Search arXiv⌕ Search

arXiv subjects

Chen Zhang

Publications and source records attributed to Chen Zhang.

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

FoleyGenEx: Unified Video-to-Audio Generation with Multi-Modal Control, Temporal Alignment, and Semantic Precision

We present FoleyGenEx, a unified video-to-audio (VTA) framework integrating multi-modal control, frame-level temporal alignment, and fine-grained semantics, enabling synchronized, versatile audio synthesis for diverse tasks. Existing VTA methods either have multi-modal control but weak temporal alignment or strong alignment but lack reference audio conditioning and semantic precision. FoleyGenEx fills this gap via three core innovations: a conditional injection mechanism for audio-controlled VTA and Foley extension, a multi-modal dynamic masking strategy preserving training synchronization, and an adverb-based data augmentation algorithm leveraging signal processing and large language models to enhance textual supervision with nuanced semantics. Experiments on AudioCaps, VGGSound, and Greatest Hits demonstrate its competitive controllable VTA performance against existing methods. Demo samples are available at https://foleygenex.github.io/FoleyGenEx.

cs.SD↗
arXiv2026

Generalist Representation, Specialist Detection: TS-Router for Time-Series Anomaly Detection

Time-series anomaly detection (TSAD) is difficult to generalize across datasets because heterogeneous temporal dynamics imply different notions of normality and favor different detection criteria. While time-series foundation models provide transferable representations, coupling them with a fixed anomaly-scoring mechanism can overlook this variation. This motivates a different perspective on foundation-model-based TSAD: using foundation models to coordinate specialized anomaly criteria rather than directly imposing a universal one. Based on this view, we propose \textbf{TS-Router}, a generalist-representation, specialist-detection framework that estimates the relative competence of heterogeneous anomaly detectors from pretrained temporal representations and selects suitable specialists for each target series. To avoid relying on specialist-performance labels from real tasks, we derive soft competence supervision from specialists' relative performance on labeled simulated tasks. At deployment, routing requires no target anomaly labels, and only the selected specialists are fitted unsupervisedly on the target series. We bound Top-\(k\) set-competence regret under representation coverage and conditional competence stability. Across 16 real-world benchmarks and four complementary evaluation metrics, TS-Router achieves the best overall average rank. Controlled ablations with multiple frozen TSFM encoders further support the use of pretrained representations for competence estimation and adaptive specialist selection. The code is available at https://anonymous.4open.science/r/TS-Router-D8FF.

cs.LG↗
arXiv2026

KUPAS MASTER: Distilling the Tacit Expertise of Master Practitioners into Agent-Ready Experience Corpora

Experienced professionals know more than just facts and conclusions. They know which cues matter, why a judgment is reasonable, and which action to take. Routine work records often leave out this tacit knowledge, making it difficult for Large Language Model (LLM) agents to use professional experience effectively. We introduce KUPAS MASTER, an experience engineering platform built around nine-layer cognitive corpus construction. It turns heterogeneous work records and practitioner interviews into traceable, reusable experience corpora for agents. Six case elements preserve the task process: context, cues, judgment, action, boundaries, and outcomes. Nine-layer cognitive corpus construction organizes tacit experience along nine extraction dimensions and stores the resulting assets in six libraries: rules, constraints, best practices, negative examples, corner cases, and skills. Semantic alignment, individual experience distillation, organizational consolidation, and cross-review preserve source evidence, conditions of use, and unresolved disagreements. The platform packages these assets into callable skills with explicit inputs, steps, dependencies, and stopping conditions, connecting experience collection to task execution and evaluation feedback. Using authorized samples from 20 randomly selected practitioners, the platform processed 1,576 source files into 23,024 individual experience records and 13,113 organizational assets. The evaluation spans multiple professional domains. Under common task inputs and scoring criteria, the base model, raw corpus retrieval-augmented generation (RAG), and KUPAS MASTER agent scored 70.63, 79.75, and 89.58, respectively. The KUPAS MASTER agent improved on raw-corpus RAG in all seven scoring dimensions. The platform provides a practical path from individual tacit experience to organizational knowledge and agent capabilities.

cs.AI↗
arXiv2026

Does Local Video Understanding Transfer Across Encounters? The EgoGears Benchmark

Embodied systems must make knowledge acquired during one encounter usable in another despite changes in viewpoint, motion, and illumination. Yet aggregate cross-video accuracy conflates failures of local perception with failures to preserve observation identity, establish correspondence, and compose evidence, obscuring whether local video understanding actually transfers. We introduce EgoGears, a complementary single- and multi-video benchmark designed to diagnose this transition. It contains 567 single-video and 1,487 multi-video questions derived from 126 human-collected egocentric recordings covering 39 outdoor routes. Repeated traversals across movement speeds and lighting conditions ground comparisons in shared physical environments; 531 questions require alignment across independent recordings. Single-video questions measure the local visual, spatial, and motion evidence available to a model, while multi-video questions test whether evidence remains bound to the correct observation and can be composed into consistent route relationships. We report 29 single-video and 31 multi-video MLLM configurations across six model families in the main leaderboard. Among the 20 configurations evaluated comparably on both splits, every model performs worse on multi-video questions, with a mean decrease of 22.5 percentage points, and the gap persists when answer format and scoring are held fixed. The gap is not explained simply by additional videos or recording boundaries. The central bottlenecks are observation--evidence binding and ordered route-state tracking. The code and benchmark are publicly available at https://github.com/lei-qi-233/EgoGears.

cs.CV↗
arXiv2026

Design of Experiment for Discovering Directed Mixed Graph

We study the design of interventions for causal discovery in simple structural causal models whose causal graphs are directed mixed graphs (DMGs) that may contain directed cycles and bidirected edges representing latent confounding. In such case, observational conditional-independence (CI) information may not identify even the graph skeleton, while CI alone cannot generally detect a bidirected edge coexisting with a directed edge. To this end, we propose a stage-wise framework based on tailored separating systems. Separating-system interventions first recover descendant relations and strongly connected components (SCCs). The SCCs are then ordered by ancestry, and an SCC-Anc separating system recovers the directed subgraph. Given this subgraph, further systems use CI tests interpreted through $d$- or $σ$-separation to recover non-adjacent bidirected edges, whose endpoints share no directed edge, and do-see comparisons to recover those coexisting with exactly one directed edge. Under our assumptions, the framework recovers the directed subgraph and every bidirected edge except double-adjacent ones, whose endpoints are connected by a directed edge in each direction. We develop algorithms for unrestricted and $M$-bounded settings, with each experiment targeting at most $M$ variables in the latter. For recovering the directed subgraph and non-adjacent bidirected edges, our upper bounds on the number and maximum size of experiments match corresponding worst-case lower bounds up to logarithmic factors.

stat.ML↗
arXiv2026

What Paired Evaluations Reveal under Visual Perturbations

Robustness evaluation must examine diverse visual perturbations, while benchmarks cover only some real-world conditions and physical testing is costly. Paired evaluations link clean and perturbed predictions for the same image, capturing changes in correctness, confidence, and acceptance beyond aggregate accuracy. We investigate how this image correspondence supports two needs in robustness evaluation: interpreting paired evaluation results and prioritizing samples for physical testing. To interpret paired evaluation results, we fix both sets of prediction records and vary their correspondence within each class. We prove that classwise correct-correct counts give the same sharp bounds on lost acceptance and mean true-class probability decrease among retained-correct inputs as any feasible five-state refinement. Distinguishing persistent from changed wrong answers can further constrain accepted-error transitions, while shared correspondence can establish policy orderings left unresolved by separate cost intervals. To prioritize samples for physical testing, we retain each image's synthetic responses and rank clean-correct images by their mean true-class probability under corruption. Across 44 classifiers, testing the highest-risk 20% finds 67% and 45% of failures under mild screen and print recaptures, versus 58% and 36% for clean confidence and 60% and 37% for an equal-size natural-transformation average. With both probability averaging and an A3Rank scoring adaptation, the tested corruption set yields higher mean failure recall than the natural-transform set; differences between scores depend on the source and budget. Together, these findings show that the value of correspondence depends on the evaluation objective: classwise counts suffice for specified reliability bounds, while image-specific synthetic responses improve the allocation of physical tests within the evaluated pool.

cs.CV↗
arXiv2026

Flow induced two-dimensional $ζ$ potential on chemically uniform solid-liquid interface: A possible electrokinetic origin of streamwise vortices

The $ζ$ potential at solid-liquid interfaces governs electrokinetic phenomena across chemistry, biology, and engineering. Despite its centrality, local measurement of this potential has remained a formidable challenge, forcing the universal assumption of spatial uniformity on chemically homogeneous surfaces. Here we introduce Fluorescence Photobleaching Electrochemistry Analysis (FLEA)-- a non-invasive technique that achieves 180 nm lateral resolution -- to map the $ζ$ potential at unprecedented spatial detail. We discover that a perfectly uniform glass surface, under laminar flow, develops an intrinsic two-dimensional $ζ$ potential landscape: approximately symmetrical V-shaped distribution across the channel width that varies systematically with flow velocity, pH, and ionic strength. This two-dimensional electrochemical heterogeneity generates a rotational electric body force that spontaneously produces streamwise vortices-structures commonly observed in boundary layers. Our findings establish FLEA as a transformative tool for surface characterization, reveal a previously unrecognized origin of streamwise vorticity at interfaces from the aspect of electrokinetic.

cond-mat.mes-hall↗
arXiv2026

Supervision Recovery for Time Series Anomaly Detection via Context-Anchored Pairing

Time series anomaly detection (TSAD) remains challenging not only because anomaly labels are scarce, but also because temporal anomalies are highly context-dependent. Existing methods often rely on unsupervised objectives or surrogate abnormal patterns, providing limited supervision for context-dependent normal--anomalous distinctions. We propose Context-Anchored Pair Supervision (CAPS), a supervision-recovery framework for TSAD. CAPS views ideal anomaly supervision as a matched comparison between normal and anomalous outcomes under the same temporal context, and seeks to recover such supervision without target-domain anomaly labels. Using simulated normal--anomalous pairs, CAPS learns structure and anomaly-semantic representations through reconstruction, background consistency, and within-pair counterfactual recombination. The resulting anomaly representations form a continuous semantic space with coarse modes and induce a sampleable multimodal prior. CAPS conditionally realizes sampled semantics as residual-form effects on target reference trajectories. The resulting context-anchored normal--anomalous counterparts provide temporal supervision for discriminative detector learning. Experiments on nine datasets show that CAPS achieves the strongest aggregate performance across all four evaluation metrics among the compared methods, while complementary ablations and transfer analyses support the roles of context anchoring, semantic disentanglement, and conditional realization.

cs.AI↗
arXiv2026

FOCUS: Fixed-Confidence Online Causal Learning Using Sequential Adaptive Interventions

We study fully online fixed-confidence causal discovery without any historical observational data. Starting from zero samples, the learner sequentially selects interventions to recover both the causal DAG and its edge weights under a linear-Gaussian structural equation model. We establish an instance-dependent lower bound for any $(ε,δ)$-correct algorithm and propose \textsc{FOCUS}, which adaptively allocates interventions through an online max--min game. A key contribution is a computable concentration inequality for the accumulated KL divergence involving causal parameters shared across interventions. We prove that \textsc{FOCUS} is $(ε,δ)$-correct and that its expected stopping time matches the lower bound in its $Θ(\log(1/δ))$ dependence up to an instance-dependent constant. Experiments demonstrate improved structure and edge-weight recovery and confirm the predicted stopping-time trend. Our codes are available on https://anonymous.4open.science/r/FOCUS_code-76E5

stat.ML↗
arXiv2026

SPBench: A Multi-Task Evaluation Benchmark for Exploration Seismic Processing

Exploration seismic processing underpins subsurface imaging and resource exploration, but learning-based methods remain difficult to compare across studies. Our survey of 368 papers finds widespread reliance on private or difficult-to-reproduce datasets, with only 25 providing public code. This obscures whether reported gains arise from model design or experimental settings. We introduce the Seismic Processing Benchmark (SPBench), covering six tasks: random noise attenuation, trace interpolation, ground-roll suppression, multiple suppression, deblending, and first-arrival picking. We reproduce 24 supervised methods on 10 datasets under 43 standardized settings and release datasets, implementations, configurations, evaluation scripts, and results. To complement global scores and per-trace pick errors, we introduce signal-component-resolved evaluation (SCoRE) for reconstruction and a reference-free ridge-curvature score (RC_norm) for first-arrival picking. Our analyses show that synthetic rankings do not reliably predict field rankings, with task-dependent agreement when models train within each setting. As degradation strengthens, rankings reorder more under coherent ground roll than under random-like interference. The ridge score agrees with MAE-based model rankings in the evaluated settings, with a mean Kendall correlation of 0.881 across three field surveys, while SCoRE reveals frequency- and energy-dependent differences hidden by global scores. SPBench provides a reproducible basis for comparing learning-based seismic processing methods and characterizes how their relative advantages vary across data settings, degradation strengths, and evaluation criteria.

physics.geo-ph↗
arXiv2026

ScaleMPA: Rethinking Scalable RRT* Acceleration With a Grid-Native Representation

Real-time motion planning remains challenging in large and high-dimensional environments. Prior acceleration of RRT* follows tree-centric state organization, which reduces per-query cost but preserves superlinear end-to-end complexity and limits parallelism through structural dependencies. This paper presents ScaleMPA, a motion-planning accelerator that rethinks RRT* with a grid-native representation. By replacing hierarchical traversal with direct grid-based access, ScaleMPA reduces the planner critical path and exposes fine-grained parallelism. To make this reformulation practical under sparse high-dimensional planning, ScaleMPA further proposes a multi-resolution grid search engine and a hash-grid memory system. Implemented in 28 nm CMOS, ScaleMPA achieves millisecond-level planning latency and delivers 4.7$\times$--44.4$\times$ speedup over state-of-the-art motion-planning accelerators.

cs.RO↗
arXiv2026

The "Rough" HAR Model

This paper proposes discrete-time approximations to rough continuous-time models of realized variance (RV). The leading rough models can be viewed as autoregressive processes driven by fractional Gaussian noise. We show that the Wold representation of this noise concentrates its dependence at the first lag when the Hurst parameter is below one half. Augmenting the autoregressive (AR) and heterogeneous autoregressive (HAR) models with a first-order moving-average (MA(1)) component therefore approximates the roughness, and the MA coefficient maps almost linearly into the Hurst parameter. We refer to these extensions as the "rough" AR and "rough" HAR models. Estimating them on the log RV of ten ETFs, we find negative MA coefficients for every asset, and the implied Hurst parameters align closely with the estimates from the continuous-time models. In the HAR literature, the negative MA(1) component is a significant feature that has been largely overlooked. In out-of-sample comparisons, the "rough" models outperform their classical counterparts for nearly every asset and horizon, with the largest gains at short horizons, and their accuracy is comparable to that of the rough continuous-time models but much easier to estimate by standard off-the-shelf software.

econ.EM↗
arXiv2026

Calibrating the Heston model with deep differential networks

We propose a gradient-based deep learning framework to calibrate the Heston option pricing model (Heston, 1993). Our neural network, henceforth deep differential network (DDN), learns both the Heston pricing formula for plain-vanilla options and the partial derivatives with respect to the model parameters. The price sensitivities estimated by the DDN are not subject to the numerical issues that can be encountered in computing the gradient of the Heston pricing function. Thus, our network is an excellent pricing engine for fast gradient-based calibrations. Extensive tests on selected equity markets show that the DDN significantly outperforms non-differential feedforward neural networks in terms of calibration accuracy. In addition, it dramatically reduces the computational time with respect to global optimizers that do not use gradient information.

q-fin.CP↗
arXiv2026

FlashGPU-sim: Enabling GPU Modeling for Modern Architectures and AI Workloads

As AI becomes increasingly ubiquitous, modern AI systems are shaped by a tight software-hardware co-design loop. Later GPUs expose features such as asynchronous data movement, tensor core pipelines, and fine-grained synchronization that high-performance kernels aggressively exploit, while emerging application behaviors increasingly influence the next generation of hardware design. Unfortunately, the latest open-source simulators for NVIDIA GPUs focus on architectures and software stacks from roughly six years ago. Therefore, they cannot support many state-of-the-art AI kernels generated by modern compiler stacks, e.g. Triton, or accurately model the hardware features they depend on. As a result, architects lack a credible platform for analyzing bottlenecks in this flywheel or evaluating design trade-offs for future AI systems. To bridge this gap, we present FlashGPU-sim, an open-source, execution-driven, cycle-accurate GPU simulator for modern AI workloads. FlashGPU-sim faithfully models modern hardware features such as asynchronous data movement, fine-grained synchronization, tensor-core execution, and distributed shared memory. A Triton extraction front-end allows direct simulation of optimized AI operators without manual porting, while multi-threaded execution makes large-scale software-hardware co-design practical. Across 131 workload configurations on RTX 5090, H100, and B200, FlashGPU-sim achieves a cycle-level MAPE of 5.24%, while multi-threaded simulation reaches a 7.86x speedup with 16 host threads. An H100 case study further demonstrates its utility for microarchitectural design exploration.

cs.AR↗
arXiv2026

TruthInsightBench: An Evidence-Grounded Benchmark for Automated Evaluation of Open-Ended Scientific Discovery Agents

Autonomous coding agents are increasingly proposed as AI-scientist systems that conduct analyses and write research reports, but executing a prescribed analysis is not the same as making a discovery. Existing benchmarks are configured for reproduction: tasks, data, and rubrics are built around a hidden target study, and recovery of its result is rewarded. We present TruthInsightBench, a benchmark configured for discovery. Its 40 blind tasks, drawn from 40 peer-reviewed studies across 10 scientific domains, expose only a neutral scientific objective and frozen data; source conclusions, expected values, and analysis paths are withheld, leaving the agent to determine what claim the data support. A fixed LLM-based judge scores the evidentiary maturity of an agent's own claims along six dimensions, operationalized as 29 artifact-grounded items, with automated, deterministic aggregation and no per-instance human grading, so evaluation can be repeated automatically as agents evolve. On one frozen base model, four coding agents form a narrow plateau (58.4-60.3 of 100) with no statistically reliable pairwise separation: they execute and document analyses competently, with comparatively strong evidence auditability and novelty, but largely lack the discriminating acts that establish a trustworthy claim (controls, robustness, falsifiability, and cross-dataset generalization). The bottleneck is scientific judgment rather than coding, and genuine discovery remains out of reach. TruthInsightBench makes this gap a measurable target; data and scoring code are at https://github.com/TruthInsight-stack/TruthInsightBench.

cs.AI↗
arXiv2026

InsightChain: Optimized Chain-of-Insight Analytics for LLM-driven Data Visualization

Large language models (LLMs) are increasingly used for automated data visualization, yet existing approaches often frame visualization generation as a single-step mapping from user query to figure or code, overlooking the iterative analytical reasoning process of expert analysts. We present InsightChain, a four-stage visualization prompting pipeline (Explore--Focus--Test--Present) that emulates expert analytical workflows, together with VG-COPRO, a vision-guided automatic prompt optimization (APO) method adapted to jointly optimize such multi-stage, executable pipelines. To address the evaluation gap for complex data visualization, we introduce the Insight Progression Metric (IPM), a rubric combining four text-based dimensions with a vision-based dimension. We assess IPM through a 100-chain human pilot and an expanded 300-chain agent-based evaluation spanning all ten domains. Experiments on public datasets show that InsightChain consistently outperforms competing prompting baselines. Existing APO methods fail to yield consistent gains on this multi-stage task, whereas VG-COPRO improves performance in both in-domain and cross-domain settings.

cs.CL↗
arXiv2026

MVWeaver: A Hierarchical Music Video Generation Agent with a Learned Song-to-Visual Bridge

Music videos are an important form of audiovisual expression in contemporary culture. They translate and extend the expressive content of songs through deliberate visual design. Existing automatic music video (MV) generation systems can generate visually plausible shots, yet often struggle with long-form coherence and song-grounded visual development. We present MVWeaver, a music video generation agent that integrates hierarchical planning with a learned song-to-visual bridge that translates song understanding into executable shot plans. The MVWeaver architecture comprises a comprehensive song analysis module, a visual planner that constructs hierarchical plans, and downstream image and video generation models that render the planned content. To equip a general-purpose LLM with MV-specific song-to-visual knowledge, we learn a bridge between song analysis and visual planning from real-MV-derived supervision and curate 1,861 real-world song--MV pairs with structured song-side, MV-side, and teacher-inferred song-to-visual rationale annotations. Using these annotations, we perform LoRA-based supervised fine-tuning (SFT) of a large language model to predict song-to-visual bridges that guide hierarchical visual planning. Our experiments demonstrate stronger song-grounded visual translation, richer visual development, and greater conceptual and shot-to-shot coherence, while ablations support the benefits of learned bridge conditioning.

cs.MM↗
arXiv2026

Complete Topological Classification with P and T Symmetries: Revealing a Topological Invariant Invisible to K-Theory

The K-theoretic framework provides a complete topological classification of the tenfold symmetry classes and has been generalized to incorporate crystalline symmetries. Here, we show that this classification is incomplete even in the elementary case of spinless systems possessing both P and T symmetries. We obtain the complete classification through a first-principles analysis of the topological classes of P- and T-symmetric bands, namely, by classifying the corresponding symmetric clutching data. We identify a topological invariant that is invisible from the K-theoretic perspective when the occupied states at each inversion-invariant momentum have uniformly positive or uniformly negative parity. In special cases, such as when all inversion-invariant momenta have uniformly positive parity, this invariant can be interpreted as the second Stiefel--Whitney class or the Euler number defined over an inversion fundamental domain, namely, half of the Brillouin zone. Our work not only reveals a new topological invariant that cannot be determined from the parity spectra at inversion-invariant momenta under P and T symmetries, but also demonstrates the existence of crystalline topological phases that are absent from the K-theoretic classification.

cond-mat.mes-hall↗