot sounding becomes statistically competitive with two-slot alternatives at the highest tested mobility. Within the evaluated schedule family, increasing mobility shifts the competitive operating region toward shorter scans, supporting joint probe-placement and sounding-duration design.

cs.IT↗
arXiv2026

Field-Aware Agent Skill Retrieval

As lifelong learning agents accumulate lifelong growing skill banks, retrieving the correct skill becomes an increasingly important bottleneck. Most current skill retrieval methods treat each skill as one flat document by concatenating fields such as the name, description, and body. However, skills are naturally structured, multi-field objects, where each field provides different information about when and how the skill should be used. In this work, we study whether preserving this structure improves skill retrieval. We represent each skill as its separate components, and compute sparse and dense similarities for each field independently, exposing a naturally tensorized, field-aware representation of the skill bank. We then combine these field-level scores either with uniform weights or with a small learned MLP. Across two different skill retrieval benchmarks, SkillRet and SRA-Bench, we find that keeping fields separate improves hybrid retrieval, and learning over the field-level scores gives the strongest and most consistent results. Our field-aware MLP reaches $77.95$ Recall@10 on SkillRet and $83.78$ Recall@10 on SRA-Bench, outperforming the corresponding concatenated learned baselines. We also find that the advantage grows as the skill bank becomes larger, suggesting that field-aware skill retrieval becomes especially useful in the setting where retrieval is most difficult. Our results show that skill representation itself matters, and that simply preserving the structure already present in skill files can substantially improve retrieval.

cs.IR↗
arXiv2026

S^3martCirc: Self-supervised Smart Circuit Discovery

Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks, from text summarization to question answering. Despite these capabilities, their black-box nature obscures internal decision-making processes. Mechanistic interpretability (MI) aims to address this by reverse-engineering neural networks into human-understandable algorithms. Current MI approaches for LLMs typically follow a two-stage paradigm: first identifying important components (circuit discovery), where components are typically individual nodes such as an attention head or feedforward neuron, and second determining the role they play in a certain task (functional interpretation). However, this sequential approach overlooks a fundamental insight: a component's importance and its functional role are inherently codependent. Unifying these stages presents two key challenges: (1) functional roles are often tied to specific nodes or components, limiting generalization, and (2) their identification relies on subjective interpretation rather than quantifiable metrics. To address these challenges, we propose S^3martCirc (Self-supervised Smart Circuit Discovery), a unified framework that simultaneously discovers circuits and interprets functionality. S^3martCirc abstracts node behavior into two general computational roles that generalize across tasks and defines a quantitative metric for assigning them, enabling importance and functional role to be discovered jointly rather than in sequence. Extensive experiments show that our framework outperforms existing methods in circuit discovery.

cs.AI↗
arXiv2026

WiSP: A Working-Set View of Mixture-of-Experts Serving on Extremely Low-Resource Hardware

Modern local and agentic workloads often need large-model capacity at low concurrency, but run on GPUs that cannot keep a frontier-scale model resident. Mixture-of-Experts (MoE) models are a natural fit because they activate only a small subset of experts per token, but their sparsity saves computation, not residency: the full expert pool still has to be stored, and any expert used by a layer must be in GPU memory when that layer runs. Static layer-level CPU offload makes such models fit, but transfers the expert layer in bulk on every forward pass, losing much of the sparsity advantage. We view low-resource MoE serving as a working-set problem on the GPU. Routed expert weights and the KV cache are two memory-demand streams competing for the same limited VRAM. We implement this view in WiSP (Working-Set Paging), a routing-aware expert pager that plugs into an unmodified serving engine and preserves byte-identical outputs. On a real 24 GiB RTX 3090, WiSP achieves up to 2.0x the decode throughput of static offload at the same memory budget when the model does not fit. A natural next step is to predict future experts and prefetch them. We find that this does not help in single-stream decode: the bottleneck is PCIe bandwidth, not prediction quality, so speculative transfers compete with demand transfers instead of hiding them. This shifts the design question from prefetching to allocation: how should one VRAM budget be divided between resident experts and the KV cache? We answer with MV-WSA (Marginal-Value Working-Set Allocation), which splits memory by marginal latency benefit per byte while enforcing a KV-admission floor. As a startup configurator, MV-WSA is the only policy we test that stays near-best on both prefill and decode; as a live controller, it resizes both pools while serving and reduces end-to-end time by up to 1.19x over a fixed offline split, without changing model outputs.

cs.LG↗
arXiv2026

Physics-Informed Stochastic Configuration Machine: A Backpropagation-Free Neural Network with Fast Training for Nonlinear Differential Equations

While Physics-Informed Neural Networks (PINNs) have emerged as a transformative paradigm for solving complex differential equations, their reliance on backpropagation-based gradient descent and automatic differentiation (AD) imposes significant computational bottlenecks and severe non-convex optimization challenges. To overcome these fundamental limitations, we propose the Physics-Informed Stochastic Configuration Machine (PI-SCM), a novel backpropagation-free framework for both forward and inverse problems in differential equations. The core mathematical contribution lies in the analytical evaluation of local Jacobians for nonlinear differential operators, which facilitates a linearized representation of the physical loss and projects it into a unified, linearized algebraic subspace. This reformulation allows for the explicit determination of optimal network weights via a sequence of generalized linear least squares solvers, effectively bypassing the iterative traps of traditional nonlinear optimizers. We develop a progressive algorithmic suite comprising localized construction (PI-SC-I), sliding-window updating (PI-SC-II), and global updating (PI-SC-III), and rigorously establish their universal approximation properties. Extensive experiments demonstrate that PI-SCM achieves high-fidelity predictive accuracy and robust parameter identification while accelerating the training process by orders of magnitude compared to standard PINNs. Our work provides a highly efficient and scalable foundation for next-generation, real-time Scientific Machine Learning applications.

math.NA↗
arXiv2026

LLM Agents for Time-Series: A Survey

LLM-based agents are increasingly being developed for time-series problems, but their design choices vary substantially across task settings. This survey adopts a problem-driven taxonomy that organizes these systems by the time-series problems they address rather than by isolated technical components. We group existing systems into four categories: forecasting and reasoning, augmentation and synthesis, anomaly detection and diagnosis, and decision support. Within each category, we examine how task requirements shape agent architecture, tool use, and memory design. We further summarize representative datasets and environments, and compare reported model performance under shared or closely related settings. Overall, this survey offers a task-oriented guide to designing LLM-based agents for time-series problems and identifies open gaps for future work.

cs.AI↗
arXiv2026

SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendation

Generative recommendation treats next-item prediction as autoregressive item-identifier generation. Specifically, items are encoded as semantic identifiers (SIDs), which are short coarse-to-fine token sequences whose early tokens capture broad semantics and later tokens refine them. Recent work augments this paradigm with reasoning traces and optimizes them via reinforcement learning with verifiable rewards, typically outcome-reward algorithm with exact-match feedback on the generated SID. However, in large-catalog recommendation, exact-match feedback on the generated SID only reports whether the final item is correct; when a generated SID mismatches, outcome-reward cannot identify which SID-token prediction caused the mismatch and may penalize matched SID-token positions together with the mismatched position. We identify that the natural unit of credit assignment in this setting is a single reasoning step (one thinking block paired with one SID token). We instantiate this idea in SAPO (Step-Aligned Policy Optimization): rather than broadcasting one advantage to the whole response, SAPO computes a separate group-relative advantage for each reasoning step and applies it only to the corresponding thinking block and SID token. Across three real-world recommendation datasets, SAPO stabilizes reinforcement-learning training and consistently improves over existing generative recommendation baselines, with the largest gains where sparse exact-match feedback makes reasoning-step credit assignment important. Our results suggest that reinforcement-learning objectives for structured generation should mirror the decoder's own decomposition of the output.

cs.AI↗
arXiv2026

Self-Evolving Code-with-Image Reasoning

Multimodal models increasingly reach for tools when solving visual tasks (crop, zoom, rotate, brighten), a paradigm known as thinking-with-images. The central challenge is one of perception: tools mostly serve to expose visual evidence, reasoning over that evidence stays in language, and most targets are ones a human could in principle determine by inspection. Some visual questions, however, are not bottlenecked by perception: recovering their answers requires executing a multi-step visual algorithm over the pixels. On such questions a model often names the correct algorithm at once yet still answers wrong, because language can describe an algorithm without being able to run one. Code-with-Image crosses that line: given nothing but a Python interpreter, the model must implement a genuine visual algorithm in code to solve the task; the program itself becomes the reasoning. The bottleneck then shifts from executing code to deciding which algorithm to implement. So we let the model teach itself: a training-free reflection loop studies its own failed programs, tests repairs against constructive ground truth, and keeps what survives as portable skills. On our Code-with-Image Bench (CwI-Bench), thirty task families induced by hidden visual computations with disjoint learning and evaluation splits, even GPT-5.6-luna stays below 30% with tool-free chain of thought; given a bare interpreter it reaches 43%, and with skills evolved through its own executable reflection, 67%. The open 27B model climbs the same ladder (9% $\rightarrow$ 33% $\rightarrow$ 56%), and the skills are plain text, transferable across scales and families. When code carries the reasoning, debugging code becomes debugging reasoning.

cs.CV↗
arXiv2026

SPECTRA: Pushing the KV Cache Beyond the 2-Bit Cliff via Spectral Transform Coding

Large language models (LLMs) increasingly read long inputs in the agentic era, from whole documents and codebases to conversations across many turns. Their inference memory is then dominated by the key-value (KV) cache, the stored attention keys and values of every token the model has read and generated. Because the cache grows with context length and is re-read in full at every generated token, a longer context means more GPU memory. To reduce this cost, most existing methods compress the KV cache by lowering every stored value to the same low precision, a technique known as quantization. They can push this to nearly two bits per value, but rarely further, because quality drops sharply at this 2-bit cliff: four levels are too few for the cache's outlier-heavy values, where a few large entries consume the levels and collapse the rest into noise. A natural remedy is to spend more bits on the channels (feature dimensions) that matter and fewer on the rest, but the raw cache offers no handle: its channels are strongly correlated, so none stands out as more important. Our analysis shows that this handle appears once the cache is rotated into a coordinate system computed from its own statistics, removing these correlations. There, a small fraction of channels carries almost all the information, and spending the budget on those few is far more accurate than spreading it evenly. Guided by this analysis, we develop SPECTRA, a training-free, drop-in codec that re-encodes the cache into this coordinate system and concentrates the bit budget on the channels that carry the signal. On Llama-3.1-8B and Qwen2.5-7B over long-context benchmarks, SPECTRA is near-lossless at 4x compression, competitive at 8x where uniform quantization has collapsed, and reaches up to 12x, pushing usable compression past the 2-bit cliff so the same GPU holds longer contexts and larger batches.

cs.LG↗
arXiv2026

The self-organized vacancy order in Pr$_9$Ge$_{16}$

In this work, we report the discovery of a new crystal structure on the Ge-rich side of the Pr-Ge binary phase diagram. Using a high-temperature flux technique, we grew single crystals of $Pr_9Ge_{16}$, which adopt a previously unreported orthorhombic $Fdd$2 structure type featuring ordered Ge vacancies. We present the anisotropic magnetic properties and identify the crystallographic $b$ axis perpendicular to the crystal plane as the magnetic easy axis. Temperature-dependent resistivity measurements reveal metallic behavior with a distinct anomaly at $T_{\mathrm{C}}$ = 14.3 K. Hall resistivity data indicate that electron-like carriers dominate, with a carrier concentration on the order of $10^{27}~\mathrm{m}^{-3}$. The magnetic order is readily suppressed by a magnetic field of approximately 0.4 T applied along the easy $b$ axis.

cond-mat.mtrl-sci↗
arXiv2026

HyMobileAgent: Data-Environment Co-Scaling for Efficient GUI Agents

As large multimodal models move from understanding content to operating on digital environments, mobile GUI has emerged as a challenging and consequential testbed for digital embodied intelligence. Mobile agents operate under three coupled constraints: precise perception of complex interfaces, scalable acquisition of high-quality interaction data, and robust long-horizon decision making under compounding execution errors. This report presents HyMobileAgent, a mobile GUI agent built on Hy3.0-VL-A3B, a vision-native foundation model featuring native any-resolution input, an A3B-scale deployment budget, and a 32K context window to model extended interaction histories. Rather than relying solely on model scaling, we develop a joint data and environment centric scaling framework to address the key bottlenecks of mobile interaction. Our framework integrates a GUI perception flywheel combining mock-interface synthesis, rejection sampling, and icon-specific augmentation; a knowledge pipeline that transforms tutorial videos into structured interaction data; a million-scale action data pipeline deployed across more than 2000 sandbox and real-device instances with automated failure attribution; the PhoneWorld Mock App Factory, providing a resettable training environment with 34 mock applications and over 34000 tasks; and a structured Planning-and-Reflection mechanism with explicit dead-loop detection for reliable long-horizon execution. We also introduce a progressive training recipe consisting of mid-training, supervised fine-tuning, and reinforcement learning with task-specific reward designs.

cs.CV↗