arXiv subjects

Kai Wang

Publications and source records attributed to Kai Wang.

At least 253 records · Page 14Linked to original sources

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

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↗

arXiv2025

Neural Index Policies for Restless Multi-Action Bandits with Heterogeneous Budgets

Restless multi-armed bandits (RMABs) provide a scalable framework for sequential decision-making under uncertainty, but classical formulations assume binary actions and a single global budget. Real-world settings, such as healthcare, often involve multiple interventions with heterogeneous costs and constraints, where such assumptions break down. We introduce a Neural Index Policy (NIP) for multi-action RMABs with heterogeneous budget constraints. Our approach learns to assign budget-aware indices to arm--action pairs using a neural network, and converts them into feasible allocations via a differentiable knapsack layer formulated as an entropy-regularized optimal transport (OT) problem. The resulting model unifies index prediction and constrained optimization in a single end-to-end differentiable framework, enabling gradient-based training directly on decision quality. The network is optimized to align its induced occupancy measure with the theoretical upper bound from a linear programming relaxation, bridging asymptotic RMAB theory with practical learning. Empirically, NIP achieves near-optimal performance within 5% of the oracle occupancy-measure policy while strictly enforcing heterogeneous budgets and scaling to hundreds of arms. This work establishes a general, theoretically grounded, and scalable framework for learning index-based policies in complex resource-constrained environments.

cs.LG↗

arXiv2025

GenColorBench: A Color Evaluation Benchmark for Text-to-Image Generation Models

Recent years have seen impressive advances in text-to-image generation, with image generative or unified models producing high-quality images from text. Yet these models still struggle with fine-grained color controllability, often failing to accurately match colors specified in text prompts. While existing benchmarks evaluate compositional reasoning and prompt adherence, none systematically assess color precision. Color is fundamental to human visual perception and communication, critical for applications from art to design workflows requiring brand consistency. However, current benchmarks either neglect color or rely on coarse assessments, missing key capabilities such as interpreting RGB values or aligning with human expectations. To this end, we propose GenColorBench, the first comprehensive benchmark for text-to-image color generation, grounded in color systems like ISCC-NBS and CSS3/X11, including numerical colors which are absent elsewhere. With 44K color-focused prompts covering 400+ colors, it reveals models' true capabilities via perceptual and automated assessments. Evaluations of popular text-to-image models using GenColorBench show performance variations, highlighting which color conventions models understand best and identifying failure modes. Our GenColorBench assessments will guide improvements in precise color generation. The benchmark will be made public upon acceptance.

cs.CV↗

arXiv2025

Zero-Dimensional Stacking Domains Enable Strong-Ductile Synergy in Additive Manufactured Titanium

Alloying by addition of oxygen interstitials during additive manufacturing provides new routes to strengthen and toughen metals and alloys. The underlying mechanisms by which such interstitial atoms lead to enhanced properties remain, however, unclear, not least due a lack of quantitative atomic-scale models linking microstructure to properties. Here using quasi-3D imaging based on multi-slice electron ptychography, we reveal the importance of a new type of interstitial-character lattice defect, namely zero-dimensional stacking domains (ZDSDs), present in high density in AM-processed oxygen-modulated pure titanium. These ZDSDs promote slip diversity, and support intense work hardening, enabling a three-fold enhancement in both strength and ductility in Ti-0.45O compared to conventional pure Ti. The work demonstrates the potential for using interstitial solutes to enhance mechanical properties in a range of critical engineering alloys.

cond-mat.mtrl-sci↗

arXiv2025

From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging

Face aging has become a crucial task in computer vision, with applications ranging from entertainment to healthcare. However, existing methods struggle with achieving a realistic and seamless transformation across the entire lifespan, especially when handling large age gaps or extreme head poses. The core challenge lies in balancing age accuracy and identity preservation--what we refer to as the Age-ID trade-off. Most prior methods either prioritize age transformation at the expense of identity consistency or vice versa. In this work, we address this issue by proposing a two-pass face aging framework, named Cradle2Cane, based on few-step text-to-image (T2I) diffusion models. The first pass focuses on solving age accuracy by introducing an adaptive noise injection (AdaNI) mechanism. This mechanism is guided by including prompt descriptions of age and gender for the given person as the textual condition. Also, by adjusting the noise level, we can control the strength of aging while allowing more flexibility in transforming the face. However, identity preservation is weakly ensured here to facilitate stronger age transformations. In the second pass, we enhance identity preservation while maintaining age-specific features by conditioning the model on two identity-aware embeddings (IDEmb): SVR-ArcFace and Rotate-CLIP. This pass allows for denoising the transformed image from the first pass, ensuring stronger identity preservation without compromising the aging accuracy. Both passes are jointly trained in an end-to-end way. Extensive experiments on the CelebA-HQ test dataset, evaluated through Face++ and Qwen-VL protocols, show that our Cradle2Cane outperforms existing face aging methods in age accuracy and identity consistency. Code is available at https://github.com/byliutao/Cradle2Cane.

cs.CV↗

arXiv2025

The Bigfoot: A footprint of a Coma cluster progenitor at z=3.98

Protoclusters, galaxy clusters' high redshift progenitors, hold the keys to understanding the formation and evolution of clusters and their member galaxies. However, their cosmological distances and spatial extensions (tens of Mpc) have inhibited complete mapping of their structure and constituent galaxies, which is key to robustly linking protoclusters to their descendants. Here we report the discovery of the Bigfoot, a tridimensional structure at $z = 3.98$ including 11 subgroups traced by 55 (700) spectroscopic (photometric) redshifts with JWST, extending over $15\times 37$ $\times 49{\rm{cMpc^3}}$ in the PRIMER-UDS field. Bigfoot's large-scale and mass function of member galaxies closely match constrained simulations' predictions for the progenitors of today's most massive clusters (${M_0} > 10^{15} {M_{_ \odot }}$). All subgroups with ${M_{\rm{h}}} > {10^{12.5}}{M_{_ \odot }}$ exhibit enhanced fractions of massive galaxies ($>{10^{10.0} {M_{_ \odot }}}$) compared to lower-mass halos and the field, demonstrating the accelerated formation of massive galaxies in massive halos. The presence of this massive protocluster with a large central halo (${10^{13.0} {M_{_ \odot }}}$) in a JWST deep field bears important cosmological implication that favors high ${σ_8}$ of PLANCK cosmology over low-redshift probes.

astro-ph.GA↗

arXiv2025

One-Step Flow Policy Mirror Descent

Diffusion policies have achieved great success in online reinforcement learning (RL) due to their strong expressive capacity. However, the inference of diffusion policy models relies on a slow iterative sampling process, which limits their responsiveness. To overcome this limitation, we propose Flow Policy Mirror Descent (FPMD), an online RL algorithm that enables 1-step sampling during flow policy inference. Our approach exploits a theoretical connection between the distribution variance and the discretization error of single-step sampling in straight interpolation flow matching models, and requires no extra distillation or consistency training. We present two algorithm variants based on rectified flow policy and MeanFlow policy, respectively. Extensive empirical evaluations on MuJoCo and visual DeepMind Control Suite benchmarks demonstrate that our algorithms show strong performance comparable to diffusion policy baselines while requiring orders of magnitude less computational cost during inference.

cs.LG↗

arXiv2025

Diffusion-DFL: Decision-focused Diffusion Models for Stochastic Optimization

Decision-focused learning (DFL) integrates predictive modeling and optimization by training predictors to optimize the downstream decision target rather than merely minimizing prediction error. To date, existing DFL methods typically rely on deterministic point predictions, which are often insufficient to capture the intrinsic stochasticity of real-world environments. To address this challenge, we propose the first diffusion-based DFL approach, which trains a diffusion model to represent the distribution of uncertain parameters and optimizes the decision by solving a stochastic optimization with samples drawn from the diffusion model. Our contributions are twofold. First, we formulate diffusion DFL using the reparameterization trick, enabling end-to-end training through diffusion. While effective, it is memory and compute-intensive due to the need to differentiate through the diffusion sampling process. Second, we propose a lightweight score function estimator that uses only several forward diffusion passes and avoids backpropagation through the sampling. This follows from our results that backpropagating through stochastic optimization can be approximated by a weighted score function formulation. We empirically show that our diffusion DFL approach consistently outperforms strong baselines in decision quality. The source code for all experiments is available at the project repository: https://github.com/GT-KOALA/Diffusion_DFL.

cs.LG↗