arXiv subjects

Kai Wang

Publications and source records attributed to Kai Wang.

At least 235 records · Page 13Linked to original sources

arXiv2025

Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Models

Recent advances in text-to-image (T2I) diffusion models have enabled remarkable control over various attributes, yet precise color specification remains a fundamental challenge. Existing approaches, such as ColorPeel, rely on model personalization, requiring additional optimization and limiting flexibility in specifying arbitrary colors. In this work, we introduce ColorWave, a novel training-free approach that achieves exact RGB-level color control in diffusion models without fine-tuning. By systematically analyzing the cross-attention mechanisms within IP-Adapter, we uncover an implicit binding between textual color descriptors and reference image features. Leveraging this insight, our method rewires these bindings to enforce precise color attribution while preserving the generative capabilities of pretrained models. Our approach maintains generation quality and diversity, outperforming prior methods in accuracy and applicability across diverse object categories. Through extensive evaluations, we demonstrate that ColorWave establishes a new paradigm for structured, color-consistent diffusion-based image synthesis.

cs.GR↗

arXiv2025

Collisionless Shocks Mediated by Shear-Flow Magnetic Fields in Ultraintense-Laser-Produced Counter-Streaming Plasmas

The formation of ion-Weibel-mediated collisionless shocks (IW-CSs) in ultraintense-laser-produced counter-streaming plasmas is investigated using particle-in-cell simulations. Analysis of the underlying microphysics reveals that a shear-flow ion-Weibel instability generates magnetic fields, which isotropize the incoming flow and mediate shock formation. An analytical expression for the shear-flow magnetic field is derived, and a scaling law relating the magnetic field amplitude to the laser intensity is established. This mechanism reduces the shock formation time and the required laser energy by three and two orders of magnitude, respectively, compared to high-power laser experiments, making it feasible to produce IW-CSs using existing multi-kilojoule, picosecond ultraintense laser facilities.

physics.plasm-ph↗

arXiv2025

Kondo-coupled van der Waals antiferromagnet with high-mobility quasiparticles

Two-dimensional van der Waals (vdW) materials exhibit high carrier mobility and tunability, making them suitable for low-power, high-performance electronic and spintronic applications. Incorporating narrow-band electronic correlation effects could further promote tunability, though mass renormalization may impact carrier mobility. It is therefore challenging to identify a vdW material with both high mobility and strong correlation. Herein, by a combination of optical spectroscopy and high-field quantum-oscillation measurements, we observe significant effective-mass enhancement in CeTe$_3$ at low temperature, arising from not only the band-structure modulation by antiferromagnetic ordering but also the narrow-band correlation effect. Despite the mass enhancement, the quantum mobility surprisingly \textit{increases} and reaches $\sim$2403 cm$^2$/Vs, likely benefiting from topological protection. Remarkably, these unique properties are maintained in atomically thin nanoflakes with quantum mobility enhanced to $\sim$3158 cm$^2$/Vs. Thus, CeTe$_3$ emerges as a promising Kondo-coupled vdW antiferromagnetic metal with high-mobility quasiparticles, potentially unlocking new device concepts.

cond-mat.str-el↗

arXiv2025

Diversity Has Always Been There in Your Visual Autoregressive Models

Visual Autoregressive (VAR) models have recently garnered significant attention for their innovative next-scale prediction paradigm, offering notable advantages in both inference efficiency and image quality compared to traditional multi-step autoregressive (AR) and diffusion models. However, despite their efficiency, VAR models often suffer from the diversity collapse i.e., a reduction in output variability, analogous to that observed in few-step distilled diffusion models. In this paper, we introduce DiverseVAR, a simple yet effective approach that restores the generative diversity of VAR models without requiring any additional training. Our analysis reveals the pivotal component of the feature map as a key factor governing diversity formation at early scales. By suppressing the pivotal component in the model input and amplifying it in the model output, DiverseVAR effectively unlocks the inherent generative potential of VAR models while preserving high-fidelity synthesis. Empirical results demonstrate that our approach substantially enhances generative diversity with only neglectable performance influences. Our code will be publicly released at https://github.com/wangtong627/DiverseVAR.

cs.CV↗

arXiv2025

A Deterministic Dimension Property of Twisted Goppa Codes

This paper presents a large-scale computational study on the dimensional properties of twisted Goppa codes. Through the systematic analysis of over 50,000 parameter sets, we uncover a remarkable deterministic regularity: the actual dimension k of a twisted Goppa code is uniquely determined by a set of macro-parameters (q,m,t,b,u). Specifically, when the order of the finite field q, the extension degree m, the degree t of the Goppa polynomial, the translation parameter b of the automorphism, and the order u of the transformation are fixed, the dimension k of the generated code remains constant.

cs.IT↗

arXiv2025

Bridging Constraints and Stochasticity: A Fully First-Order Method for Stochastic Bilevel Optimization with Linear Constraints

This work provides the first finite-time convergence guarantees for linearly constrained stochastic bilevel optimization using only first-order methods, requiring solely gradient information without any Hessian computations or second-order derivatives. We address the unprecedented challenge of simultaneously handling linear constraints, stochastic noise, and finite-time analysis in bilevel optimization, a combination that has remained theoretically intractable until now. While existing approaches either require second-order information, handle only unconstrained stochastic problems, or provide merely asymptotic convergence results, our method achieves finite-time guarantees using gradient-based techniques alone. We develop a novel framework that constructs hypergradient approximations via smoothed penalty functions, using approximate primal and dual solutions to overcome the fundamental challenges posed by the interaction between linear constraints and stochastic noise. Our theoretical analysis provides explicit finite-time bounds on the bias and variance of the hypergradient estimator, demonstrating how approximation errors interact with stochastic perturbations. We prove that our first-order algorithm converges to $(δ, ε)$-Goldstein stationary points using $Θ(δ^{-1}ε^{-5})$ stochastic gradient evaluations, establishing the first finite-time complexity result for this challenging problem class and representing a significant theoretical breakthrough in constrained stochastic bilevel optimization.

math.OC↗

arXiv2025

Explainable AI-Generated Image Detection RewardBench

Conventional, classification-based AI-generated image detection methods cannot explain why an image is considered real or AI-generated in a way a human expert would, which reduces the trustworthiness and persuasiveness of these detection tools for real-world applications. Leveraging Multimodal Large Language Models (MLLMs) has recently become a trending solution to this issue. Further, to evaluate the quality of generated explanations, a common approach is to adopt an "MLLM as a judge" methodology to evaluate explanations generated by other MLLMs. However, how well those MLLMs perform when judging explanations for AI-generated image detection generated by themselves or other MLLMs has not been well studied. We therefore propose \textbf{XAIGID-RewardBench}, the first benchmark designed to evaluate the ability of current MLLMs to judge the quality of explanations about whether an image is real or AI-generated. The benchmark consists of approximately 3,000 annotated triplets sourced from various image generation models and MLLMs as policy models (detectors) to assess the capabilities of current MLLMs as reward models (judges). Our results show that the current best reward model scored 88.76\% on this benchmark (while human inter-annotator agreement reaches 98.30\%), demonstrating that a visible gap remains between the reasoning abilities of today's MLLMs and human-level performance. In addition, we provide an analysis of common pitfalls that these models frequently encounter. Code and benchmark are available at https://github.com/RewardBench/XAIGID-RewardBench.

cs.CV↗

arXiv2025

Rethinking Autoregressive Models for Lossless Image Compression via Hierarchical Parallelism and Progressive Adaptation

Autoregressive (AR) models, the theoretical performance benchmark for learned lossless image compression, are often dismissed as impractical due to prohibitive computational cost. This work re-thinks this paradigm, introducing a framework built on hierarchical parallelism and progressive adaptation that re-establishes pure autoregression as a top-performing and practical solution. Our approach is embodied in the Hierarchical Parallel Autoregressive ConvNet (HPAC), an ultra-lightweight pre-trained model using a hierarchical factorized structure and content-aware convolutional gating to efficiently capture spatial dependencies. We introduce two key optimizations for practicality: Cache-then-Select Inference (CSI), which accelerates coding by eliminating redundant computations, and Adaptive Focus Coding (AFC), which efficiently extends the framework to high bit-depth images. Building on this efficient foundation, our progressive adaptation strategy is realized by Spatially-Aware Rate-Guided Progressive Fine-tuning (SARP-FT). This instance-level strategy fine-tunes the model for each test image by optimizing low-rank adapters on progressively larger, spatially-continuous regions selected via estimated information density. Experiments on diverse datasets (natural, satellite, medical) validate that our method achieves new state-of-the-art compression. Notably, our approach sets a new benchmark in learned lossless compression, showing a carefully designed AR framework can offer significant gains over existing methods with a small parameter count and competitive coding speeds.

cs.CV↗

arXiv2025

EAGLE: Episodic Appearance- and Geometry-aware Memory for Unified 2D-3D Visual Query Localization in Egocentric Vision

Egocentric visual query localization is vital for embodied AI and VR/AR, yet remains challenging due to camera motion, viewpoint changes, and appearance variations. We present EAGLE, a novel framework that leverages episodic appearance- and geometry-aware memory to achieve unified 2D-3D visual query localization in egocentric vision. Inspired by avian memory consolidation, EAGLE synergistically integrates segmentation guided by an appearance-aware meta-learning memory (AMM), with tracking driven by a geometry-aware localization memory (GLM). This memory consolidation mechanism, through structured appearance and geometry memory banks, stores high-confidence retrieval samples, effectively supporting both long- and short-term modeling of target appearance variations. This enables precise contour delineation with robust spatial discrimination, leading to significantly improved retrieval accuracy. Furthermore, by integrating the VQL-2D output with a visual geometry grounded Transformer (VGGT), we achieve a efficient unification of 2D and 3D tasks, enabling rapid and accurate back-projection into 3D space. Our method achieves state-ofthe-art performance on the Ego4D-VQ benchmark.

cs.CV↗

arXiv2025

Can Randomly Structured Metasurfaces Be Used for Quantum Tomography of High-Dimensional Spatial Qudits?

Reconstructing the density matrix of the quantum state of photons through a tomographically complete set of measurements, known as quantum state tomography, is an essential task in nearly all applications of quantum science and technology, from quantum sensing to quantum communications. Recent advances in optical metasurfaces enable the design of ultrathin nanostructured optical elements performing such state tomography tasks, promising greater simplicity, miniaturization, and scalability. However, reported metasurfaces on this goal were limited to a small Hilbert dimension, e.g., polarization qubits or spatial qudits with only a few states. When scaling up to higher-dimensional qudit tomography problems, especially those involving spatial qudits, a natural question arises: whether a metasurface with randomized nanostructures is sufficient to perform such qudit tomography, achieving optimal conditions. In this work, we attempt to answer this question through a set of numerical experiments with random metasurfaces, utilizing large-scale simulations of over 16,000 distinct metasurfaces each exceeding 200 wavelengths in size. We show that with sufficient redundancy in the number of detectors, random metasurfaces perform reasonably well in quantum photonic spatial qudit tomography encoded in Hermite-Gaussian states for up to approximately 10 states. Furthermore, we discuss additional considerations for optimizing metasurfaces in multiphoton cases. Our work opens a pathway toward computationally efficient, miniaturized, and error-tolerant quantum measurement platforms.

quant-ph↗

arXiv2025

HiMo-CLIP: Modeling Semantic Hierarchy and Monotonicity in Vision-Language Alignment

Contrastive vision-language models like CLIP have achieved impressive results in image-text retrieval by aligning image and text representations in a shared embedding space. However, these models often treat text as flat sequences, limiting their ability to handle complex, compositional, and long-form descriptions. In particular, they fail to capture two essential properties of language: semantic hierarchy, which reflects the multi-level compositional structure of text, and semantic monotonicity, where richer descriptions should result in stronger alignment with visual content.To address these limitations, we propose HiMo-CLIP, a representation-level framework that enhances CLIP-style models without modifying the encoder architecture. HiMo-CLIP introduces two key components: a hierarchical decomposition (HiDe) module that extracts latent semantic components from long-form text via in-batch PCA, enabling flexible, batch-aware alignment across different semantic granularities, and a monotonicity-aware contrastive loss (MoLo) that jointly aligns global and component-level representations, encouraging the model to internalize semantic ordering and alignment strength as a function of textual completeness.These components work in concert to produce structured, cognitively-aligned cross-modal representations. Experiments on multiple image-text retrieval benchmarks show that HiMo-CLIP consistently outperforms strong baselines, particularly under long or compositional descriptions. The code is available at https://github.com/UnicomAI/HiMo-CLIP.

cs.CV↗

arXiv2025

Unifying Anderson transitions and topological amplification in non-Hermitian chains

Non-Hermitian systems with non-reciprocal hopping may display the non-Hermitian skin effect, where states under open boundary conditions localize exponentially at one edge of the system. This localization has been linked to spectral winding and topological gain, forming a bulk-boundary correspondence akin to the one relating edge modes to bulk topological invariants in topological insulators and superconductors. In this work, we establish a bulk-boundary correspondence for disordered Hatano-Nelson models. We relate the localization of states to spectral winding using the Lyapunov exponent and the Thouless formula. We identify two kinds of phase transitions and relate them to transport properties. Our framework is relevant to a broad class of 1D non-Hermitian models, opening new directions for disorder-resilient transport and quantum-enhanced sensing in photonic, optomechanical, and superconducting platforms.

cond-mat.dis-nn↗

arXiv2025

Direct Mapping of Intrinsic Topology of Bound States in the Continuum via Nonlinear Emission

The direct mapping of the intrinsic topology in a leaky photonic band is crucial and challenging in topological photonics. For instance, observables in bound states in the continuum (BICs) feature complex topological textures such as a polarization vortex in momentum space, which nonetheless is difficult to be characterized in far-field scattering, especially considering the dominant direct channel. Here, we propose and experimentally demonstrate a hybrid nonlinear metasurface that enables a direct visualization of the intrinsic topology in BICs via second-harmonic generation (SHG). The enhanced local-source of SHG from the ultrathin indium tin oxide can effectively excite the emissions from the eigenmodes of a TiO2 photonics crystal slab, achieving three-order enhancement of SHG magnitudes. Importantly, these enhanced SH emissions carry topological polarization textures of BICs to the far field. With this, we can directly construct polarization vector maps of symmetry-protected BICs and chiral symmetry-broken quasi-BICs, clearly visualizing the winding structure around V points, the generation and evolution of chiral C points. This work provides a universal approach for characterizing topological photonic systems via coherent nonlinearity processes, opening new avenues for studying topological phenomena in non-Hermitian photonic systems.

physics.optics↗

arXiv2025

PSTF-AttControl: Per-Subject-Tuning-Free Personalized Image Generation with Controllable Face Attributes

Recent advancements in personalized image generation have significantly improved facial identity preservation, particularly in fields such as entertainment and social media. However, existing methods still struggle to achieve precise control over facial attributes in a per-subject-tuning-free (PSTF) way. Tuning-based techniques like PreciseControl have shown promise by providing fine-grained control over facial features, but they often require extensive technical expertise and additional training data, limiting their accessibility. In contrast, PSTF approaches simplify the process by enabling image generation from a single facial input, but they lack precise control over facial attributes. In this paper, we introduce a novel, PSTF method that enables both precise control over facial attributes and high-fidelity preservation of facial identity. Our approach utilizes a face recognition model to extract facial identity features, which are then mapped into the $W^+$ latent space of StyleGAN2 using the e4e encoder. We further enhance the model with a Triplet-Decoupled Cross-Attention module, which integrates facial identity, attribute features, and text embeddings into the UNet architecture, ensuring clean separation of identity and attribute information. Trained on the FFHQ dataset, our method allows for the generation of personalized images with fine-grained control over facial attributes, while without requiring additional fine-tuning or training data for individual identities. We demonstrate that our approach successfully balances personalization with precise facial attribute control, offering a more efficient and user-friendly solution for high-quality, adaptable facial image synthesis. The code is publicly available at https://github.com/UnicomAI/PSTF-AttControl.

cs.CV↗

arXiv2025

Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond

General world models represent a crucial pathway toward achieving Artificial General Intelligence (AGI), serving as the cornerstone for various applications ranging from virtual environments to decision-making systems. Recently, the emergence of the Sora model has attained significant attention due to its remarkable simulation capabilities, which exhibits an incipient comprehension of physical laws. In this survey, we embark on a comprehensive exploration of the latest advancements in world models. Our analysis navigates through the forefront of generative methodologies in video generation, where world models stand as pivotal constructs facilitating the synthesis of highly realistic visual content. Additionally, we scrutinize the burgeoning field of autonomous-driving world models, meticulously delineating their indispensable role in reshaping transportation and urban mobility. Furthermore, we delve into the intricacies inherent in world models deployed within autonomous agents, shedding light on their profound significance in enabling intelligent interactions within dynamic environmental contexts. At last, we examine challenges and limitations of world models, and discuss their potential future directions. We hope this survey can serve as a foundational reference for the research community and inspire continued innovation. This survey will be regularly updated at: https://github.com/GigaAI-research/General-World-Models-Survey.

cs.CV↗

arXiv2025

Deformation of nef adjoint canonical line bundles

Much inspired by J. A. Wiśniewski's nef-value function method, we prove that in a smooth projective family over the unit disk, if the adjoint bundle of the canonical line bundle with a relatively semiample line bundle is nef on one fiber, then it remains nef on all fibers. We further extend this result to the semiampleness of the adjoint canonical line bundles. Using these, we prove the deformation invariance of any generalized plurigenera by assuming that only one fiber admits the semiample canonical line bundle and improve the first author--Xiao-Lei Liu's recent deformation rigidity of projective manifolds with semiample canonical line bundles. In particular, also by E. Viehweg--K. Zuo's result on the minimal number of singular fibers in a family and the first author--X. Liu's isotriviality result, if a projective family over $\mathbb{P}^1$ or an elliptic curve has one fiber with the big and nef (or more generally semiample) canonical line bundle, then all fibers are isomorphic to this fiber. Next, much inspired by M. Andreatta--T. Peternell's deformation theoretical approach, we prove that, in a smooth Kähler family of threefolds, if the canonical line bundle of one fiber is not nef, then none of its small deformations admits a nef canonical line bundle either. This partially confirms a problem posed by F. Campana--T. Peternell and the global stability of semiampleness of canonical line bundles of threefolds under a Kähler smooth deformation.

math.AG↗

arXiv2025

Dissecting the mass quenching in TNG50: Galaxy size determines the quenching mode

The diminishing of star formation is accompanied by size differentiating, as quiescent galaxies are more compact than star-forming galaxies at fixed stellar mass. In order to understand how galaxy quenching is related to galaxy sizes, we performed a demographic study of 46 massive quiescent central galaxies with stellar mass from $10^{10.5}\rm M_\odot$ to $10^{11}\rm M_\odot$ in the TNG50 simulation. We found that, in addition to the triggering active galactic nucleus (AGN) feedback, galaxy size is also a major determinant of the quenching process, as small and compact galaxies are immediately quenched by the kinetic AGN feedback, while galaxies with large sizes are still active until strangulated by the cutoff of new gas replenishment. Further spatially resolved inspection reveals that this short and intense kinetic AGN feedback can only suppress the star formation within 1-2 kpc, resulting in this size-dependent effect of quenching. We also identify a long-term effect of a few Gyr timescale that the gas inflow rate is progressively suppressed after triggering kinetic feedback, which appears to effectively quench large galaxies entirely. We conclude that kinetic AGN feedback has two key roles in quenching: a short-term, intense effect that quenches the central 2 kpc region, and a long-term effect that suppresses the gas inflow rate and further quenches the entire galaxy.

astro-ph.GA↗

arXiv2025

ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows

As large language models (LLMs) advance, the ultimate vision for their role in science is emerging: we could build an AI collaborator to effectively assist human beings throughout the entire scientific research process. We refer to this envisioned system as ResearchGPT. Given that scientific research progresses through multiple interdependent phases, achieving this vision requires rigorous benchmarks that evaluate the end-to-end workflow rather than isolated sub-tasks. To this end, we contribute CS-54k, a high-quality corpus of scientific Q&A pairs in computer science, built from 14k CC-licensed papers. It is constructed through a scalable, paper-grounded pipeline that combines retrieval-augmented generation (RAG) with multi-stage quality control to ensure factual grounding. From this unified corpus, we derive two complementary subsets: CS-4k, a carefully curated benchmark for evaluating AI's ability to assist scientific research, and CS-50k, a large-scale training dataset. Extensive experiments demonstrate that CS-4k stratifies state-of-the-art LLMs into distinct capability tiers. Open models trained on CS-50k with supervised training and reinforcement learning demonstrate substantial improvements. Even 7B-scale models, when properly trained, outperform many larger proprietary systems, such as GPT-4.1, GPT-4o, and Gemini 2.5 Pro. This indicates that making AI models better research assistants relies more on domain-aligned training with high-quality data than on pretraining scale or general benchmark performance. We release CS-4k and CS-50k in the hope of fostering AI systems as reliable collaborators in CS research.

cs.LG↗