Searcharxiv⌕ Search

arXiv subjects

Yueqi Wang

Publications and source records attributed to Yueqi Wang.

At least 19 recordsLinked to original sources

Patch LegONet: Resolving Localized High-Frequency PDE Dynamics with Low-Frequency Operator Blocks

Localized interfaces, layers, and shocks can require high spatial resolution even when most of a partial differential equation (PDE) solution remains smooth. In global spectral methods, resolving these features requires increasing the approximation order across the entire domain. LegONet builds PDE solvers from reusable mechanism blocks, but its global coefficient representation faces the same limitation. We introduce Patch LegONet, which reuses pretrained mechanism blocks on smaller physical patches to resolve localized fine scales. The solution consists of a global background and local corrections. Mapping a fixed reference representation onto smaller patches increases local resolution without enlarging the blocks. The corrections join smoothly to the global background at patch boundaries. Differential operators are rescaled analytically to account for each patch's physical size. Nonlinear mechanisms are evaluated on the combined solution to include interactions between the background and local corrections. Patches can move, merge, or be removed during rollout while the pretrained patch blocks remain frozen. Six experiments on Allen-Cahn and viscous Burgers equations assess static, multiple, and moving patches in one to three dimensions. At comparable numbers of degrees of freedom, Patch LegONet consistently lowers the final relative solution error compared with global refinement. The reduction is approximately one order of magnitude in most tests. These results extend mechanism reuse across spatial scales and provide a practical route to local refinement in learned PDE solvers.

math.NA↗

Ultra Fast PDE Solving via Physics Guided Few-step Diffusion

Diffusion-based models have demonstrated impressive accuracy and generalization in solving partial differential equations (PDEs). However, their practical utility still suffers from high sampling costs and insufficient physical consistency, mainly due to many-step iterative sampling and insufficient physics guidance. To address these issues, we propose \emph{Phys-Instruct}, a physics-guided distillation framework that compresses a pre-trained diffusion PDE solver into a few-step generator while explicitly enforcing PDE consistency through distillation guidance. We reformulate the training objective as a constrained problem with PDE residual, and derive a score-function identity that leads to a practical physics-guided generator update. Across five PDE benchmarks, Phys-Instruct achieves orders-of-magnitude faster inference while reducing the PDE Error by factors of $2.4$ to $15.5$, compared with the corresponding 200-step EDM teachers. Moreover, the resulting unconditional student model functions as a compact prior, enabling efficient and physically consistent inference for various downstream conditional tasks. Our results indicate that Phys-Instruct is an effective and efficient framework for ultra-fast PDE solving powered by generative models.

cs.LG↗

Multiscale LegONet: Learning Coefficient-Dependent Local Spaces for Composable Multiscale Finite Elements with Localized Error Bounds

We introduce multiscale LegONet (Ms-LegONet), a plug-and-play learned block for heterogeneous elliptic problems. One network per spatial dimension is trained once on local coefficient patches and reused, without retraining, across coefficient layouts, sources, boundary data and domain sizes within the trained coefficient class. On a fixed primitive patch the network maps the local coefficient to a zero-boundary space, the only learned object. The multiscale basis functions are the harmonic extensions of a fixed set of boundary traces, each a Galerkin solve in that space. Shared interface traces enforce continuity, larger blocks are assembled by recursive static condensation without any parent-scale network, and a localized Céa bound attributes the error of the learned spaces primitive by primitive. The training labels are harmonic responses of single patches, so no global solve enters the training. Against MsFEM, GMsFEM, the neural-operator element method and an end-to-end Fourier neural operator, Ms-LegONet is the most accurate at equal unknowns: its $L^2$ error is $4$ to $150$ times below the baselines on two-dimensional mosaics of $256$ high-contrast primitives, and its median error stays within $0.1$ percentage points of that of exact local spaces in three-dimensional layered media. For each new coefficient it is $1.6$ to $2.3$ times faster than a fine-grid direct solve in two dimensions. In three dimensions it computes the many-query port response of a chain $30$ to $900$ times faster than finite element solves on the same or a finer mesh, at a relative error of $10^{-4}$ against their $6\%$ and $1.6\%$.

math.NA↗

Discrete Edge Multiscale Space based Hybrid Schwarz Preconditioner for High-Frequency Helmholtz Problems

In this work, we develop a novel hybrid Schwarz method, termed as edge multiscale space based hybrid Schwarz (EMs-HS), for solving the Helmholtz problem with large wavenumbers. The problem is discretized using $H^1$-conforming nodal finite element methods on meshes of size $h$ decreasing faster than $k^{-3/2}$ such that the discretization error can be bounded by the data uniformly with respect to $k$. EMs-HS consists of a one-level Schwarz preconditioner (RAS-imp) and a coarse solver in a multiplicative way. The RAS-imp preconditioner solves local problems on overlapping subdomains with impedance boundary conditions in parallel, and combines the local solutions using partition of unity. On the PDE level, this coarse space corresponds to an edge multiscale space proposed in {[S. Fu, G. Li, R. Craster, and S. Guenneau, \emph{Multiscale Model. Simul.}, 19(4):1684-1709, 2021]}. The approximation properties of this coarse space to the discrete solutions from the primal and adjoint problems are derived by a novel conforming Galerkin finite element method based upon a nonstandard variational formulation. This work represents the first theoretical analysis of an edge multiscale space at the discrete level. We prove that the EMs-HS preconditioner leads to a convergent fixed-point iteration uniformly for large wavenumbers, by rigorously analyzing the approximation properties of the coarse space to the global Helmholtz harmonic extension part and to the solution of the adjoint problem. We provide extensive numerical results on the sharpness of the theoretical findings and also demonstrate the method on challenging heterogeneous models.

math.NA↗

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators

Generative retrieval has emerged as a powerful paradigm for LLM-based recommendation. However, industrial recommender systems often benefit from restricting the output space to a constrained subset of items based on business logic (e.g. enforcing content freshness or product category), which standard autoregressive decoding cannot natively support. Moreover, existing constrained decoding methods that make use of prefix trees (Tries) incur severe latency penalties on hardware accelerators (TPUs/GPUs). In this work, we introduce STATIC (Sparse Transition Matrix-Accelerated Trie Index for Constrained Decoding), an efficient and scalable constrained decoding technique designed specifically for high-throughput LLM-based generative retrieval on TPUs/GPUs. By flattening the prefix tree into a static Compressed Sparse Row (CSR) matrix, we transform irregular tree traversals into fully vectorized sparse matrix operations, unlocking massive efficiency gains on hardware accelerators. We deploy STATIC on a large-scale industrial video recommendation platform serving billions of users. STATIC produces significant product metric impact with minimal latency overhead (0.033 ms per step and 0.25% of inference time), achieving a 948x speedup over a CPU trie implementation and a 47-1033x speedup over a hardware-accelerated binary-search baseline. Furthermore, the runtime overhead of STATIC remains extremely low across a wide range of practical configurations. To the best of our knowledge, STATIC enables the first production-scale deployment of strictly constrained generative retrieval. In addition, evaluation on academic benchmarks demonstrates that STATIC can considerably improve cold-start performance for generative retrieval. Our code is available at https://github.com/youtube/static-constraint-decoding.

cs.IR↗

OpticalRec: Unified Optical Vision-Language Representation for Multimodal Recommendation

Recent advances in vision-language modeling have substantially improved multimodal encoding, retrieval and reasoning. Yet for multimodal recommendation, encoding rich item vision-language semantic interactions remains a long-standing bottleneck, which hampers accurate item representation learning and user-item matching. Mainstream approaches primarily adopt independent encoding of vision and language modality followed by rigid late fusion such as concatenation, inherently omitting native vision-language interactions and introducing cross-modal semantic distortion. To address this challenge, we propose OpticalRec, the first visual-space unified encoding paradigm for multimodal collaborative filtering, a fundamental recommendation setting. Instead of isolated modality-specific encoding, OpticalRec renders item textual metadata as visual glyphs, enabling native image-text interaction within the visual encoder - the perceptual encoding level. The resulting representations are further processed by the language decoder - the semantic encoding level, allowing OpticalRec to exploit the dual-attention mechanism of modern vision-language models that previous encoding methods omitted. OpticalRec's efficacy is theoretically supported by mutual information analysis and empirically demonstrated through superior performance across strong baselines and benchmarks. As a plug-and-play module, OpticalRec (1) introduces minimal cost, (2) is robust against rendered text font, color and layout, etc., and (3) integrates seamlessly into existing multimodal collaborative filtering models.

cs.IR↗

SIPO: Unifying Reinforcement Learning with On-Policy Self-Distillation

Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for improving large language models (LLMs) on various tasks, yet its sparse outcome rewards lack token-level credit assignment for intermediate steps. To address this, on-policy self-distillation (OPSD) leverages a self-teacher with privileged context to provide additional dense learning signals. However, because the self-teacher is often overconfident and imposes excessive penalties on long reasoning trajectories, OPSD frequently struggles in practice. To mitigate this, we propose self-instructing policy optimization (SIPO) with a contrastive self-teacher to provide dense credit. At each iteration, SIPO samples multiple rollouts per prompt from the current policy, scores them with environment rewards, and constructs two teacher contexts for each rollout by pairing the reference answer with mistakes made within the group. The model then re-evaluates its own responses under both contexts, using the difference between the two teacher log-probabilities as token-level feedback, so that biases shared by both contexts are expected to largely cancel. The resulting objective yields a token-level advantage for every rollout: the reward still sets the main direction of each update while the self-teacher redistributes credit across tokens. Even in groups where every rollout fails and group-relative advantages vanish, SIPO still provides a learning signal. By preserving direct optimization of the task reward while providing dense, token-level feedback, this approach bridges reinforcement learning and on-policy self-distillation. Extensive experiments across multiple reasoning and code-generation benchmarks demonstrate that SIPO outperforms both RLVR and OPSD baselines without an external teacher or additional generation.

cs.AI↗

Mend the Measurement Gap: Latent User Preference Modeling for Short-Form Video Recommendation

Recommender systems rely heavily on heterogeneous behavioral feedback to infer user preference. Although abundant, these signals are imperfect measurements: the same observed behavior can arise from different underlying states, such as genuine enjoyment, passive consumption, or inattention. The challenge is especially acute in short-form video, where watch-based signals are strongly affected by measurement confounders such as video duration - the same watch time can imply different levels of preference for videos of different lengths, while ratio-based metrics can systematically favor short videos. As a result, optimizing raw engagement can amplify measurement artifacts rather than improving user value. We propose a Factorized Latent Value Model (FLVM) for measuring user preference from heterogeneous behavioral feedback. The model treats observed behaviors as noisy measurements of a low-dimensional, factorized latent value state and uses structured output heads to model heterogeneous feedback signals. A restricted baseline path captures predictable variation from measurement-confounding features such as video duration, user propensity, and session context, while a routed latent path estimates preference-relevant value advantage. The resulting latent value score can be integrated into an existing recommender system as a ranking feature or ranking score. On YouTube Shorts, a major short-form video platform, this model improves offline metrics and lifts a primary viewer enjoyment metric by 2.67% in online A/B tests.

cs.IR↗

Geometry-aware LegONet for PDE Learning on Arbitrary Domains

Learned PDE solvers often entangle governing operators with the geometry, boundary conditions, and discretization used for training. This limits reuse when the same physics is posed on new domains, and it also makes physical-law discovery geometry-dependent. We introduce Geometry-aware LegONet (gLegONet), a boundary-manifold extension of Lego-like operator learning. Physical mechanisms are pretrained once as modular variational blocks on an ambient spectral domain. For a target geometry, sampled boundary constraints define an affine admissible manifold. Its mass-orthonormal tangent coordinates are used to evolve the dynamics and evaluate candidate law-discovery features directly. Changing the domain therefore changes only an algebraic coordinate interface, not the learned operator blocks. This converts arbitrary-domain PDE learning from geometry-specific retraining or soft penalty enforcement into boundary-guaranteed assembly of reusable mechanisms. In forward simulations and sparse identification tests on unseen domains, the method maintains boundary residuals near the algebraic tolerance and yields predictive governing laws from short-time observations.

math.NA↗

Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs

Video Large Language Models (Video LLMs) incur high inference latency due to a large number of visual tokens provided to LLMs. To address this, training-free visual token pruning has emerged as a solution to reduce computational costs; however, existing methods are primarily validated on Multiple-Choice Question Answering (MCQA) benchmarks, where coarse-grained cues often suffice. In this work, we reveal that these methods suffer a sharp performance collapse on fine-grained understanding tasks requiring precise visual grounding, such as hallucination evaluation. To explore this gap, we conduct a systematic analysis and identify sink tokens--semantically uninformative tokens that attract excessive attention--as a key obstacle to fine-grained video understanding. When these sink tokens survive pruning, they distort the model's visual evidence and hinder fine-grained understanding. Motivated by these insights, we propose Sink-Token-aware Pruning (SToP), a simple yet effective plug-and-play method that introduces a sink score to quantify each token's tendency to behave as a sink and applies this score to existing spatial and temporal pruning methods to suppress them, thereby enhancing video understanding. To validate the effectiveness of SToP, we apply it to state-of-the-art pruning methods (VisionZip, FastVid, and Holitom) and evaluate it across diverse benchmarks covering hallucination, open-ended generation, compositional reasoning, and MCQA. Our results demonstrate that SToP significantly boosts performance, even when pruning up to 90% of visual tokens.

cs.LG↗

Numerical homogenization for indefinite time-harmonic Maxwell equations

We propose a novel numerical homogenization method based on the edge multiscale approach for solving indefinite time-harmonic Maxwell equations in heterogeneous media with large wavenumber. Numerical methods for these equations in homogeneous media with high wavenumber are particularly challenging due to the so-called pollution effect: the mesh size must be significantly smaller than the reciprocal of the wavenumber to achieve a desired accuracy. This challenge is amplified in heterogeneous media, which frequently occur in practical applications such as metamaterial simulations, since resolving the heterogeneity is necessary for obtaining reliable solutions. Our approach overcomes this difficulty by avoiding explicit resolution of the heterogeneity, while employing a mesh size that depends almost linearly on the reciprocal of the wavenumber. The approximation properties and stability of the method rely critically on the development and rigorous analysis of a novel, nonstandard variational formulation, which constitutes the main innovation of this work. Extensive numerical experiments are provided to validate our theoretical findings.

math.NA↗

True random number generation through stochastic magnonic bistability

True random number generators (TRNGs) underpin modern cryptography, yet existing implementations face fundamental trade-offs between speed, scalability, and entropy quality. Here, we demonstrate that stochastic switching in the bistable regime of spin-wave dynamics provides a physical entropy source for high-quality random number generation. Our magnonic random number generator (mRNG), based on a lithography-patterned microstrip on yttrium iron garnet (YIG), exploits thermal fluctuations near the nonlinear bistable regime to generate random bitstreams that pass all 15 NIST SP 800-22 statistical tests at rates with 20 Mb/s. We implement a random-bit multiplier using synchronized mRNG units and demonstrate scalability to 200-nm-wide nanoscale waveguides, establishing spin-wave bistability as a viable physical entropy source for integrated random number generation.

cond-mat.mtrl-sci↗

LegONet: Plug-and-Play Structure-Preserving Neural Operator Blocks for Compositional PDE Learning

Learned PDE solvers are often trained as monolithic surrogates for a specific equation, boundary condition and discretization. This makes them difficult to reuse when mechanisms change and it can limit stability under long-horizon rollout. We introduce Lego-like Operator Network (LegONet), a compositional framework that builds PDE solvers from plug-and-play, structure-preserving operator blocks defined on shared boundary-adapted spectral representations. LegONet separates boundary handling from mechanism learning, satisfying boundary conditions by construction. It also separates mechanism learning from time integration, enabling pretrained blocks to be assembled into new solvers without retraining. We also derive a finite-horizon error decomposition that separates block mismatch from splitting error and provides mechanism-level diagnostics for long-horizon predictions. Across ten time-dependent PDEs, LegONet delivers accurate closed-loop rollouts with improved stability under cross-PDE recombination and boundary reconfiguration. More broadly, this modular formulation suggests a path from task-specific neural solvers towards plug-and-play operator libraries for scientific computing.

math.NA↗

FASA: Frequency-aware Sparse Attention

The deployment of Large Language Models (LLMs) faces a critical bottleneck when handling lengthy inputs: the prohibitive memory footprint of the Key Value (KV) cache. To address this bottleneck, the token pruning paradigm leverages attention sparsity to selectively retain a small, critical subset of tokens. However, existing approaches fall short, with static methods risking irreversible information loss and dynamic strategies employing heuristics that insufficiently capture the query-dependent nature of token importance. We propose FASA, a novel framework that achieves query-aware token eviction by dynamically predicting token importance. FASA stems from a novel insight into RoPE: the discovery of functional sparsity at the frequency-chunk (FC) level. Our key finding is that a small, identifiable subset of "dominant" FCs consistently exhibits high contextual agreement with the full attention head. This provides a robust and computationally free proxy for identifying salient tokens. Building on this insight, FASA first identifies a critical set of tokens using dominant FCs, and then performs focused attention computation solely on this pruned subset. Across a spectrum of long-context tasks, from sequence modeling to complex CoT reasoning, FASA consistently outperforms all token-eviction baselines and achieves near-oracle accuracy, demonstrating remarkable robustness even under constraint budgets. Notably, on LongBench-V1, FASA reaches nearly 100\% of full-KV performance when only keeping 256 tokens, and achieves 2.56$\times$ speedup using just 18.9\% of the cache on AIME24.

cs.CL↗

A POD-DeepONet Framework for Forward and Inverse Design of 2D Photonic Crystals

We develop a reduced-order operator-learning framework for forward and inverse band-structure design of two-dimensional photonic crystals with binary, pixel-based $p4m$-symmetric unit cells. We construct a POD--DeepONet surrogate for the discrete band map along the standard high-symmetry path by coupling a POD trunk extracted from high-fidelity finite-element band snapshots with a neural branch network that predicts reduced coefficients. This architecture yields a compact and differentiable forward model that is tailored to the underlying Bloch eigenvalue discretization. We establish continuity of the discrete band map on the relaxed design space and prove a uniform approximation property of the POD--DeepONet surrogate, leading to a natural decomposition of the total surrogate error into POD truncation and network approximation contributions. Building on this forward surrogate, we formulate two end-to-end neural inverse design procedures, namely dispersion-to-structure and band-gap inverse design, with training objectives that combine data misfit, binarity promotion, and supervised regularization to address the intrinsic non-uniqueness of the inverse mapping and to enable stable gradient-based optimization in the relaxed space. Our numerical results show that the proposed framework achieves accurate forward predictions and produces effective inverse designs on practical high-contrast, pixel-based photonic layouts.

physics.optics↗

Reduced-Basis Deep Operator Learning for Parametric PDEs with Independently Varying Boundary and Source Data

Parametric PDEs power modern simulation, design, and digital-twin systems, yet their many-query workloads still hinge on repeatedly solving large finite-element systems. Existing operator-learning approaches accelerate this process but often rely on opaque learned trunks, require extensive labeled data, or break down when boundary and source data vary independently from physical parameters. We introduce RB-DeepONet, a hybrid operator-learning framework that fuses reduced-basis (RB) numerical structure with the branch-trunk architecture of DeepONet. The trunk is fixed to a rigorously constructed RB space generated offline via Greedy selection, granting physical interpretability, stability, and certified error control. The branch network predicts only RB coefficients and is trained label-free using a projected variational residual that targets the RB-Galerkin solution. For problems with independently varying loads or boundary conditions, we develop boundary and source modal encodings that compress exogenous data into low-dimensional coordinates while preserving accuracy. Combined with affine or empirical interpolation decompositions, RB-DeepONet achieves a strict offline-online split: all heavy lifting occurs offline, and online evaluation scales only with the RB dimension rather than the full mesh. We provide convergence guarantees separating RB approximation error from statistical learning error, and numerical experiments show that RB-DeepONet attains accuracy competitive with intrusive RB-Galerkin, POD-DeepONet, and FEONet while using dramatically fewer trainable parameters and achieving significant speedups. This establishes RB-DeepONet as an efficient, stable, and interpretable operator learner for large-scale parametric PDEs.

cs.LG↗

PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations

Large Language Models (LLMs) pose a new paradigm of modeling and computation for information tasks. Recommendation systems are a critical application domain poised to benefit significantly from the sequence modeling capabilities and world knowledge inherent in these large models. In this paper, we introduce PLUM, a framework designed to adapt pre-trained LLMs for industry-scale recommendation tasks. PLUM consists of item tokenization using Semantic IDs, continued pre-training (CPT) on domain-specific data, and task-specific fine-tuning for recommendation objectives. For fine-tuning, we focus particularly on generative retrieval, where the model is directly trained to generate Semantic IDs of recommended items based on user context. We conduct comprehensive experiments on large-scale internal video recommendation datasets. Our results demonstrate that PLUM achieves substantial improvements for retrieval compared to a heavily-optimized production model built with large embedding tables. We also present a scaling study for the model's retrieval performance, our learnings about CPT, a few enhancements to Semantic IDs, along with an overview of the training and inference methods that enable launching this framework to billions of users in YouTube.

cs.IR↗

LLM-Powered Nuanced Video Attribute Annotation for Enhanced Recommendations

This paper presents a case study on deploying Large Language Models (LLMs) as an advanced "annotation" mechanism to achieve nuanced content understanding (e.g., discerning content "vibe") at scale within a large-scale industrial short-form video recommendation system. Traditional machine learning classifiers for content understanding face protracted development cycles and a lack of deep, nuanced comprehension. The "LLM-as-annotators" approach addresses these by significantly shortening development times and enabling the annotation of subtle attributes. This work details an end-to-end workflow encompassing: (1) iterative definition and robust evaluation of target attributes, refined by offline metrics and online A/B testing; (2) scalable offline bulk annotation of video corpora using LLMs with multimodal features, optimized inference, and knowledge distillation for broad application; and (3) integration of these rich annotations into the online recommendation serving system, for example, through personalized restrict retrieval. Experimental results demonstrate the efficacy of this approach, with LLMs outperforming human raters in offline annotation quality for nuanced attributes and yielding significant improvements of user participation and satisfied consumption in online A/B tests. The study provides insights into designing and scaling production-level LLM pipelines for rich content evaluation, highlighting the adaptability and benefits of LLM-generated nuanced understanding for enhancing content discovery, user satisfaction, and the overall effectiveness of modern recommendation systems.

cs.IR↗