arXiv subjects

Zhen Li

Publications and source records attributed to Zhen Li.

At least 73 records · Page 4Linked to original sources

arXiv2026

Ab initio calculations of two-neutrino and neutrinoless double-$\boldsymbolβ$ decay of $^{48}$Ca and related Gamow-Teller strength distributions

We present ab initio calculations of two-neutrino double-beta ($2νββ$) decay of $^{48}$Ca and the related Gamow-Teller (GT) strength functions in $^{48}$Sc using the valence-space in-medium similarity renormalization group (VS-IMSRG) with nuclear interactions and electroweak currents based on chiral effective field theory. We find that the usual $pf$-shell valence space significantly underestimates the nuclear matrix element (NME) of $2νββ$ decay compared to experiment, while an enlarged $d_{3/2}pf$ valence space yields very good agreement with the experimental value without any adjustments. We trace this to an improved description of the involved GT strength distributions, so that the enlarged valence space captures important correlations. The enlarged $d_{3/2}pf$ valence space leads to neutrinoless $ββ$ NMEs of $^{48}$Ca that are twice as large compared to the $pf$-shell calculation. Our findings suggest that studies with different valence spaces and related GT strengths are important for assessing ab initio NME calculations of heavier $ββ$ decays.

nucl-th↗

arXiv2026

From Pixels to States: Rethinking Interactive World Models as Game Engines

Building interactive worlds that respond coherently to player actions has long been a shared goal of computer graphics, games, and artificial intelligence. Recent video generative models provide a data-driven route toward this goal by predicting future observations conditioned on user actions, and are increasingly regarded as potential next-generation game engines. Realizing a genuinely interactive game world, however, requires interaction outcomes that follow rules over evolving game conditions, consequences that persist over long horizons, and a generation loop that operates in real time. Conventional game engines realize these properties through a recurrent action-state-observation loop, in which player actions update an explicit game state according to predefined rules and observations are rendered from the resulting state. Taking this loop as an organizing lens, this paper examines interactive game world modeling along four dimensions: player action control, game state dynamics, state-observation persistence, and real-time interactive generation. For each dimension, we start from the capabilities required by an interactive game world, group existing approaches into representative families, and discuss the strengths and trade-offs of each family. Complementing this analysis, we present a scalable data engine for Black Myth: Wukong that collects over 90 hours of gameplay with frame-aligned player actions, ground-truth game states, and visual observations, together with structured and semantic annotations, as a resource for state-aware game world modeling. We hope this paper offers a clear picture of where the field stands and fosters progress toward interactive game worlds.

cs.CV↗

arXiv2026

Z-Reward: Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions

Reward models are central to text-to-image post-training, but visual preference is subjective and better represented as a distribution over rubric scores than as a deterministic scalar. Existing scalar, score-token, and pairwise reward models over-compress uncertainty and fine-grained score differences, while reasoning-based generative rewards provide stronger judgments but are costly to deploy and difficult to use as direct optimization signals. We propose Z-Reward, a teacher-student reward modeling framework that decouples reasoning-heavy judgment from efficient reward deployment. The teacher is a large VLM that uses reasoning to infer rubric-aligned score distributions, and is trained with Group-wise Direct Score Optimization (GDSO), which combines policy-gradient rewards from distribution expectations with direct pointwise and pairwise supervision on score distributions and score gaps. The student is trained with Reasoning-Internalized Score Distillation (RISD), which transfers the teacher's reasoning-conditioned score distribution into a compact VLM without requiring explicit reasoning chains at inference time. On our internally annotated evaluation set, the 27B GDSO teacher reaches 89.6% human preference accuracy, outperforming SFT, RewardDance, and GRPO, while the 9B RISD student reaches 88.6%, outperforming the OPD baseline and closely matching the larger teacher. We further show that Z-Reward can serve as a differentiable reward signal for text-to-image optimization, yielding a 41.3% net human-preference improvement over the SFT baseline.

cs.CV↗

arXiv2026

Effective Synthetic Image Detection via Noise Residual Clustering

The rapid advancement of generative artificial intelligence (AI) has made synthetic images remarkably realistic, posing security threats such as misinformation and fraud. It is significant to detect the synthetic image in the manner of passive and blind image authentication. Most existing detectors rely on supervised training with large labeled datasets, leading to high costs and degraded performance on unknown generative models. To attenuate such deficiencies, we propose a training-free detection method. Specifically, noise residual fingerprints are first extracted by a simple yet effective pre-trained Noiseprint++ model. Then multi-scale features are further extracted from such residual by a frozen Vision Transformer (ViT), followed by adaptive weighted fusion. Only a few real image samples are used needed to initialize the clustering centers for unsupervised K-Means, distinguishing real and synthetic images without training. Extensive evaluations on four benchmark datasets show that our proposed scheme achieves an average accuracy of 82.2%, outperforming the state-of-the-art detectors on generalization ability. Superior performance is gained on the popular diffusion type of synthetic images, and the effectiveness of each module is validated by ablation studies. Source code will be publicly available at https://github.com/multimediaFor/NoiseCluSID.

cs.CV↗

arXiv2026

High-order perturbative calculations of nuclear ground states: Automated evaluation of many-body diagrams

We advance the many-body perturbation theory (MBPT) calculations of the ground-state energy and radius of closed-shell nuclei beyond third order. Using automated diagram generation and evaluation up to fifth order, we present ground-state properties of selected closed-shell nuclei up to $^{78}$Ni with two- and three-nucleon interactions derived from chiral effective field theory. A clear convergence trend is observed for the ground-state energy enabling calculations at improved accuracy. We further investigate in detail the decomposition of the fourth-order contributions. For the ground-state energy, the magnitude of the fourth-order contribution is typically less than half of the third order, and a typical cancellation among different classes of diagrams is observed. Finally, we perform a comprehensive comparison between MBPT and non-perturbative in-medium similarity renormalization group (IMSRG) calculations, with the goal to provide insight into many-body uncertainties associated with the IMSRG(2) truncation.

nucl-th↗

arXiv2026

Differentiable OPLS Force Field Parameterization for Ionic Electrolytes and High-Throughput Application to Lithium-ion Batteries

The rational design of ionic electrolytes for lithium-ion batteries (LIBs) is severely constrained by the vast solvent-salt combinatorial space and low efficiency of empirical trial-and-error. While molecular dynamics (MD) bridges microscopic solvation structures and macroscopic physicochemical properties, classical force fields often lack sufficient accuracy for multicomponent systems. To address these challenges, we develop an automated differentiable OPLS-AA force field parameterization workflow tailored for general ionic electrolytes. It employs topology-guided atom typification to reduce parameter redundancy and optimizes Lennard-Jones parameters via the DMFF framework, with experimental density as the fitting target and ionic conductivity as an independent validation metric. Rigorous convergence tests yield a standardized simulation protocol with $\sim$100,000-atom systems and 35-40 ns NVT runs to ensure reliable transport property quantification. High-throughput MD simulations of over 10,000 formulations spanning 67 solvents and 15 lithium salts are conducted on the Tianqiong platform, generating a comprehensive dataset covering five core properties: density, dielectric constant, viscosity, diffusion coefficient, and ionic conductivity. t-SNE visualization reveals partial clustering of distinct salt chemistries, continuous property gradients with concentration and temperature, and internal physical self-consistency, with solvent composition identified as another key performance regulator. Together, the accurate transferable force field and large-scale dataset provide a solid foundation for data-driven rational design of ionic electrolytes.

physics.chem-ph↗

arXiv2026

AlayaWorld: Long-Horizon and Playable Video World Generation

Game worlds have traditionally been built through labor-intensive production pipelines, making them costly to develop, difficult to customization, and expensive to modify after deployment. Recent advances in video world models offer a fundamentally different paradigm. Rather than explicitly authoring every component of a virtual environment, these models autoregressively synthesize future observations conditioned on the current world state and user interactions, enabling playable worlds to be generated online. Trained on both gameplay recordings and real-world videos, they can capture diverse visual appearances and physical dynamics, opening new opportunities for interactive applications beyond gaming, including embodied intelligence. In this paper, we present \textbf{AlayaWorld}, a full-stack open-source framework for building interactive generative worlds. AlayaWorld enables open-ended real-time interaction, allowing users to freely navigate and perform diverse actions such as combat, spell casting, and monster summoning. The framework unifies the complete development-from data preparation model architecture, model training, inference acceleration, and deployment-within a modular and extensible architecture. Alongside the framework, we release reproducible pipelines, reference implementations, evaluation tools, and comprehensive documentation, establishing a practical foundation for future research and real-time applications of generative world models.

cs.CV↗

arXiv2026

Generalized Synthetic Image Detection with Enhanced RGB-Noise Representation Learning

The rapid advancement of large-scale generative models has accelerated the spread of highly deceptive AI-generated images, making generalized synthetic image detection a critical imperative. Existing forensic networks often struggle with cross-model generalization and realworld degradations due to their reliance on single-domain representations and conventional binary classification optimization. To overcome these limitations, we propose RNSIDNet, a novel forensic framework that achieves robust detection through enhanced RGB-Noise representation learning. Specifically, our method employs a dual-branch architecture where global RGB semantics, extracted by an attention-refined CLIP backbone, dynamically modulate highfrequency noise artifacts captured by Bayar convolutions via a Feature-wise Linear Modulation (FiLM) module. To further enhance the learned representations, we design a Hard Sample-aware Contrastive Learning (HSCL) strategy. By explicitly penalizing challenging training samples, HSCL reshapes the latent feature space to maximize the discriminative margin between pristine and synthetic domains. Extensive experiments across eight public benchmark datasets verify that our model achieves state-of-the-art performance, delivering superior generalization ability, robustness, and computational efficiency. Code and dataset will be publicly available on https://github.com/multimediaFor/RNSIDNet.

cs.CV↗

arXiv2026

Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

The landscape of high-performance image generation models is currently dominated by proprietary systems, such as Nano Banana Pro and Seedream 4.0. Leading open-source alternatives, including Qwen-Image, Hunyuan-Image-3.0 and FLUX.2, are characterized by massive parameter counts (20B to 80B), making them impractical for inference, and fine-tuning on consumer-grade hardware. To address this gap, we propose Z-Image, an efficient 6B-parameter foundation generative model built upon a Scalable Single-Stream Diffusion Transformer (S3-DiT) architecture that challenges the "scale-at-all-costs" paradigm. By systematically optimizing the entire model lifecycle -- from a curated data infrastructure to a streamlined training curriculum -- we complete the full training workflow in just 314K H800 GPU hours (approx. $630K). Our few-step distillation scheme with reward post-training further yields Z-Image-Turbo, offering both sub-second inference latency on an enterprise-grade H800 GPU and compatibility with consumer-grade hardware (<16GB VRAM). Additionally, our omni-pre-training paradigm also enables efficient training of Z-Image-Edit, an editing model with impressive instruction-following capabilities. Both qualitative and quantitative experiments demonstrate that our model achieves performance comparable to or surpassing that of leading competitors across various dimensions. Most notably, Z-Image exhibits exceptional capabilities in photorealistic image generation and bilingual text rendering, delivering results that rival top-tier commercial models, thereby demonstrating that state-of-the-art results are achievable with significantly reduced computational overhead. We publicly release our code, weights, and online demo to foster the development of accessible, budget-friendly, yet state-of-the-art generative models.

cs.CV↗

arXiv2026

Distribution Matching Distillation Meets Reinforcement Learning

Distribution Matching Distillation (DMD) facilitates efficient inference by distilling multi-step diffusion models into few-step variants. Concurrently, Reinforcement Learning (RL) has emerged as a vital tool for aligning generative models with human preferences. While both represent critical post-training stages for large-scale diffusion models, existing studies typically treat them as independent, sequential processes, leaving a systematic framework for their unification largely unexplored. In this work, we demonstrate that jointly optimizing these two objectives yields mutual benefits: RL enables more preference-aware and controllable distillation rather than uniformly compressing the full data distribution, while DMD serves as an effective regularizer to mitigate reward hacking during RL training. Building on these insights, we propose DMDR, a unified framework that incorporates Reward-Tilted Distribution Matching optimization alongside two dynamic distillation training strategies in the initial stage, followed by the joint DMD and RL optimization in the second stage. Extensive experiments demonstrate that DMDR achieves state-of-the-art visual quality and prompt adherence among few-step generation methods, even surpassing the performance of its multi-step teacher model.

cs.CV↗

arXiv2026

Quantum Computations on Fusion Blanket Molten Salts

Molten salts such as FLiBe (2LiF--BeF$_2$) are leading blanket materials for breeding and recovering tritium in fusion reactors. Predicting tritium speciation requires accurate electronic ground-state energies for representative molten-salt clusters, a demanding task for correlated electronic-structure methods. Here we report the first application of heterogeneous quantum--classical computing to tritium binding in FLiBe. Clusters drawn from ab initio molecular dynamics are partitioned by an embedded-wavefunction (EWF) method into atom-centered fragments, and the largest fragments are solved on IBM quantum hardware using extended sample-based quantum diagonalization (ext-SQD). Across nine clusters, the heterogeneous quantum--classical workflow reproduces fragment ground-state energies with agreement to full configuration interaction within 0.7~kcal/mol and a mean absolute deviation of 0.3~kcal/mol. In contrast, fragmented and unfragmented conformational energy differences and tritium binding energies differ by 12~kcal/mol and 110~kcal/mol on average, respectively, identifying fragment construction rather than fragment solution as the dominant source of algorithmic bias. To the best of our knowledge, this is the first such demonstration for a charged ionic system and in particular an inorganic molten salt, where electrostatic and polarization effects make the accurate treatment of electronic correlation particularly challenging. These results also identify areas of future research towards an accurate and scalable quantum--classical workflow to compute free-energy estimates of tritium speciation in fusion blankets.

quant-ph↗

arXiv2026

ToE: A Hierarchical and Explainable Claim Verification Framework with Dynamic Multi-source Evidence Retrieval and Aggregation

The rapid spread of fake news poses increasing threats to information ecosystems, especially as AI-generated misinformation under Generative Engine Optimization (GEO) poisoning allows adversarially crafted content to be systematically surfaced by retrieval systems, contaminating LLM reasoning. In this paper, we propose Tree of Evidence (ToE), a hierarchical evidence reasoning framework for automated fact-checking that models each claim as a dynamically expanding argument tree. ToE integrates a reinforcement learning-driven multi-source retrieval agent, an evidence evaluation agent, and an argument tree aggregation algorithm to iteratively decompose, retrieve, and verify claims through an explainable evidence chain. We further provide a theoretical analysis of the retrieval process, deriving a formal error bound that guarantees the learned policy converges to a neighborhood of the information-theoretically optimal policy. Experiments across multiple datasets and backbone LLMs demonstrate that ToE achieves improvements ranging from 4 to 24 percentage points over competitive baselines, with particularly pronounced gains on adversarially poisoned inputs.

cs.AI↗

arXiv2026

ReFPO: Reflow Regularization for Flow Matching Policy Gradients

We present Reflow-regularized Flow Matching Policy Gradients (ReFPO), a simple online RL method that adds explicit Reflow regularization to FPO for efficient flow-based control. We uncover a key structural property: the gradient updates in Flow Matching Policy Gradients (FPO) can be interpreted as an implicit advantage-weighted Reflow process, providing a new geometric perspective on flow-based policy gradients. Building on this insight, ReFPO introduces an explicit geometric regularizer that can be implemented with a single line of code change without incurring additional computational overhead or auxiliary distillation stages. By synergizing advantage-guided updates with path rectification, our method reduces CFM proxy-ratio spikes, stabilizes PPO-style training, and enables high-fidelity one-step inference that often matches or exceeds multi-step performance. We experimentally demonstrate that ReFPO improves average performance and discretization robustness across GridWorld, MuJoCo Playground, and high-dimensional Humanoid Control tasks, providing a scalable and stable approach for generative policies in complex physical simulations.

cs.RO↗

arXiv2026

Psyzkaller: Learning from Historical and On-the-Fly Execution Data for Smarter Seed Generation in OS kernel Fuzzing

OS Kernel fuzzers such as Syzkaller often struggle to generate syscall sequences that respect intrinsic Syscall Dependency Relations (SDRs), resulting in seeds that either violate kernel constraints or fail to reach deep execution paths. We propose leveraging an N-gram model to learn SDRs from both kernel execution history and ongoing fuzzing results. This enables the fuzzer to capture dependencies in similar kernel versions while adapting to target-specific behaviors, thereby improving the validity of generated seeds. Additionally, we introduce a bidirectional Random Walk strategy to enhance the diversity of generated seeds. We implement this approach in a prototype, Psyzkaller, on top of Syzkaller. Experiments show that, trained with the large-scale DongTing dataset and continuously updated with ongoing fuzzing results, Psyzkaller improves Syzkaller's code coverage by 4.6%-7.0%, triggers 110.4%-187.2% more crashes, and discovers eight previously unknown kernel vulnerabilities. Furthermore, Psyzkaller outperforms state-of-the-art fuzzers such as ACTOR and SyzDescribe in both coverage and crashes.

cs.CR↗

arXiv2026

Shadow of Rotating Black Hole Immersed in Dark Matter Halo

The recent black hole shadow observations by the Event Horizon Telescope provide a unique opportunity to probe both the strong gravity regime and the environment surrounding supermassive black holes. Since dark matter halos are expected to exist around galactic-center black holes, they may leave observable signatures on black hole shadows. In this work, we investigate the spacetime structure, photon dynamics, and shadow properties of a rotating black hole immersed in a generalized double power law dark matter halo. Starting from a static dark matter black hole solution, we employ the Newman--Janis algorithm to construct its rotating counterpart and obtain a Kerr-like metric with a dark matter-modified mass function. We analyze the horizon structure, ergosphere, and unstable spherical photon orbits, and find that the dark matter halo generally enlarges the horizon, shifts the photon shell outward, and modifies the black hole shadow. The effects become more pronounced for rapidly rotating black holes. Using the shadow observation of Sgr A*, we further constrain the dark matter halo parameter space and identify correlations among the halo parameters, black hole spin, and observer inclination angle. Our results suggest that black hole shadow observations provide a promising probe of dark matter distributions near supermassive black holes.

gr-qc↗

arXiv2026

Elastic Queries Reinforcement Learning: Self-Aware Policy Execution for VLA Models

Vision-language-action (VLA) models are powerful action generators for robot manipulation, but they are typically executed with fixed inference and replanning schedules. This rigidity ignores the uneven difficulty of robot control: contact-rich or uncertain states may need more computation and fresher feedback, while easier states can often be handled with fewer inference steps and longer open-loop execution. We propose Elastic Queries Reinforcement Learning (EQRL), a framework that makes each VLA policy query elastic. A lightweight latent-schedule adaptor jointly selects the latent input, denoising budget, and action chunk length, without fine-tuning the underlying VLA model. To make scheduling difficulty-aware, EQRL trains a critic over the joint latent-schedule action and derives a state difficulty signal from critic ensemble disagreement. This signal guides compute toward difficult states, while a learned residual allows task-driven correction. We formulate variable chunk execution as query-level macro-action RL with chunk-dependent discounting and an amortized number-of-function-evaluations (NFE) budget. Across simulation and real-robot manipulation, EQRL reduces amortized inference cost while preserving or improving task success.

cs.RO↗

arXiv2026

High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation

Few-step diffusion distillation has become increasingly mature for 4-8-step generation, yet pushing further to 2 steps remains challenging. In this work, we introduce Z-Image Turbo++, a high-quality 2-step image generation model distilled from the 8-step Z-Image Turbo teacher. Our method addresses the central bottlenecks of increased task difficulty and limited model capacity in 2-step generation through three simple but effective design choices tailored to this regime. First, we propose Distribution-Aligned Adversarial Learning, which uses teacher-generated images rather than external real images as real samples for GAN training, providing a more attainable and informative adversarial target. Second, we adopt Step-Decoupled Parameterization, assigning independent model parameters to the two denoising steps to better match their distinct capacity demands. Third, we perform End-to-End Training with Iterative Regularization, allowing the first step to receive gradients from final image quality while preserving a meaningful intermediate generation through an explicit step-1 loss. Together, these designs substantially narrow the quality gap between 2-step and 8-step generation in both qualitative and quantitative evaluations, highlighting the potential of carefully tailored distillation strategies for improving the quality-efficiency trade-off in few-step generation.

cs.CV↗

arXiv2026

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation

As the foundational architecture of modern machine learning, Transformers have driven remarkable progress across diverse AI domains. Despite their transformative impact, a persistent challenge across various Transformers is Attention Sink (AS), in which a disproportionate amount of attention is focused on a small subset of specific yet uninformative tokens. AS complicates interpretability, significantly affecting the training and inference dynamics, and exacerbates issues such as hallucinations. In recent years, substantial research has been dedicated to understanding and harnessing AS. However, a comprehensive survey that systematically consolidates AS-related research and offers guidance for future advancements remains lacking. To address this gap, we present the first survey on AS, structured around three key dimensions that define the current research landscape: Fundamental Utilization, Mechanistic Interpretation, and Strategic Mitigation. Our work makes a pivotal contribution by highlighting the key concepts and main trends in the field, guiding researchers through the evolution of AS-related studies. We envision this survey as a valuable resource, empowering researchers to effectively manage AS within the current Transformer paradigm, while simultaneously inspiring innovative advancements for the next generation of Transformers. The paper list of this work is available at https://github.com/ZunhaiSu/Awesome-Attention-Sink.

cs.LG↗