Search arXiv⌕ Search

arXiv subjects

Xu Yang

Publications and source records attributed to Xu Yang.

At least 19 recordsLinked to original sources
arXiv2026

Neural Compression of Long ADMM Trajectory for Multiparametric Quadratic Program

Solving large-scale multiparametric quadratic programs (mpQPs) in real time often requires thousands of iterative optimization updates, creating a major computational bottleneck in model predictive control and learning-enabled systems. This paper proposes TQPNet, a self-supervised neural compression framework that learns to compress long ADMM optimization trajectories into a compact neural warm start followed by a few refinement iterations. We derive a low-dimensional ADMM scheme operating on the primal-dual variables $(x,β)$ and show that its iteration admits an equivalent ReLU-layer representation, termed ADMM(ReLU). Building on this insight, TQPNet combines a multilayer perceptron with ReLU activations (MLP(ReLU)) and a small number of unrolled ADMM(ReLU) refinement layers. The network is trained offline using an optimality-condition-informed residual loss, eliminating the need for solver-generated labels. The proposed residual-based framework enables both self-supervised training and online solution certification through adaptive ADMM(ReLU) refinement. Experiments on large-scale mpQPs and real-time MPC applications demonstrate that TQPNet achieves high accuracy, strong generalization, and substantially faster inference than conventional optimization-based methods.

math.OC↗
arXiv2026

High-resolution tactile observation makes hidden racket-control mechanisms learnable

Experts can master fine hand-object manipulation skills, yet limited conscious perception of rapid tactile interactions hinders their ability to articulate the underlying control mechanisms. Badminton racket control requires rapid, fine hand-force coordination, providing a demanding testbed for uncovering these mechanisms. An 864-node tactile-inertial glove with synchronized 100-Hz acquisition recorded over 14,000 strokes from more than 70 participants across five skills. Inspired by sensorimotor control, our mechanics-grounded two-layer framework inferred object-driving and grip-stabilizing control from tactile history, while resolving their spatiotemporal force realization. We found that higher proficiency was associated with selective rather than extensive control: greater skill specificity, anticipatory regulation, focal distal modulation and lower geometric torque cancellation, while spatiotemporal coordination showed a non-monotonic acquire-refine pattern. We translated these mechanisms into personalized guidance targeting force control and force-motion coordination. In a randomized cohort, mechanism-guided learners gained 0.72 expert-rated skill levels versus 0.05 with level-only feedback, making control mechanisms actionable.

cs.LG↗
arXiv2026

Current-Sheet Formation in Electron Magnetohydrodynamics with Split Fractional Dissipation

Thin current sheets are central small-scale structures in electron magnetohydrodynamics (EMHD), closely associated with energy dissipation and fast magnetic reconnection at electron scales. We study their formation numerically in a $2\frac{1}{2}$-dimensional EMHD system on a periodic domain with split fractional dissipation, where the magnetic potential and the vertical magnetic component are damped separately. The local theory is governed by a symmetric combined damping balance, but the numerical onset of small-scale growth need not follow this symmetry. A scaling analysis identifies the out-of-plane current as the primary concentration observable, since it is regularized only through the magnetic-potential equation. Using a validated Fourier pseudospectral exponential time-differencing solver with resolution-controlled diagnostics, we find a clear decay/concentration dichotomy. The onset boundary is markedly asymmetric: current-sheet formation appears to be controlled mainly by damping of the magnetic potential, rather than by the combined damping strength. The analyticity strip collapses to the grid scale, the concentration sharpens under grid refinement, and the observed growth is consistent with an energy-critical self-similar rate, with exponent near three. These experiments indicate that magnetic-potential damping is the apparent binding constraint for current-sheet concentration, refining the symmetric sum picture.

physics.plasm-ph↗
arXiv2026

A Continuous-Time Actor-Critic Framework for Jump-Diffusion Controls with Normalizing Flows

Continuous-time stochastic control with time-inhomogeneous jump-diffusion dynamics is central in finance and economics, but computing optimal policies is difficult under explicit time dependence, discontinuous shocks, and high dimensionality. We propose an actor-critic framework that serves as a mesh-free solver for entropy-regularized control problems and stochastic games with jumps. The approach is built on a time-inhomogeneous little q-function and an appropriate occupation measure, yielding a policy-gradient representation that accommodates time-dependent drift, volatility, and jump terms. To represent expressive stochastic policies in continuous-action spaces, we parameterize the actor using conditional normalizing flows, enabling flexible non-Gaussian policies while retaining exact likelihood evaluation for entropy regularization and policy optimization. We validate the method on time-inhomogeneous linear-quadratic control, Merton portfolio optimization, and a multi-agent portfolio game, using explicit solutions or high-accuracy benchmarks. Numerical results demonstrate stable learning under jump discontinuities, accurate approximation of optimal stochastic policies, and favorable scaling with respect to dimension and number of agents.

math.OC↗
arXiv2026

ManimAgent: Self-Evolving Multimodal Agents for Visual Education

Multi-round reflection lets agents built on large language models recover from failures within a single task, but each task remains an isolated episode: lessons learned across many reflection rounds on one task are discarded before the next begins. We study this gap on a code-generation task: from a scientific paper section, the agent writes Python in the open-source Manim library to render a mathematical animation. We present ManimAgent, a self-evolving multimodal agent that carries reflection experience across tasks through a dual-channel Episodic Memory Bank grown entirely from its own task stream, with no weight updates and no human seeds. After each animation converges, a vision-language model scores the rendered keyframes; the resulting signals populate a positive channel M+ that stores success rationales as soft Reference Examples, and a negative channel M- that stores validated failure patterns as hard Known Pitfalls. On a fixed-probe evaluation against no-memory, matched-budget retrieval-augmented generation, and shuffled-memory baselines, blind human Pass@1 rises and reflection rounds fall as memory size grows.

cs.AI↗
arXiv2026

TrajCFG: Token-Wise Classifier-Free Guidance via Denoising Trajectory Feedback

Classifier-free guidance (CFG) typically applies a shared scale to all latent tokens, although their velocity predictions evolve differently during sampling. We introduce Trajectory-Adaptive Classifier-Free Guidance (TrajCFG), a training-free method for flow-matching models that adapts token-wise guidance using historical changes in guided velocity direction. TrajCFG maps this feedback to bounded scales, assigning stronger guidance to larger directional changes and weaker guidance to more consistent directions. It combines adjacent-step and interval-normalized longer-span feedback, reusing standard CFG predictions without additional model evaluations. Controlled diagnostics and ablations examine the roles of directional feedback, token-wise allocation, and history-span fusion. Experiments on text-to-video, image-to-video, text-to-audio-video, text-to-image, and image-to-3D generation show improvements over base samplers across multiple backbones. For text-to-video generation, TrajCFG improves VBench Total scores by 0.30-0.75 points over the strongest evaluated baseline on each of three backbones. These results support historical directional feedback as a broadly applicable signal for fine-grained guidance allocation. The project page is available at https://jyliu-98.github.io/trajcfg-project-page/.

cs.CV↗
arXiv2026

Realtime-Bench: Can Frontier Models Solve Real-time Interactive Problems?

Real-time interaction requires agents to perceive evolving environments and act under temporal constraints, yet existing evaluations of real-time streaming models focus on conversational quality and streaming perception, leaving effective action under strict temporal constraints untested. We introduce Realtime-Bench, a suite of carefully curated dynamic tasks where delayed actions directly affect success. Under Wall Clock, where environments advance according to actual inference latency, the best success rate reaches only 44% and the best Pass^3 is only 36%, demonstrating that real-time interaction remains challenging. To separate serving latency from models' real-time streaming capability, we compare Wall Clock with Paused Clock, which removes inference delays as an idealized reference, and introduce Token Clock, which advances simulated time according to generated token counts, testing temporal awareness independently of physical serving speed. We find that temporal costs limit success in evolving environments and that higher reasoning effort has mixed effects under time pressure, reflecting a trade-off between decision quality and timely execution. Based on these results, we discuss future directions for improving real-time multimodal models, including adaptive reasoning with temporal awareness and continuous perception and action.

cs.AI↗
arXiv2026

CUA-Recovery: Benchmarking Error Recovery in Long-Horizon Computer-Use Agents

As computer-use agents (CUAs) move to long-horizon workflows spanning multiple applications, undetected errors can silently corrupt persistent state and cause cascading failures in subsequent actions. Reliable error detection and recovery have become critical bottlenecks for building robust CUAs. However, existing benchmarks focus primarily on end-to-end task performance, providing limited insight into whether agents can detect and recover from errors during execution. The few benchmarks that evaluate recovery rely largely on manually injected errors, which may not reflect the types or horizons of failures induced by real agent policies. We introduce CUA-Recovery, a benchmark comprising test and training suites across multiple desktop applications. We construct it using ReRail, a framework for synthesizing long-horizon tasks and trajectories in a persistent desktop environment. ReRail composes MyPCBench tasks into new long-horizon workflows with executable ground truth, collects verifier-confirmed failures from multiple policies, and turns them into verified recovery trajectories. CUA-Recovery comprises a human-verified test suite of 2,250 erroneous states over 100 tasks and a training suite of 8.6K trajectories over 377 tasks. Evaluation on the test suite shows that agents struggle both to recognize inherited errors and to complete the task. Across six agents and six takeover depths, Error Awareness Rate (EAR) reaches at most 44.0% and Pass@3 at most 25.5%. After fine-tuning Qwen3.5-35B-A3B on the training suite, its average EAR rises from 19.9% to 35.2% on held-out recovery states, and its Rubric Score goes from 5.0% to 16.1%. It also gains 15.3 points on MyPCBench and 10.8 points on Odysseys for Pass@3, showing that the training trajectories help both with recovery and with completing tasks from a clean start. Our code is available at https://github.com/xu-hu-2002/CUA-Recovery.

cs.AI↗
arXiv2026

PhyPro-FM: A Physics and Prompt-Guided Graph Foundation Model for Contingency Analysis

The continuous evolution of next-generation power systems, characterized by the high penetration of renewable energy resources and dynamic topology variations, poses formidable challenges to traditional N-1/N-2 contingency analysis in terms of computational efficiency and scalability. While deep learning-based methods offer accelerated inference, existing studies predominantly treat contingency analysis as a pure regression problem, often overlooking the physical essence of grid operation and engineering requirements of real-world scenarios. To bridge this gap, this paper proposes a physics and prompt-guided graph foundation model (PhyPro-FM) for generalizable and engineering-viable contingency analysis. The proposed architecture integrates graph neural networks with a learnable global query mechanism and, notably, introduces a prompt-guided learning paradigm. By leveraging historical snapshots as few-shot prompts, the model dynamically captures correlations between target and historical operating conditions, significantly enhancing generalization capabilities under unseen topologies. Furthermore, we design a physics-informed training mechanism that prioritizes branch power flow errors over nodal voltage errors, aligning the optimization objective with critical grid security constraints. To ensure engineering applicability, a physics-informed inference mechanism is also developed, incorporating a residual-based correction module and a specialized post-processing strategy for singular branches to circumvent numerical instability. Comprehensive experiments demonstrate that PhyPro-FM outperforms state-of-the-art methods in accuracy and generalization, validating its superior physical consistency and robustness for practical engineering applications.

eess.SY↗
arXiv2026

Bridging Scales: Asymptotic Analysis and AI-Assisted Formalization

Asymptotic analysis is one of the classical tools for bridging models across scales. Behind many such derivations lies a common symbolic structure: an ansatz, a substitution, an order-by-order matching procedure, and the extraction of effective equations or interface conditions. This article revisits that structure through two representative bridges: the kinetic-to-fluid limit, illustrated by radiative transfer with interface layers and by neural-network approximations of Boltzmann equations, and the quantum-to-classical limit, illustrated by the Frozen Gaussian Approximation and its Dirac extension. We then explain why such derivations are natural candidates for AI-assisted formalization: their recurring symbolic structures can be organized, verified, and reused. In this sense, a carefully structured expository paper may serve not only as a review, but also as a mathematical seed for future AI-assisted environments.

math.NA↗
arXiv2026

Amora: Communication-Efficient Private Approximate Nearest Neighbors Search

Approximate nearest neighbors search (ANNS) over cloud-hosted vector databases raises a critical privacy concern: the query vector, which often encodes sensitive user intent, is exposed to the server. Private ANNS (PANNS) allows a client to retrieve nearest neighbors without revealing its query. The state-of-the-art single-server scheme, Pacmann (ICLR'25), achieves high accuracy via graph-based search with private information retrieval (PIR), but incurs substantial communication overhead because each PIR query retrieves only a single vertex. We present Amora, a communication-efficient PANNS system that applies SimplePIR to a partitioned graph index so that one PIR query is amortized over many vertices. To retrieve as much of the distance and neighbor information the search needs under a limited communication budget, Amora adopts a dual-PIR split layout with two heterogeneous PIR matrices that stay balanced in dimension: VecPIR retrieves inner products for an entire partition of vertices as their distance at once, while NbrPIR retrieves necessary neighbor lists at subgroup granularity for graph traversal. This layout shifts the cost model of PIR query from per-vertex to per-partition, which significantly reduces the communication overhead. To further improve efficiency by reducing the number of scans and query rounds in the PIR database, Amora introduces batch PIR to pack multiple queries into one matrix multiplication, centroid-based pruning to filter unpromising partitions, and TopCand exploration that seeds jump-style graph navigation with the closest vertices from each retrieved partition. We evaluate Amora on five datasets spanning 96 to 1024 dimensions and up to 10 million vectors. Compared to Pacmann, Amora reduces online communication by 93--99% while achieving higher search accuracy.

cs.DB↗
arXiv2026

Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events

Video multimodal large language models (MLLMs) have made rapid progress in general and long-form video understanding, yet their ability to capture and use brief, answer-critical visual evidence remains underexplored. Momentary actions or state transitions may determine an answer while occupying only a small fraction of the video. Performance on broad video understanding tasks alone does not establish whether models can reliably identify and use this temporally localized evidence. We introduce Moment-Video, a benchmark for evaluating temporal fidelity through momentary visual event understanding. Questions are constructed around visually observable events or event sequences, requiring models to notice, count, describe, or reason about transient evidence. The benchmark contains 1,000 human-verified video-QA pairs across seven domains and 25 subcategories, covering four tasks: Temporal Occurrence, Temporal Counting, Action Description, and Temporal Reasoning. We evaluate 34 proprietary and open-source MLLMs. Under the main evaluation settings, the best-performing model, Seed-2.0-Pro, achieves 39.6% overall accuracy, while most open-source models remain below 25%. Diagnostic analyses show that denser frame sampling improves some models, but substantial errors persist even when sampled frames cover all annotated necessary event intervals in an audited subset. Performance also declines on longer videos, suggesting additional temporal-localization challenges. By exposing these limitations, Moment-Video provides a diagnostic benchmark to guide the evaluation and development of video MLLMs that more reliably understand brief, answer-critical visual events.

cs.CV↗
arXiv2026

TreeGraft: Adaptive Multi-Drafter Grafting for Tree-Based Speculative Decoding

Speculative decoding accelerates large language model inference through a draft-then-verify paradigm. Building on this, tree-structured methods improve inference by organizing proposals into multiple candidate paths, increasing the accepted length. However, existing tree-structured methods use a single drafter for all drafting steps, creating a dilemma: a smaller drafter is fast but yields lower-quality trees, whereas a larger drafter improves tree quality but suffers from high latency. To address this, we propose TreeGraft, a multi-drafter framework in which drafters of different costs jointly construct a shared draft tree. TreeGraft uses the stronger drafter to rescore candidates by updating scores assigned by the weaker drafter, reselect grafting positions, and recover promising paths left unexplored. It also integrates stronger drafter expansions non-destructively, preserving existing branches that may still be accepted by the target model. Together, these designs improve the quality of the shared draft tree. To control the drafting cost, TreeGraft introduces a lightweight scheduler distilled from an offline value system to decide when to call the stronger drafter. Across 10 model pairs and 6 benchmarks, TreeGraft outperforms the better of the two fixed single-drafter endpoint strategies by 15.1% on average, reaching a maximum gain of 26.6%. Our code is available at https://github.com/fjm9933/TreeGraft.

cs.CL↗
arXiv2026

Frequency Routing and Identity Conditioning for Thermal-to-Visible Face Translation

Thermal-to-visible (T2V) face translation has important applications in nighttime biometric recognition, low-light surveillance, and human interpretation of thermal observations. The task remains challenging because thermal images do not directly record visible appearance, while the cross-spectral cues useful for reconstruction vary across frequency components and semantic roles. Existing spatially conditioned models tend to process these cues through a homogeneous adaptation path and do not explicitly separate local structure from global identity. We propose FreqID-Control, a parameter-efficient framework that organizes thermal guidance according to spectral reliability and semantic role while preserving the pretrained generative prior. It combines frequency-routed low-rank adaptation, which allocates separate transformation subspaces to low-frequency structure and high-frequency detail, with shared cross-spectral identity conditioning, which supplies compact global identity tokens independently of spatial thermal tokens. A controlled analysis on MCXFace and SpeakingFaces provides the empirical basis for this design, revealing stable low-frequency correspondence and edge-localized detail correspondence. Experiments on both datasets demonstrate strong image fidelity and biometric identity preservation, while controlled ablations on MCXFace confirm the complementary contributions of frequency routing and shared identity conditioning.

cs.CV↗
arXiv2026

AlignPred: Error-Controlled KV Cache Compression via Alignment and Predictive Coding

Long-running agents retain KV caches across turns and sessions for hours or days. Compressing these persistent caches requires reducing storage while controlling reconstruction error. We present AlignPred, a codec that combines local alignment with predictive coding under a configurable KV reconstruction-error budget. Local orthogonal transforms align related heads or layers into a common coordinate frame, allowing AlignPred to combine token-wise prediction with same-token prediction across heads or layers. Residuals are quantized on an error-bounded lattice and entropy-coded, without learned predictors, encoder-side mode search, or large joint transforms. Across three attention mechanisms, AlignPred requires less storage than the evaluated baselines at comparable measured reconstruction error. Against the evaluated CPU codec implementations, it decodes at least 1.6 times faster while matching or improving encode time. AlignPred achieves near-native task scores at substantially compressed operating points on LongBench-Pro at 128K context. AlignPred's SGLang HiCache integration reduces persistent target-KV storage by 42-72% relative to native HiCache, with comparable latency.

cs.PF↗
arXiv2026

FleetGuard:Identity-Capped Conformal Risk Allocation for Reliable UAV Edge-Cloud Offloading

Compromised UAV reporters can poison latency telemetry and attract offloaded tasks to degraded servers. We present FleetGuard, an identity-capped conformal offloader for local, edge, and cloud execution. With equal buffers of m scores and a cap of K compromised identities, a Km rank correction retains one-sided fixed-level coverage without an honest-reporter majority. A deterministic repair scheduler allocates task-specific risk under fleet, capacity, and deadline constraints. Heavy-tailed simulations with eight reporters, four edges, 30 independent seeds, and 20 batches per seed and condition yield 2.08% deadline misses under seven low-score compromised reporters (95% clustered interval: 1.94-2.24%), compared with approximately 9.6% for pooled conformal, reporter-median, and mean rules. FleetGuard saves 22.3% energy over fixed-risk BRC and approaches adaptive exact assignment within 1.1%, with 2.6x lower mean scheduling time.

cs.CE↗
arXiv2026

Hear the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generation

Recent joint video-audio generation models have achieved strong semantic correspondence and temporal synchronization. However, applications such as AR/VR and interactive gaming further require stereo audio to provide an immersive sense, which remains largely overlooked. Effective stereo audio requires the perceived sound location to evolve consistently with the motion of its corresponding visual source. We refer to this property as Dynamic Spatial Correspondence and propose StereoBind, a framework that binds visual source motion to stereo sound generation. StereoBind uses motion tracks to coordinate visual motion and stereo audio through three complementary mechanisms. Visual Motion Binding establishes source-aware audiovisual correspondence, the Spatial Track Encoder captures absolute source positions, and Residual Track RoPE models relative motion. For supervision and evaluation, we construct StereoWorld-29K, a large-scale stereo audio-video dataset with paired motion tracks, and StereoWorldBench for measuring audiovisual spatial consistency. Experiments show that StereoBind substantially improves spatial alignment in stereo audio generation over existing models while preserving overall audiovisual quality.

cs.CV↗
arXiv2026

Invariant Measures for Interacting Continuous-State Population Models

We study invariant probabilities for nonlinear two-population branching systems with competition, cooperation, or predator--prey interaction, driven by Brownian noise and spectrally positive stable jumps. Without immigration, every invariant probability of a conservative competitive or predator--prey system is concentrated on the boundary under either boundary convention. With nontrivial axis dynamics, coordinatewise continuation admits only the point mass at the origin. For cooperative systems, we give criteria for boundary concentration and interior stationarity, including a sharp criterion for bilinear cooperation with a common relative noise exponent. With immigration, explicit parameter conditions yield existence and stationary moment bounds. For square-root diffusions with positive immigration, these conditions ensure interior concentration and full support on the closed quadrant. Further lower bounds on immigration rates give uniqueness and convergence of time-averaged transition laws.

math.PR↗