Searcharxiv⌕ Search

arXiv subjects

Xin Zhang

Publications and source records attributed to Xin Zhang.

At least 37 records · Page 2Linked to original sources
arXiv2026

Agentic Tool-Augmented Reasoning for Explainable Image Forgery Detection

Conventional image forgery detection methods produce binary scores or pixel-level masks without interpretable evidence, while recent multimodal large language model (MLLM)-based approaches generate post-hoc explanations of predetermined classification results rather than reasoning from evidence. Inspired by the forensic workflow of human judicial experts, we propose Agentic Tool-Augmented Reasoning (ATAR), a framework integrating 22 specialized forensic tools across seven complementary domains to autonomously detect, localize, and explain image forgeries through multi-turn reasoning. A Dual-Stream Forensic Reasoning paradigm combines a high-level semantic anomaly path, which magnifies suspicious regions for fine-grained inspection, with a low-level forgery artifact path, which invokes forensic tools to extract objective evidence. We further introduce Forensics Curriculum Learning: during General Experience SFT, an automated teacher-student mentoring pipeline synthesizes multi-turn tool-usage reasoning trajectories; during Forensic Scene RL, a Tool Prior Curriculum guides early tool exploration and progressively transfers control to the agent, while a Structured Evidence Reward provides fine-grained process-level supervision. Experiments across IMDL, Deepfake detection, DMDL, and AIGC detection show that ATAR achieves 78.5% average image-level F1 on six zero-shot IMDL benchmarks, surpassing the strongest MLLM baseline by 11.8 percentage points, and remains competitive with specialized detectors on other tasks while producing substantially more faithful and grounded explanations.

cs.CV↗
arXiv2026

Factorized neural posterior estimation for rapid and reliable inference of parameterized post-Einsteinian deviation parameters in gravitational waves

The direct detection of gravitational waves (GWs) by LIGO has confirmed general relativity (GR), but testing GR via GWs requires estimating parameterized post-Einsteinian (ppE) deviation parameters in waveform models. Traditional Bayesian inference methods like Markov chain Monte Carlo (MCMC) provide reliable estimates but suffer from prohibitive computational costs, failing to meet the real-time demands and surging data volume of future GW detectors. Here, we propose a factorized neural posterior estimation framework: we construct independent normalizing flow models for each of the nine ppE deviation parameters, and effectively integrate prior information from other source parameters via a conditional embedding network. Leveraging a hybrid neural network with a convolutional neural network and a Residual Neural Network for feature extraction, our method performs rapid and statistically reliable posterior inference directly from binary black hole signals. Compared to conventional MCMC, our approach achieves millisecond-scale inference time with a speedup factor of $9 \times 10^4$. Comprehensive validations show that the posterior estimates pass the Kolmogorov-Smirnov test and achieve empirical coverage probabilities close to theoretical targets. We apply this method to the GW150914 event and find that the resulting posterior distributions are in good agreement with existing results. This work demonstrates the great potential of deep learning for GW parameter estimation and provides a viable technical solution for real-time GR tests with next-generation detectors.

astro-ph.IM↗
arXiv2026

Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation

Few-step streaming audio--video generation requires both causal modeling and step distillation, yet standard training recipes face two context-related challenges. Teacher forcing pairs clean history with a noisy target, but supervises predictive contextual representations only indirectly through velocity prediction. Meanwhile, directly reusing bidirectional score models in causal Distribution Matching Distillation (DMD) creates a mismatch between generation and scoring contexts. We address these challenges with Salt++, a two-stage post-training framework comprising Causal Self-Flow (CSF) and context-aligned autoregressive DMD. CSF exploits contextual information asymmetry by varying the history while keeping the noisy target fixed: a noise-mixed-history student aligns its intermediate representations with those of a clean-history exponential-moving-average teacher. This self-supervised signal encourages the student to extract semantic information and improves cross-modal alignment. Context-aligned AR DMD shares the causal mask and prefix across generator sampling, fake-score training, and real-score evaluation to match generated and reference distributions under a block-conditional KL objective. With calibrated teacher guidance, it performs clean-prefix few-step distillation and then adapts to generated histories without switching objectives or requiring separate consistency distillation. At 480p, Salt++ improves visual and motion quality by 57% and 45% over OmniForcing on JavisBench under the same 4-step causal setting. A separate scale-wise post-training stage extends Salt++ to 4-step $1664\times960$ generation, outperforming bidirectional LTX-2 on six of seven reported metrics. Project page: https://xingtongge.github.io/Saltpp

cs.CV↗
arXiv2026

High-fidelity geometric quantum gates exceeding 99.9% in germanium quantum dots

Achieving high-fidelity and robust qubit manipulations is a crucial requirement for realizing faulttolerant quantum computation. Here, we demonstrate a single-hole spin qubit in a germanium quantum dot and characterize its control fidelity using gate set tomography. The maximum control fidelities reach 97.48%, 99.81%, 99.88% for the I, X/2 and Y /2 gate, respectively. These results reveal that off-resonance noise during consecutive I gates in gate set tomography sequences severely limits qubit performance. Therefore, we introduce geometric quantum computation to realize noiseresilient qubit manipulation. The geometric gate control fidelities remain above 99% across a wide range of Rabi frequencies. The maximum fidelity surpasses 99.9%. Furthermore, the fidelities of geometric X/2 and Y /2 (I) gates exceed 99% even when detuning the microwave frequency by +-2.5 MHz (+-1.2 MHz), highlighting the noise-resilient feature. These results demonstrate that geometric quantum computation is a potential method for achieving high-fidelity qubit manipulation reproducibly in semiconductor quantum computation.

quant-ph↗
arXiv2026

Shared Worlds, Private Minds: Structured Memory for Long-Form Writing as World Creation

LLM agents that write long-form fiction need an explicit memory of the evolving storyworld to keep new events consistent with established facts. Such memory must keep heterogeneous narrative information distinct, integrate story developments across granularities, and recover dependencies that a writing request leaves implicit. We present NarraWorld, a structured memory system for long-form writing that treats memory construction as world creation. From a shared evidence-grounded graph, NarraWorld derives four connected views: world facts, per-character beliefs, open developments, and hypothetical branches (possible-world continuations). Hierarchical aggregation with atomic closure consolidates events into scenes, plotlines, and plots, keeping each higher-level node traceable to its constituent source spans. For retrieval, planned reconstruction infers a query's dependencies from the current narrative situation and a preview of memory, then assembles the relevant records within a token budget. Across three writing benchmarks, NarraWorld achieves the strongest aggregate results. Its memory also transfers to situated role-playing and largely preserves recall on a general-purpose long-term memory benchmark, paving the way for agents that sustain coherent storyworlds across diverse narrative tasks.

cs.CL↗
arXiv2026

STR: Supervised Transcoder Replacement for Reducing Steering Side Effects

Model steering can strengthen a target behavior while degrading other useful behaviors. We introduce Supervised Transcoder Replacement (STR) to reduce these side effects for existing steering methods, including those fitted without a protection objective. STR learns a replacement for the multilayer perceptron (MLP) computation at the steering layer through supervision for target control, non-target preservation, and fidelity without steering. Selected steering methods then fit directions on the frozen replacement while retaining their own fitting objectives. We evaluate three steering methods across Gemma and Llama models using Corrigibility preferences and four harmful-request safety datasets. SALAD-Bench supplies protection training data and a separate in-distribution evaluation split; HarmBench, AdvBench, and StrongREJECT are reserved for out-of-distribution testing. STR substantially reduces steering side effects on the in-distribution evaluation and extends this protection to the unseen safety datasets while retaining effective target control. For target-only supervised steering vectors, pooled out-of-distribution attack success rate falls from 42.46% to 14.42% on Gemma-3-4B and from 34.97% to 12.91% on Gemma-3-12B. These results show that replacement training can benefit steering methods fitted without protection objectives.

cs.AI↗
arXiv2026

Thermodynamic geometry as the missing link: toward a unified framework for black hole first-order phase transitions

Black hole first-order phase transitions have been described by several seemingly independent frameworks, including local geometry, global topology, complex analysis, and thermodynamic geometry. While the first three have been unified, thermodynamic geometry has remained outside. We prove that the divergence points of the normalized Ruppeiner curvature scalar $R_N$ coincide exactly with the solutions of $T'(r_h)=0$, where $r_h$ is the horizon radius. These solutions include extremal points (spinodal points) and stationary inflection points (thermodynamic critical points). Thus, the divergence of $R_N$ is a necessary but not sufficient condition for a first-order phase transition. This clarifies the mathematical origin of curvature divergence and why thermodynamic geometry can reliably indicate but not alone confirm phase transitions. Using the local geometric framework as a central framework, we incorporate Ruppeiner geometry into this unified picture; a similar analysis also applies to Weinhold geometry. Consequently, the four frameworks are unified within a single structure based on the local folding of the temperature function. This advances our understanding of the mathematical structure of black hole first-order phase transitions and provides clues for possible extensions to other types of phase transitions.

gr-qc↗
arXiv2026

TARL: Transaction-Aware Reliable Ledgers for Executable Memory Management in Long-Term Agents

Persistent memory helps long-term agents retain knowledge, yet a single update error can repeatedly distort future retrieval and reasoning. Most existing systems reduce memory updating to a binary Write/Hold decision, which cannot distinguish whether new information should be added, ignored, used to revise an outdated belief, rejected as unreliable, or deferred for verification. These choices may share the same binary label while producing fundamentally different memory states. We introduce TARL, a memory state update framework that maps each statement to one of five executable actions. TARL identifies the affected memory, resolves its temporal scope, compares source reliability, and updates accepted, pending, and rejected ledgers. It is further trained by comparing the memory states produced by alternative update operations, encouraging the model to select the operation that leads to the correct result. We also introduce TARL-Mem, a benchmark with fine-grained action labels and next-state targets. Across in-domain, cross-source, temporal, counterfactual, and sequential evaluations, TARL improves action prediction and state recovery, reduces memory pollution, preserves conflicting evidence, and limits cumulative corruption.

cs.AI↗
arXiv2026

Cross-Model Autoscaling for Shared LLM Serving

Multi-model LLM serving is moving toward shared MaaS clusters, where co-hosted models compete for a fixed GPU budget while each model experiences time-varying demand and must satisfy its own latency SLO. Existing LLM autoscalers remain largely model-local: their signals expose local runtime activity or delayed latency outcomes, and their scale-up or provisioning decisions do not directly determine how shared capacity should be allocated across competing models. We present the Token-service-share Rebalancing Engine (TRE), a control-plane framework for hot-switched multi-model LLM serving. TRE introduces Token Service Share (TSS), a calibrated, demand-normalized signal that estimates effective token service per active or queued request and yields a comparable health score across heterogeneous models and SLO classes. Guided by TSS, TRE coordinates bounded receiver--donor capacity movement under a fixed GPU budget: it separates fast rescue from slower rebalancing and incrementally reallocates active replicas toward models with the largest calibrated service deficits. We implement TRE on a Kubernetes-based hot-switch serving stack without modifying the inference scheduler. Across seven LLM serving traces, TRE reduces P95 end-to-end latency by 11.9--79.0\% and P99 latency by 12.5--72.6\% compared with a state-of-the-art KV-cache-based reactive autoscaler running on the same hot-switch runtime. The gains hold on both targeted stress probes and production-derived conversation/code traces, where TRE reduces P95/P99 latency by 50.8/63.7\% and 79.0/72.6\%, respectively. These results show that effective hot-switched autoscaling requires not only fast replica actuation, but also calibrated service-deficit signals and coordinated cross-model capacity arbitration. Our code and artifacts are available at https://github.com/zxzx9898/Token-service-share_Rebalancing_Engine.

cs.DC↗
arXiv2026

A one-sided constrained martingale transport between two uniform laws

We minimize $\mathbb E[h(Y-X)]$ over martingale couplings of $\text{Unif}[-1,1]$ and $\text{Unif}[-2,2]$ satisfying $Y\geq X-k$, where $h\in C^1([-3,3])$ has convex derivative. Feasibility holds exactly for $k\geq1$. For each such $k$, we construct a coupling that minimizes all costs in this class. For $1<k<3$, its support consists of two graphs, with $D(x)=x-k$ on $[k-2,1]$. The maps admit an explicit parametrization for $2\leq k<3$ and are determined by scalar equations with unique admissible roots for $1<k<2$. We prove optimality by a dual inequality, using an analytic estimate in the latter range. At $k=1$ the optimizer is $Y=X\pm1$ with equal probabilities; for $k\geq3$ it is the ordinary left-curtain coupling. In the unconstrained problem, left-monotonicity identifies the left-curtain coupling, which is optimal for this cost class. Under the constraint, a discrete example shows that the corresponding support condition, even together with every two-source comparison, does not imply optimality.

math.PR↗
arXiv2026

Evaluation of OpenAI o1: Opportunities and Challenges of AGI

This comprehensive study evaluates the performance of OpenAI's o1-preview large language model across a diverse array of complex reasoning tasks, spanning multiple domains, including computer science, mathematics, natural sciences, medicine, linguistics, and social sciences. Through rigorous testing, o1-preview demonstrated remarkable capabilities, often achieving human-level or superior performance in areas ranging from coding challenges to scientific reasoning and from language processing to creative problem-solving. Key findings include: -83.3% success rate in solving complex competitive programming problems, surpassing many human experts. -Superior ability in generating coherent and accurate radiology reports, outperforming other evaluated models. -100% accuracy in high school-level mathematical reasoning tasks, providing detailed step-by-step solutions. -Advanced natural language inference capabilities across general and specialized domains like medicine. -Impressive performance in chip design tasks, outperforming specialized models in areas such as EDA script generation and bug analysis. -Remarkable proficiency in anthropology and geology, demonstrating deep understanding and reasoning in these specialized fields. -Strong capabilities in quantitative investing. O1 has comprehensive financial knowledge and statistical modeling skills. -Effective performance in social media analysis, including sentiment analysis and emotion recognition. The model excelled particularly in tasks requiring intricate reasoning and knowledge integration across various fields. While some limitations were observed, including occasional errors on simpler problems and challenges with certain highly specialized concepts, the overall results indicate significant progress towards artificial general intelligence.

cs.CL↗
arXiv2026

Stochastic linear-quadratic control problem for regime-switching jump-diffusion system and its application to finance

This paper investigates a stochastic linear-quadratic (SLQ) control problem for a regime-switching jump-diffusion system. Unlike traditional regime-switching diffusion systems that couple a diffusion process with a Markov chain, we incorporate the jumps of the Markov chain into the state equation. This modeling methodology effectively captures potential gains or losses of the system during the regime transitions. It should be noted that the introduction of Markov chain jumps into the state equation leads to increased complexity in the corresponding coupled differential Riccati equations (CDREs), thereby rendering the solvability of the control problem more challenging. Under the assumption that the cost functional is uniformly convex, we establish the unique solvability of the corresponding CDREs. Building upon this foundation, we derive a closed-loop representation for the unique open-loop optimal control. Finally, we apply our theoretical results to the mean-variance portfolio selection problem in a regime-switching financial market with Markov chain jumps and obtain its efficient frontier.

math.OC↗
arXiv2026

An explicit rational lemniscate counterexample with certified separators

In the setting of the previously reported degree-seven counterexample of ani, we present an explicit monic polynomial with real rational coefficients and a direct proof by certified separators. The polynomial has seven simple zeros in the open unit disk. Every continuous path joining distinct zeros in its closed unit sublevel set has image of one-dimensional Hausdorff measure greater than $2+10^{-8}$. Five piecewise-linear graphs exclude twenty of the twenty-one zero pairs; two short forbidden segments force a quantitative detour for the remaining pair. Exact rational Bernstein certificates verify the graph inequalities on forty-four terminal intervals and their unbounded tails. The proof does not require critical-point counting or analytic inverse branches. We separately record the general continuum and dilation arguments that transfer path-length obstructions to Hausdorff measure and to closed sublevel sets. Those transfers are not asserted as new principles. The focus is the explicit real-coefficient construction, its separation certificates, and its verified numerical margin, rather than a first negative answer to the length-two question or a disproof of every larger universal bound.

math.GN↗
arXiv2026

NeuIDO: Neural Intrinsic Dynamics Operator for Physics-Informed 4D World Models

World models aim to capture environmental dynamics and predict future trajectories, showing growing potential for embodied intelligence. Physics-informed 4D generation integrates physical simulation to predict 3D object interactions, offering a promising pathway toward world models. However, this paradigm relies on manually imposed dynamical assumptions rather than internalizing world dynamics, and thus still leaves a gap toward a true world model. To bridge this gap, we propose NeuIDO, a novel world dynamics modeling framework that learns a unified intrinsic dynamics representation from visual observations, advancing physics-informed 4D generation toward a world model. Specifically, we formulate world modeling as a neural operator learning problem and introduce a two-stage training strategy to learn a generalizable mapping from the visual observation distribution to the intrinsic dynamics distribution. Building on this observation-dynamics mapping, NeuIDO enables zero-shot dynamics inference directly from videos and can be further aligned with complex real-world dynamics via few-shot adaptation. Extensive experiments demonstrate that NeuIDO effectively unifies the intrinsic dynamics underlying diverse visual observations into a shared representation and rapidly infers dynamics in novel scenes.

cs.CV↗
arXiv2026

WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory and In-Context Learning

World Action Models (WAMs) offer a promising paradigm for robotic manipulation by jointly modeling visual state transitions and robot actions. However, existing WAMs are constrained by limited temporal context, coarse episode-level language supervision, and predominantly text-only conditioning, which hinder task-progress tracking and fine-grained language-video-action grounding while limiting visual-context reasoning and cross-embodiment transfer. In this paper, we introduce WorldScape Policy 2.0, a controllable WAM with reasoning-augmented long short-term memory. Its causal short-term visual memory supplies recent observations as DiT prefill to preserve local interaction dynamics, while its long short-term event memory organizes historical VLM outputs into global-history, local-active, and event-boundary representations for progress-aware retrieval. The retrieved history augments perception and autoregressively generated planning tokens, yielding an implicit subgoal condition for autonomous planning; semantic forcing further transfers event-level instruction semantics into this latent planning pathway. To establish fine-grained multimodal controllability, we construct ManipEvent-5M, an event-grounded embodied pretraining dataset containing nearly 5 million event segments with aligned action trajectories, episode-level task instructions, segment-level subtask captions, goal images, and video demonstrations. These designs provide a unified interface for autonomous planning from high-level instructions and controllable execution from fine-grained text, goal-image, or video-context prompts. Experiments in both simulation and real-world platforms demonstrate superior capabilities in long-horizon autonomous planning, fine-grained instruction following and in-context adaptation.

cs.RO↗
arXiv2026

Singular Submodules of Abelian Groups over Their Endomorphism Rings

Let $A$ be an abelian group and $E=\Endo_{\Z}(A)$. We give a module-theoretic description of the singular $E$-submodules asked for in Fuchs' Problem~1.2. For a unital ring $R$ and a left $R$-module $M$, put $W=I_R({}_RR)\oplus I_R(M)$ and $J=\Jaco(\Endo_R(W))$, and let $u$ be the image of $1_R$. The classical essential-kernel criterion yields \[ Z_R(M)=M\cap Ju. \] For $R=E$ and $M=A$, all singular submodules are therefore the $E$-submodules of $A\cap Ju$. Writing $T=t(A)$ and $B=A/T$, we prove a torsion-transfer formula, identify the torsion part as $\bigoplus_p pT_p$, and describe simultaneous prime lifting by a canonical obstruction. The resulting extension gives an $\Extt/\Homm$ parametrization of all singular submodules. We obtain explicit formulas for torsion groups and for $\Z(p^\infty)\oplus B$ with $B$ torsion-free; in the latter case the fully invariant subgroup lattice of $B$ occurs as an interval. The general description retains the induced endomorphism action and extension data, rather than giving a classification by classical group invariants.

math.GN↗
arXiv2026

Selective Cotton Boll Localization for Robotic Harvesting: Evaluation of Deep Learning Vision Models Under Field Conditions

This study developed and evaluated a deep-learning-based perception framework for selective robotic cotton picking. The dataset contained 1,008 annotated field images collected using three cameras under varying natural lighting and weather conditions. Object-detection models from the YOLOv8 through YOLOv13 families were evaluated using their default configurations, while segmentation performance was assessed using YOLOv8-seg, YOLOv11-seg, YOLOv12-seg, the Segment Anything Model (SAM), SAMv2.1, FastSAM, and Grounded-SAM with the Recognize Anything Model (RAM). Among the detection models, GELAN-s achieved the most favorable balance between mean average precision (mAP) and inference speed, obtaining an mAP of 86.1%, precision of 81.6%, recall of 76.6%, and an F1-score of 79.0%, with an average inference time of 42.3 ms per image. Among the direct segmentation models, YOLOv12-m-seg provided the most favorable balance between AP@0.5 and FPS, achieving a segmentation AP@0.5 of 83.7% with an inference time of 20.4 ms per image. In the detection-prompted segmentation approach, bounding-box prompts generated by GELAN-s improved the localization of cotton bolls for SAM and SAMv2.1, while SAMv2.1 Tiny consistently outperformed FastSAM and Grounded-SAM with RAM. In the area-based evaluation against manually annotated segmentation masks, YOLOv12-m-seg achieved an $R^2$ value of 0.966, compared with 0.860 for GELAN-s + SAMv2.1 Tiny. Field experiments conducted using a UR5e robotic manipulator, a custom end-effector, and a ZED2i stereo camera further validated the effectiveness of the YOLOv12-m-seg model for real-time cotton boll detection, segmentation, and selective picking under varying confidence levels. These results demonstrate that YOLOv12-m-seg provides an efficient perception model for robotic cotton harvesting and has strong potential for field deployment.

cs.CV↗
arXiv2026

CLASP: A Cluster-Level Autonomous Selective Picking Robot with a Soft Rolling-Band Gripper for Fresh-Market Blueberry Harvesting

Fresh-market blueberries require selective, gentle picking, which is labor-intensive and expensive. Over-the-row machine harvesters are fast but non-selective, bruising mixed-ripeness fruit and limiting yield to the processing market. Selective robotic harvesters typically target individual fruits rather than fruit clusters, which limits harvesting efficiency for small, densely clustered blueberries. This paper presents CLASP, a Cluster-Level Autonomous Selective Picking robot with a Soft Active Rolling-Band Gripper (SARB-Gripper). Two compliant bands envelop the cluster and roll against the fruit, drawing mature berries off in sequence, while closed-loop regulation of the pulling force keeps the applied load below the immature detachment threshold. A global-to-local perception pipeline pairs an eye-to-hand camera for global cluster detection and target selection with an eye-in-hand camera for local localization and cluster orientation estimation. Field measurements confirm a clear detachment-force separation between mature and immature fruit, and the SARB-Gripper reproduces a commanded pulling force to within \SI{3.7}{\percent}, enabling selective harvesting at the cluster level. In end-to-end field trials, CLASP autonomously grasped 23 of 25 presented clusters (\SI{92}{\percent}). With the component cost of approximately \$3326 per unit, CLASP offers a scalable approach to selective cluster-level harvesting for fresh-market blueberries.

cs.RO↗