arXiv subjects

Zidan Wang

Publications and source records attributed to Zidan Wang.

9 recordsLinked to original sources

arXiv2026

AWPD: Frequency Shield Network for Agnostic Watermark Presence Detection

Invisible watermarks, as an essential technology for image copyright protection, have been widely deployed with the rapid development of social media and AIGC. However, existing invisible watermark detection heavily relies on prior knowledge of specific algorithms, leading to limited detection capabilities for ``unknown watermarks'' in open environments. To this end, we propose a novel task named Agnostic Watermark Presence Detection (AWPD), which aims to identify whether an image carries a copyright mark without requiring decoding information. We construct the UniFreq-100K dataset, comprising large-scale samples across various invisible watermark embedding algorithms. Furthermore, we propose the Frequency Shield Network (FSNet). This model deploys an Adaptive Spectral Perception Module (ASPM) in the shallow layers, utilizing learnable frequency gating to dynamically amplify high-frequency watermark signals while suppressing low-frequency semantics. In the deep layers, the network introduces Dynamic Multi-Spectral Attention (DMSA) combined with tri-stream extremum pooling to deeply mine watermark energy anomalies, forcing the model to precisely focus on sensitive frequency bands. Extensive experiments demonstrate that FSNet exhibits superior zero-shot detection capabilities on the AWPD task, outperforming existing baseline models. Code and datasets will be released upon acceptance.

cs.CV↗

arXiv2026

iGVLM: Dynamic Instruction-Guided Vision Encoding for Question-Aware Multimodal Understanding

Despite the success of Large Vision--Language Models (LVLMs), most existing architectures suffer from a representation bottleneck: they rely on static, instruction-agnostic vision encoders whose visual representations are utilized in an invariant manner across different textual tasks. This rigidity hinders fine-grained reasoning where task-specific visual cues are critical. To address this issue, we propose iGVLM, a general framework for instruction-guided visual modulation. iGVLM introduces a decoupled dual-branch architecture: a frozen representation branch that preserves task-agnostic visual representations learned during pre-training, and a dynamic conditioning branch that performs affine feature modulation via Adaptive Layer Normalization (AdaLN). This design enables a smooth transition from general-purpose perception to instruction-aware reasoning while maintaining the structural integrity and stability of pre-trained visual priors. Beyond standard benchmarks, we introduce MM4, a controlled diagnostic probe for quantifying logical consistency under multi-query, multi-instruction settings. Extensive results show that iGVLM consistently enhances instruction sensitivity across diverse language backbones, offering a plug-and-play paradigm for bridging passive perception and active reasoning.

cs.CV↗

arXiv2026

ITO: Images and Texts as One via Synergizing Multiple Alignment and Training-Time Fusion

Image-text contrastive pretraining has become a dominant paradigm for visual representation learning, yet existing methods often yield representations that remain partially organized by modality. We propose ITO, a framework addressing this limitation through two synergistic mechanisms. Multimodal multiple alignment enriches supervision by mining diverse image-text correspondences, while a lightweight training-time multimodal fusion module enforces structured cross-modal interaction. Crucially, the fusion module is discarded at inference, preserving the efficiency of standard dual-encoder architectures. Extensive experiments show that ITO consistently outperforms strong baselines across classification, retrieval, and multimodal benchmarks. Our analysis reveals that while multiple alignment drives discriminative power, training-time fusion acts as a critical structural regularizer -- eliminating the modality gap and stabilizing training dynamics to prevent the early saturation often observed in aggressive contrastive learning.

cs.CV↗

arXiv2026

Separators in Enhancing Autoregressive Pretraining for Vision Mamba

The state space model Mamba has recently emerged as a promising paradigm in computer vision, attracting significant attention due to its efficient processing of long sequence tasks. Mamba's inherent causal mechanism renders it particularly suitable for autoregressive pretraining. However, current autoregressive pretraining methods are constrained to short sequence tasks, failing to fully exploit Mamba's prowess in handling extended sequences. To address this limitation, we introduce an innovative autoregressive pretraining method for Vision Mamba that substantially extends the input sequence length. We introduce new \textbf{S}epara\textbf{T}ors for \textbf{A}uto\textbf{R}egressive pretraining to demarcate and differentiate between different images, known as \textbf{STAR}. Specifically, we insert identical separators before each image to demarcate its inception. This strategy enables us to quadruple the input sequence length of Vision Mamba while preserving the original dimensions of the dataset images. Employing this long sequence pretraining technique, our STAR-B model achieved an impressive accuracy of 83.5\% on ImageNet-1k, which is highly competitive in Vision Mamba. These results underscore the potential of our method in enhancing the performance of vision models through improved leveraging of long-range dependencies.

cs.CV↗

arXiv2025

Wonderful Team: Zero-Shot Physical Task Planning with Visual LLMs

We introduce Wonderful Team, a multi-agent Vision Large Language Model (VLLM) framework for executing high-level robotic planning in a zero-shot regime. In our context, zero-shot high-level planning means that for a novel environment, we provide a VLLM with an image of the robot's surroundings and a task description, and the VLLM outputs the sequence of actions necessary for the robot to complete the task. Unlike previous methods for high-level visual planning for robotic manipulation, our method uses VLLMs for the entire planning process, enabling a more tightly integrated loop between perception, control, and planning. As a result, Wonderful Team's performance on real-world semantic and physical planning tasks often exceeds methods that rely on separate vision systems. For example, we see an average 40% success rate improvement on VimaBench over prior methods such as NLaP, an average 30% improvement over Trajectory Generators on tasks from the Trajectory Generator paper, including drawing and wiping a plate, and an average 70% improvement over Trajectory Generators on a new set of semantic reasoning tasks including environment rearrangement with implicit linguistic constraints. We hope these results highlight the rapid improvements of VLLMs in the past year, and motivate the community to consider VLLMs as an option for some high-level robotic planning problems in the future.

cs.AI↗

arXiv2024

Quantum Spin Supersolid as a precursory Dirac Spin Liquid in a Triangular Lattice Antiferromagnet

Based on the recent experiments on the triangular lattice antiferromagnet Na$_2$BaCo(PO$_4$)$_2$, we propose the easy-axis XXZ spin-1/2 model on the triangular lattice, that exhibits a quantum spin supersolid, to be a precursory Dirac spin liquid. Despite the presence of a three-sublattice magnetic order as a spin supersolid, we suggest that this system is close to a Dirac spin liquid by exploring its spectroscopic response. The physical consequence is examined from the spectroscopic response, and we establish the continuous spectra near the M point in addition to the K point excitation from the spinon continuum on top of the three-sublattice order. Moreover, the satellite peaks were predicted at the mid-points connecting the $Γ$ and K points. This proposal offers a plausible understanding of the recent inelastic neutron scattering measurement in Na$_2$BaCo(PO$_4$)$_2$ and could inspire further research in relevant models and materials, such as K$_2$Co(SeO$_3$)$_2$ and Rb$_2$Co(SeO$_3$)$_2$, and even more anisotropic magnets like PrMgAl$_{11}$O$_{19}$.

cond-mat.str-el↗

arXiv2023

Cold Diffusion on the Replay Buffer: Learning to Plan from Known Good States

Learning from demonstrations (LfD) has successfully trained robots to exhibit remarkable generalization capabilities. However, many powerful imitation techniques do not prioritize the feasibility of the robot behaviors they generate. In this work, we explore the feasibility of plans produced by LfD. As in prior work, we employ a temporal diffusion model with fixed start and goal states to facilitate imitation through in-painting. Unlike previous studies, we apply cold diffusion to ensure the optimization process is directed through the agent's replay buffer of previously visited states. This routing approach increases the likelihood that the final trajectories will predominantly occupy the feasible region of the robot's state space. We test this method in simulated robotic environments with obstacles and observe a significant improvement in the agent's ability to avoid these obstacles during planning.

cs.RO↗

arXiv2018

Emulating topological chiral magnetic effects in artificial Weyl semimetals

We realized highly tunable Weyl semimetal-bands and subsequently emulated the topological chiral magnetic effects in superconducting quantum circuits. Driving the superconducting quantum circuits with elaborately designed microwave fields, we mapped the momentum space of a lattice to the parameter space, realizing the Hamiltonian of a Weyl semimetal. By measuring the energy spectrum, we directly imaged the Weyl points of cubic lattices, whose topological winding numbers were further determined from the Berry curvature measurement. In particular, we used an additional microwave field to produce a momentum-dependent chemical potential, from which the chiral magnetic topological current was extracted in the presence of an artificial magnetic field. This pure topological current is proportional to the magnetic field, which is in contrast to the famous Ampere's law, and may have significant impacts on topological materials and quantum devices.

cond-mat.mes-hall↗

arXiv2017

Realizing and manipulating space-time inversion symmetric topological semimetal bands with superconducting quantum circuits

We have experimentally realized novel space-time inversion (P-T) invariant Z2-type topological semimetal-bands, via an analogy between the momentum space and a controllable parameter space in superconducting quantum circuits. By measuring the whole energy spectrum of system, we imaged clearly an exotic tunable gapless band structure of topological semimetals. Two topological quantum phase transitions from a topological semimetal to two kinds of insulators can be manipulated by continuously tuning the different parameters in the experimental setup, one of which captures the Z2 topology of the PT semimetal via merging a pair of nontrivial Z2 Dirac points. Remarkably, the topological robustness was demonstrated unambiguously, by adding a perturbation that breaks only the individual T and P symmetries but keeps the joint PT symmetry. In contrast, when another kind of PT -violated perturbation is introduced, a topologically trivial insulator gap is fully opened.

quant-ph↗