arXiv subjects

Zhongyi Zhang

Publications and source records attributed to Zhongyi Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Wan-Animate-2: Pushing the Application Boundaries of Character Animation

Character image animation remains a foundational yet challenging task in computer vision. Existing approaches can be broadly categorized into three paradigms: methods based on explicit motion representations suffer from extraction errors and identity drift; methods based on implicit motion features lose fine-grained dynamics through compression; and in-context learning approaches avoid intermediate representations but incur prohibitive computational costs. Furthermore, all current systems are designed for offline synthesis, unable to meet the real-time requirements of interactive applications such as digital avatars and live-streaming hosts. To address these limitations, we present Wan-Animate-2, an end-to-end character animation framework that directly consumes the driving video within a redesigned Diffusion Transformer. Our architecture achieves superior motion fidelity and identity preservation by eliminating intermediate motion extractors entirely. We further introduce text driven viewpoint control that decouples the output camera perspective from the driving video--a capability rarely supported by prior character animation methods that rely on explicit motion representations. Beyond generation quality, we present Wan-Animate-2-Lite, an efficient variant that reduces inference latency to real-time thresholds through a three-stage training paradigm: teacher forcing pretraining with error buffer mechanism, and Self-Forcing distillation with chunk-wise backpropagation. This enables streaming character animation for interactive applications, opening new deployment scenarios that were previously infeasible. Qualitative evaluations and user studies demonstrate that Wan-Animate-2 achieves high-fidelity animation results across diverse characters and motion patterns. To foster further research and community development, we will release the Wan-Animate-2-Base model weights to the public.

cs.CV↗

arXiv2026

CARE: Pre-Execution Command Verification for Shell-Executing LLM Agents

Large Language Model (LLM) agents are increasingly used for coding and terminal automation, making shell-command dispatch a high-stakes runtime control point. We study command-level pre-execution mediation for individual shell commands produced by LLM agents under bounded path context. Existing safeguards remain limited: generic guardrails do not model shell structure in sufficient detail, always-on LLM judges are relatively costly and variable, and shell parsers do not directly prevent harmful execution. We present CARE (Canonicalization, Attribution, and Resolution Engine), a shell-specific, static-first verifier for individual shell commands before execution. CARE canonicalizes generated commands into stable verification targets, derives deterministic evidence over syntax, command semantics, path context, and provenance-backed risk patterns, and escalates only underdetermined cases to an LLM judge. This design keeps the common case fast, reproducible, and auditable while reserving neural adjudication for borderline commands. On the balanced main split, CARE reaches 85.64% F1 with a 0.91% false-positive rate at 2.32 ms mean latency. When deployed in its static enforcement profile, CARE retains 84.99% F1 at 0.34 ms and reduces realised harm on RedCode-gen to 37.33%. Across external-generalization tests and controlled Docker-sandbox execution, these profiles expose a practical trade-off between benign recovery, false-positive burden, latency, and harm reduction. Overall, command-level shell mediation can reduce dispatch-boundary risk for LLM agents while preserving most benign workflows.

cs.CR↗

arXiv2026

Getting the Parameters Right: A Difficulty-Graded Benchmark and Probe-Guided Training for LLM Tool Calls

Large language model agents derive much of their capability from tool use. Existing research on tool use has largely focused on selecting the right tool and orchestrating the order of calls. However, correctly filling the parameters of a tool call is equally critical for successful execution and has received far less attention. In domains such as cloud networking, even frontier models correctly complete fewer than half of tool calls. Inspired by recent analyses showing that LLM hidden states encode rich information about model predictions, we discover that while the model generates a parameter value, its hidden state contains a strong correctness signal: a simple linear probe can accurately predict whether the value will be correct. Based on this observation, we propose a unified probe-guided framework with two complementary approaches: probe-filtered bootstrapped training (PBT), which uses the probe to filter reliable self-generated calls for fine-tuning, and probe-guided reranking (PGR), which uses the probe to select better candidates during inference. To support systematic evaluation, we release ParamBench, a benchmark built from real cloud-network APIs that categorizes every instance into five difficulty levels according to parameter nesting depth, cross-parameter dependencies, and the reasoning required to derive values from earlier calls. Extensive experiments across 5 open models on ParamBench and 6 external benchmarks demonstrate that our method substantially improves parameter generation, raising the average exact match from 19.7% to 59.6%.

cs.AI↗

arXiv2026

MultiAnimate: A Unified Framework for Controllable Multi-Character Animation

Recent advances in generative models and technological innovations have significantly addressed the fundamental challenges of character image animation. However, existing approaches predominantly focus on character animation from a single reference image, substantially limiting their applicability in scenarios such as multiple character interaction animation. To fill this gap, this paper introduces MultiAnimate, a comprehensive framework that enables concurrent animation of multiple characters within a shared environment while preserving both identity consistency and spatial relationships. The framework achieves these objectives through multiple well-designed mechanisms. First, we incorporate an identity-specific reference net that enables appearance extraction from multiple reference images, distinguishing MultiAnimate from existing approaches constrained to single reference inputs. Second, we implement an identity-aware pose encoder to address the character-pose binding challenge, wherein an attention mechanism enables the network to accurately differentiate and process multiple pose sequences during generation. Third, we introduce an interaction guider module that enhances the framework's capability to handle complex inter-character interactions by leveraging character-specific mask information, serving as an optional component that refines the pose sequences. Extensive experiments and ablation analyses demonstrate our framework's superiority in multiple character animation, particularly in scenarios involving complex motion sequences.

cs.CV↗

arXiv2026

VisualRepair: Dynamic Tool Calling and Region Focusing for Visual Software Issue Repair

Automated Program Repair (APR) has witnessed significant progress with the advent of Large Language Models (LLMs). However, as modern software systems increasingly expose rich graphical user interfaces, effectively leveraging visual information from bug screenshots has become essential for understanding bugs and generating accurate fixes in multimodal scenarios. Real-world issue reports frequently contain heterogeneous visual attachments including UI screenshots, IDE snapshots, GIFs, and text-centric images, each with distinct visual patterns and domain-specific semantics that impose substantial perceptual demands on MLLMs. Furthermore, bug screenshots often contain large expanses of uninformative and bug-irrelevant regions, distracting the model's attention and limiting patch diversity. To address these challenges, we propose VisualRepair, an MLLM-based framework for visual software issue repair comprising two core modules: Image Type-aware Tool Calling (ITTC), which classifies input images and dynamically invokes a tailored tool-calling chain for robust visual interpretation, and Dynamic Test-time Region Focusing (DTRF), which grounds multiple bug-related region candidates and refines them via an adaptive zoom-in and zoom-out strategy to improve fault localization and promote diverse patch generation. Extensive experiments on the SWE-bench Multimodal benchmark demonstrate that VisualRepair consistently outperforms state-of-the-art approaches. VisualRepair resolves 196 and 25 instances on the test and dev sets, respectively, surpassing the best baseline by 10 and 11 instances. These results highlight the effectiveness of type-aware visual understanding and region-focused localization for automated visual software issue repair.

cs.SE↗

arXiv2026

UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models

World models based on video generation demonstrate remarkable potential for simulating interactive environments yet suffer from persistent difficulties in two key areas: maintaining long-term content consistency when scenes are revisited and enabling precise camera control from user-specified inputs. Existing methods based on explicit 3D reconstruction often compromise flexibility in unbounded scenarios and struggle to preserve fine-grained structures. Alternative methods rely directly on previously generated frames without establishing explicit spatial correspondence, thereby limiting controllability and consistency. To address these limitations, we present UCM, a novel framework for unified modeling of long-term memory and precise camera control via a time-aware positional encoding warping mechanism. To reduce computational overhead, we design an efficient dual-stream diffusion transformer for high-fidelity generation. Moreover, we introduce a scalable data curation strategy that utilizes point-cloud-based rendering to simulate scene revisiting, enabling training on over 500K monocular videos. Extensive experiments on real-world and synthetic benchmarks demonstrate that UCM significantly outperforms state-of-the-art methods on long-term scene consistency, while achieving precise camera controllability in high-fidelity video generation.

cs.CV↗

arXiv2026

EfficientUICoder: A Bidirectional Token Compression Framework for Efficient MLLM-Based UI Code Generation

Multimodal Large Language Models have demonstrated exceptional performance in UI2Code tasks, significantly enhancing website development efficiency. However, these tasks incur substantially higher computational overhead than traditional code generation due to the large number of input image tokens and extensive output code tokens required. Our comprehensive study identifies significant redundancies in both image and code tokens that exacerbate computational complexity and hinder focus on key UI elements, resulting in excessively lengthy and often invalid HTML files. We propose EfficientUICoder, a compression framework for efficient UI code generation with three key components. First, Element and Layout-aware Token Compression preserves essential UI information by detecting element regions and constructing UI element trees. Second, Region-aware Token Refinement leverages attention scores to discard low-attention tokens from selected regions while integrating high-attention tokens from unselected regions. Third, Adaptive Duplicate Token Suppression dynamically reduces repetitive generation by tracking HTML/CSS structure frequencies and applying exponential penalties. Extensive experiments show EfficientUICoder achieves a 55%-60% compression ratio without compromising webpage quality and delivers superior efficiency improvements: reducing computational cost by 44.9%, generated tokens by 41.4%, prefill time by 46.6%, and inference time by 48.8% on 34B-level MLLMs. Code is available at https://github.com/WebPAI/EfficientUICoder.

cs.SE↗

arXiv2026

Spectroscopic fingerprints of a ferroaxial charge density wave

Unconventional charge density waves (CDWs) with complex order parameters can host exotic collective modes and non-trivial topologies. They have emerged as a new frontier in the study of quantum matter. Recent experiments on rare-earth tritellurides have reported evidence for a ferroaxial CDW through the detection of characteristic Raman modes. This phase, often regarded as a hidden order, has been recognized to arise from the coupling between charge and orbital degrees of freedom in these materials. Yet, spectroscopic insight into its underlying electronic structure and the explicit form of its order parameter symmetry has remained elusive. Here, we present results from linearly polarized angle-resolved photoemission spectroscopy (ARPES) and scanning tunneling microscopy (STM) measurements of the CDW phase in LaTe$_3$. Our ARPES measurements reveal a complex landscape of spectral gaps across the reconstructed Fermi surface, while our STM-based quasiparticle interference (QPI) mapping, enhanced through the selective deposition of atomic scattering centers, directly reveals an inter-orbital CDW with mixed $p_x$-$p_z$ orbital character. The detailed analysis of the QPI characteristics in terms of the order parameter symmetry within the orbital subspace of the Fermi surface suggests a mixed CDW phase with substantial ferroaxial component, which breaks all vertical mirror symmetries. More broadly, our work establishes a powerful spectroscopic pathway, based on scattering off individual atoms, for identifying and characterizing hidden, multi-component electronic orders in quantum materials using STM and ARPES measurements.

cond-mat.str-el↗

arXiv2026

Evolution of the intertwining correlated topological phases in iron-based superconductor Fe(Te,Se)

Multiple topological electronic phases can coexist within a single quantum material and induce different topological superconducting states, offering deeper insights into interplay of topological superconducting states and Majorana modes, which may also be influenced and modified by correlation effect. Iron-based superconductors, with both topological states and correlation effect, is an ideal platform to study these phenomena. Here, with high resolution angle resolved photoelectron spectroscopy, we directly resolve two distinct intertwining topological states in iron-based superconductor Co-doped Fe(Te,Se), and study their evolution with electron doping. We identify a region where both topological insulator surface states and topological Dirac semimetal states intersect the Fermi level. The topological states are affected by the strong correlation effect and are isolated from trivial bulk states. The evolution between distinct topological phases offers a good opportunity to study various Majorana modes from different superconducting phases according to theoretical analysis. Our findings establish an ideal platform for exploring the interaction between multiple topological superconducting states and the related Majorana modes.

cond-mat.supr-con↗

arXiv2026

Minimum Sum Set Cover: Structures and Algorithm

A set cover of a hypergraph $H$ is a set of vertices intersecting every hyperedge. In the minimum sum set cover problem, vertices are selected one by one; each edge pays the position of the first vertex that hits it, and the objective is to minimize the total cost. When $H$ is a graph, this is the minimum sum vertex cover problem. A solution is specified by a set cover $S$ together with an ordering of its vertices. While the classical set cover problem seeks to minimize $|S|$, the minimum sum variant favors covering many edges early and may prefer larger covers. This motivates a natural question: how large can the gap between~$\overrightarrowτ$ and $τ$ be? We prove an upper bound $\overrightarrowτ \le τ\log_{2} \lvert E(H)\rvert$, and show that for any positive~$n$, there exists a hypergraph $H$ on $n + 3$ vertices with $τ=3$ and $\overrightarrowτ=n$. For graphs, we obtain stronger bounds: we prove~$\overrightarrowτ \le 2τ\log_{2} τ$, improving the bound of Liu et al.\ [Theor. Comput. Sci., 2025], and we construct graphs with~$\overrightarrowτ = Ω\left( \frac{τ\log τ}{\log\log τ}\right)$, nearly matching this upper bound. On the algorithmic side, we show that minimum sum set cover is fixed-parameter tractable on bounded-rank hypergraphs, parameterized by~$\overrightarrowτ$, extending the algorithm of Liu et al.\ for graphs (i.e., rank-two hypergraphs).

cs.DM↗

arXiv2026

GRAFNet: Multiscale Retinal Processing via Guided Cortical Attention Feedback for Enhancing Medical Image Polyp Segmentation

Accurate polyp segmentation in colonoscopy is essential for cancer prevention but remains challenging due to: (1) high morphological variability (from flat to protruding lesions), (2) strong visual similarity to normal structures such as folds and vessels, and (3) the need for robust multi-scale detection. Existing deep learning approaches suffer from unidirectional processing, weak multi-scale fusion, and the absence of anatomical constraints, often leading to false positives (over-segmentation of normal structures) and false negatives (missed subtle flat lesions). We propose GRAFNet, a biologically inspired architecture that emulates the hierarchical organisation of the human visual system. GRAFNet integrates three key modules: (1) a Guided Asymmetric Attention Module (GAAM) that mimics orientation-tuned cortical neurones to emphasise polyp boundaries, (2) a MultiScale Retinal Module (MSRM) that replicates retinal ganglion cell pathways for parallel multi-feature analysis, and (3) a Guided Cortical Attention Feedback Module (GCAFM) that applies predictive coding for iterative refinement. These are unified in a Polyp Encoder-Decoder Module (PEDM) that enforces spatial-semantic consistency via resolution-adaptive feedback. Extensive experiments on five public benchmarks (Kvasir-SEG, CVC-300, CVC-ColonDB, CVC-Clinic, and PolypGen) demonstrate consistent state-of-the-art performance, with 3-8% Dice improvements and 10-20% higher generalisation over leading methods, while offering interpretable decision pathways. This work establishes a paradigm in which neural computation principles bridge the gap between AI accuracy and clinically trustworthy reasoning. Code is available at https://github.com/afofanah/GRAFNet.

cs.CV↗

arXiv2026

CAST-CKT: Chaos-Aware Spatio-Temporal and Cross-City Knowledge Transfer for Traffic Flow Prediction

Traffic prediction in data-scarce, cross-city settings is challenging due to complex nonlinear dynamics and domain shifts. Existing methods often fail to capture traffic's inherent chaotic nature for effective few-shot learning. We propose CAST-CKT, a novel Chaos-Aware Spatio-Temporal and Cross-City Knowledge Transfer framework. It employs an efficient chaotic analyser to quantify traffic predictability regimes, driving several key innovations: chaos-aware attention for regime-adaptive temporal modelling; adaptive topology learning for dynamic spatial dependencies; and chaotic consistency-based cross-city alignment for knowledge transfer. The framework also provides horizon-specific predictions with uncertainty quantification. Theoretical analysis shows improved generalisation bounds. Extensive experiments on four benchmarks in cross-city few-shot settings show CAST-CKT outperforms state-of-the-art methods by significant margins in MAE and RMSE, while offering interpretable regime analysis. Code is available at https://github.com/afofanah/CAST-CKT.

cs.AI↗

arXiv2025

Mirror-Selective Quasiparticle Interference in Bilayer Nickelate Superconductor

The recent discovery of high-temperature superconductivity in both bulk and thin-film bilayer nickelates has garnered significant attention. In this study, inspired by recent STM experiments on thin films, we investigate the quasiparticle interference (QPI) characteristics of bilayer nickelates in both normal and superconducting states to identify their Fermiology and pairing symmetry. We demonstrate that the mirror symmetry inherent in the bilayer structure induces mirror-selective quasiparticle scattering by establishing selection rules based on the mirror properties of impurities and the mirror eigenvalues of electronic wavefunctions. This mirror-selective scattering allows for the differentiation of distinct Fermiologies, as QPI patterns vary markedly between scenarios with and without the $d_{z^2}$-bonding Fermi surface (FS). Furthermore, it enables the separate detection of sign changes in superconducting gaps both within the same FS and between different FSs. Crucially, if the mirror-symmetry-enforced selection rules are ignored, the QPI response of an $s_\pm$-wave state can masquerade as that of a conventional $s$-wave state, leading to a misidentification of the pairing symmetry. When combined with field-dependent and reference QPI measurements, this approach facilitates the precise determination of pairing symmetry, even in the presence of FS-dependent gaps and gap anisotropy. Additionally, we discuss practical considerations for STM measurements to effectively identify the pairing symmetry. Our findings demonstrate that mirror-selective QPI is a powerful tool for distinguishing between different Fermiologies and pairing states, which is helpful in pinning down pairing symmetry and revealing the pairing mechanism in bilayer nickelates.

cond-mat.supr-con↗

arXiv2025

FaceTracer: Unveiling Source Identities from Swapped Face Images and Videos for Fraud Prevention

Face-swapping techniques have advanced rapidly with the evolution of deep learning, leading to widespread use and growing concerns about potential misuse, especially in cases of fraud. While many efforts have focused on detecting swapped face images or videos, these methods are insufficient for tracing the malicious users behind fraudulent activities. Intrusive watermark-based approaches also fail to trace unmarked identities, limiting their practical utility. To address these challenges, we introduce FaceTracer, the first non-intrusive framework specifically designed to trace the identity of the source person from swapped face images or videos. Specifically, FaceTracer leverages a disentanglement module that effectively suppresses identity information related to the target person while isolating the identity features of the source person. This allows us to extract robust identity information that can directly link the swapped face back to the original individual, aiding in uncovering the actors behind fraudulent activities. Extensive experiments demonstrate FaceTracer's effectiveness across various face-swapping techniques, successfully identifying the source person in swapped content and enabling the tracing of malicious actors involved in fraudulent activities. Additionally, FaceTracer shows strong transferability to unseen face-swapping methods including commercial applications and robustness against transmission distortions and adaptive attacks.Our code is available at: https://github.com/zzy224/FaceTracer.

cs.CV↗

arXiv2025

nnSAM2: nnUNet-Enhanced One-Prompt SAM2 for Few-shot Multi-Modality Segmentation and Composition Analysis of Lumbar Paraspinal Muscles

Purpose: To develop and validate No-New SAM2 (nnsam2) for few-shot segmentation of lumbar paraspinal muscles using only a single annotated slice per dataset, and to assess its statistical comparability with expert measurements across multi-sequence MRI and multi-protocol CT. Methods: We retrospectively analyzed 1,219 scans (19,439 slices) from 762 participants across six datasets. Six slices (one per dataset) served as labeled examples, while the remaining 19,433 slices were used for testing. In this minimal-supervision setting, nnsam2 used single-slice SAM2 prompts to generate pseudo-labels, which were pooled across datasets and refined through three sequential, independent nnU-Net models. Segmentation performance was evaluated using the Dice similarity coefficient (DSC), and automated measurements-including muscle volume, fat ratio, and CT attenuation-were assessed with two one-sided tests (TOST) and intraclass correlation coefficients (ICC). Results: nnsam2 outperformed vanilla SAM2, its medical variants, TotalSegmentator, and the leading few-shot method, achieving DSCs of 0.94-0.96 on MR images and 0.92-0.93 on CT. Automated and expert measurements were statistically equivalent for muscle volume (MRI/CT), CT attenuation, and Dixon fat ratio (TOST, P < 0.05), with consistently high ICCs (0.86-1.00). Conclusion: We developed nnsam2, a state-of-the-art few-shot framework for multi-modality LPM segmentation, producing muscle volume (MRI/CT), attenuation (CT), and fat ratio (Dixon MRI) measurements that were statistically comparable to expert references. Validated across multimodal, multicenter, and multinational cohorts, and released with open code and data, nnsam2 demonstrated high annotation efficiency, robust generalizability, and reproducibility.

eess.IV↗

arXiv2025

LaTCoder: Converting Webpage Design to Code with Layout-as-Thought

Converting webpage designs into code (design-to-code) plays a vital role in User Interface (UI) development for front-end developers, bridging the gap between visual design and functional implementation. While recent Multimodal Large Language Models (MLLMs) have shown significant potential in design-to-code tasks, they often fail to accurately preserve the layout during code generation. To this end, we draw inspiration from the Chain-of-Thought (CoT) reasoning in human cognition and propose LaTCoder, a novel approach that enhances layout preservation in webpage design during code generation with Layout-as-Thought (LaT). Specifically, we first introduce a simple yet efficient algorithm to divide the webpage design into image blocks. Next, we prompt MLLMs using a CoTbased approach to generate code for each block. Finally, we apply two assembly strategies-absolute positioning and an MLLM-based method-followed by dynamic selection to determine the optimal output. We evaluate the effectiveness of LaTCoder using multiple backbone MLLMs (i.e., DeepSeek-VL2, Gemini, and GPT-4o) on both a public benchmark and a newly introduced, more challenging benchmark (CC-HARD) that features complex layouts. The experimental results on automatic metrics demonstrate significant improvements. Specifically, TreeBLEU scores increased by 66.67% and MAE decreased by 38% when using DeepSeek-VL2, compared to direct prompting. Moreover, the human preference evaluation results indicate that annotators favor the webpages generated by LaTCoder in over 60% of cases, providing strong evidence of the effectiveness of our method.

cs.SE↗

arXiv2025

Attention to the strengths of physical interactions: Transformer and graph-based event classification for particle physics experiments

A major task in particle physics is the measurement of rare signal processes. Even modest improvements in background rejection, at a fixed signal efficiency, can significantly enhance the measurement sensitivity. Building on prior research by others that incorporated physical symmetries into neural networks, this work extends those ideas to include additional physics-motivated features. Specifically, we introduce energy-dependent particle interaction strengths, derived from leading-order SM predictions, into modern deep learning architectures, including Transformer Architectures (Particle Transformer), and Graph Neural Networks (Particle Net). These interaction strengths, represented as the SM interaction matrix, are incorporated into the attention matrix (transformers) and edges (graphs). Our results in event classification show that the integration of all physics-motivated features improves background rejection by $10\%-40\%$ over baseline models, with an additional gain of up to $9\%$ due to the SM interaction matrix. This study also provides one of the broadest comparisons of event classifiers to date, demonstrating how various architectures perform across this task. A simplified statistical analysis demonstrates that these enhanced architectures yield significant improvements in signal significance compared to a graph network baseline.

hep-ph↗

arXiv2025

Fermi-surface diagnosis for topological superconductivity with $s$-wave-like pairing symmetries

Theoretical prediction of topological superconductivity is key to their discovery. Recently, it is proved that in 199 out of 230 space groups, topological superconductivity coexists with an $s$-wave-like pairing symmetry, raising the hope of finding more candidates for this exotic phase. However, a comprehensive and efficient method for diagnosing topological superconductivity in realistic materials remains elusive. Here, we derive Fermi-surface formulas for gapped and gapless topological phases of time-reversal symmetric superconductors with $s$-wave-like pairing symmetries in all layer and space groups, applicable to thin-film and bulk materials. Our diagnosis uses only the sign of the pairing and the Fermi velocity at several Fermi points, and yields complete (partial) diagnosis for gapped topological superconductivity in 159 (40) out of the 199 space groups. This provides a fundamental basis for the first-principles prediction of new topological superconductors.

cond-mat.supr-con↗