arXiv subjects

Xin Jiang

Publications and source records attributed to Xin Jiang.

At least 19 recordsLinked to original sources

arXiv2026

WolfSociety: Understanding Collective Risk from Harmful-Agent Scaling in Financial Agent Societies

Safety evaluations typically focus on individual agents, but interacting agents can spread harmful information and influence the environment in which later decisions are made. We study how collective failure changes with harmful-agent fraction and society size in a controlled financial agent society, where agents communicate over a social network and trade in a shared market. In the primary financial scenario, collective failure requires broad harmful diffusion together with severe price dislocation or liquidity stress. Across all tested society sizes, failure remains rare at low harmful fractions but rises sharply over a narrow range. As society size grows from N=100 to N=2000, the harmful fraction associated with a 50% failure probability decreases from 4.7% to 2.2%, while the corresponding number of harmful agents increases from approximately 5 to 44. In contrast, when the number of harmful agents is held fixed, their impact becomes weaker as the society grows. Controlled interventions further show that broader network reach shifts the collapse boundary toward lower harmful fractions, whereas stronger conformity alone has little effect. To characterize these effects, we introduce Agent Society Dynamics, a finite-size framework for relating harmful-agent fraction, society size, and interaction structure to collective failure. Overall, our results reveal a nonlinear, size-dependent collapse transition in financial agent societies, showing that collective failure depends not only on the prevalence of harmful agents but also on the size and interaction structure of the surrounding society. Code is available at https://github.com/SAIL-Research-Lab/WolfSociety.

physics.soc-ph↗

arXiv2026

ERR+: Sequential Entropy Resolution for Efficient and Decisive LLM Reasoning

Large reasoning models achieve strong performance on complex tasks by generating extended chain-of-thought (CoT) traces via reinforcement learning with verifiable rewards (RLVR). While current RLVR methods have achieved strong results with correctness-based reward signals, they provide limited guidance on the quality of the reasoning process itself, leaving the internal reasoning structure largely unoptimized. Through empirical analysis across multiple model families, we identify a consistent pattern: correct reasoning trac es exhibit more frequent and larger token-level entropy drops within the thinking phase than incorrect ones. We propose ERR+, a two-phase RLVR framework grounded in this observation. The first phase trains with the Entropy Relief Reward (ERR), a bonus proportional to cumulative token-level entropy drops in the thinking phase, log-normalized by response length. Unlike prior methods that suppress entropy, ERR rewards the resolution of uncertainty while leaving exploratory high-entropy states unconstrained. The second phase introduces the Robust Relative Efficiency Reward, which scores each response's length against co-generated peers via a $\tanh$-transformed within-group $z$-score. We provide a formal analysis showing that joint optimization of the two objectives induces gradient conflict in early training, motivating the sequential design . Experiments on five datasets demonstrate consistent improvements in both accuracy and response conciseness across model backbones. Our code is available at https://github.com/XrkArul/err_response

cs.LG↗

arXiv2026

What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents

LLM agents increasingly rely on generated interaction data to learn how to interact with external environments. Agentic data generation must maintain consistency among environments, tasks, interactions, and success signals while producing experience that is useful rather than merely abundant. Existing work spans many agent domains, but domain-centered organization and heterogeneous evaluation often obscure common generation mechanisms and conflate candidate construction with verification and selection. This work develops a two-level framework for the field. First, we represent agentic data as a common factorized object $(E,q,\tau,v)$, comprising an environment specification, task signal, interaction realization, and optional verifier. We organize generation paradigms by their primary anchor and dependency structure. Second, we formulate generation as constrained distribution design through the Accuracy-Complexity-divErsity (ACE) lens. Accuracy establishes the feasible support of grounded and internally consistent data. Within this support, Complexity places learning mass relative to the capability of a declared learner and execution configuration, while divErsity controls coverage and redundancy of data. Using this framework, we explore how prior work verifies generated experience, constructs and calibrates difficulty, and expands behavioral coverage. The literature reveals a shift toward execution-grounded accuracy, learner-relative complexity, and diversity beyond surface variation or dataset size. We further discuss broader directions and emerging trends in agentic data generation through the ACE lens, including their implications for scaling, data sources, training regimes and adaptive learning. Overall, the central challenge is not simply to generate more data, but to continually allocate valid, informative, and non-redundant experience as agents and environments evolve.

cs.AI↗

arXiv2026

Complexity and Stability of Neural Activity Across Aging and Neurodegenerative Disease

Objective: EEG signals fluctuate continuously even within a fixed cognitive state, but an important question is whether the brain still reuses similar activity patterns to represent information over time. Methods: To address this, we model EEG as distributions of windowed activity patterns and quantify their temporal stability using Wasserstein distance, while intrinsic dimensionality captures representational complexity. Results: Across multi-task, lifespan, and clinical EEG datasets, we find that neural representations show constrained, condition-specific stability rather than unconstrained drift. Higher intrinsic dimensionality is consistently associated with lower stability, suggesting that richer representational spaces are less reproducible over time. Both measures exhibit reproducible spatial organization, with posterior regions showing higher dimensionality and lower stability than frontal regions. Healthy aging is characterized by increased dimensionality and reduced stability, whereas mild cognitive impairment and Alzheimer's disease show a joint collapse of both. Conclusions: These findings provide a distribution-level framework for understanding neural stability across cognition, aging, and disease. Significance: This framework offers a principled approach to quantifying neural representational stability, with potential utility as a sensitive biomarker for tracking cognitive aging and neurodegeneration in clinical settings.

q-bio.NC↗

arXiv2026

DailyBench: A Unified Benchmark for AI-Generated and Manipulated Images from Modern Generative Models

Recent advances in generative models have shifted AI-generated image detection from identifying easily distinguishable, fully synthetic images to identifying highly realistic content generated by both modern generation and manipulation pipelines. However, existing detection benchmarks are often built with outdated generative models and primarily emphasize full-image synthesis, creating a growing mismatch between benchmark data and the images encountered in real-world generation and editing scenarios. To bridge this gap, we introduce DailyBench, a high-quality unified benchmark for evaluating whether AI-generated image detectors can generalize across both modern full-image synthesis and object-level manipulation. DailyBench contains two complementary subsets: FakeBench, which includes high-quality images synthesized by recent open-source and commercial generative models, and ManipulationBench, which introduces challenging object-level edits applied to real images using advanced image-conditional models. This design makes DailyBench a realistic testbed for studying both generator-level generalization and manipulation-aware detection under subtle local edits. Experiments on DailyBench reveal substantial robustness gaps in current detectors: methods reporting 91-96% balanced accuracy on GenImage drop to 60-76% on FakeBench and 54-66% on ManipulationBench. These results show that existing detectors remain poorly generalized to realistic synthesis and manipulation, highlighting DailyBench as a rigorous testbed for developing robust and manipulation-aware AI-generated image detection methods. The project is available at https://dailybench.github.io/

cs.CV↗

arXiv2026

Local Linear Convergence of the Primal-Dual Hybrid Gradient Method for Semidefinite Programming

Primal-dual first-order methods are widely used for large-scale semidefinite programming (SDP), but their ability to compute highly accurate solutions is not well explained by global convergence theory alone. We study the local convergence of the primal-dual hybrid gradient (PDHG) method applied to a standard primal--dual SDP pair. We show that PDHG converges eventually (R-)linearly whenever the limiting KKT point satisfies either strict complementarity or primal--dual nondegeneracy. The proof views PDHG as a preconditioned proximal point method for the KKT inclusion and combines its descent inequality with a local error bound. Under strict complementarity, the error bound follows from the local spectral geometry of the positive semidefinite cone; under primal-dual nondegeneracy, it follows from strong regularity of the KKT mapping. We also give a simple SDP instance where both regularity conditions fail and PDHG can converge only sublinearly. This contrasts with linear programming, where PDHG admits a local linear convergence regime even for degenerate instances. Numerical experiments support the theory and identify difficult SDP instances where PDHG struggles to reach high accuracy.

math.OC↗

arXiv2026

MoWorld: A Flash World Model

The future of World Models depends not only on scaling model capability, but also on scaling practicality and inference efficiency. High-frame-rate inference enables responsive perception, planning, and control in real-world autonomous systems. To this end, we present MoWorld, a cost-effective yet high-performance Flash World Model with an end-to-end framework spanning data generation, pre-training, distillation, and efficient inference, enabling up to 50 FPS real-time interaction with cinematic visual quality without the need of high-end GPUs. To enable large-scale real-world deployment, MoWorld jointly optimizes model capability and cost throughout the entire development pipeline. Specifically, unlike existing approaches that primarily rely on large-scale video corpora, MoWorld is built upon a scalable 3D-native data engine accumulated from our large-scale 3D vision and generative modeling pipeline, enabling the efficient construction of geometrically consistent training data across diverse real-world and synthetic environments. Based on this foundation, a curriculum cross-frame pre-training strategy for stable and scalable World Model learning, an efficient denoising-step distillation algorithm to reduce diffusion training cost, and a mixed-precision parallel inference framework for low-cost real-time deployment. MoWorld is the first real-time interactive World Model built on the Neural Processing Unit (NPU) and can achieves up to 50 FPS in such the devices, enabling practical and efficient deployment at scale. Comprehensive evaluations demonstrate that MoWorld achieves leading performance; notably, its average inference cost is only 30\%-50\% of that of existing World Models, providing a practical foundation for large-scale real-world applications of World Models. We also demonstrate diverse applications of MoWorld.

cs.CV↗

arXiv2026

A Relaxation and Rectification (ReCR) Framework for Systems with Linear and Complementary Constraints: Theoretical Foundation, Algorithms and Numerical Experiments

Systems defined by linear and complementarity constraints (SLCCs) arise frequently in engineering, economics, and other related fields. They also appear in the optimality conditions of many challenging optimization models, such as bilinear optimization and linearly constrained quadratic optimization. It is known that finding a feasible solution to an SLCC is NP-hard in general. In this paper, we study the feasibility problem for a given SLCC: either find a feasible solution or determine that the system is infeasible. To this end, we introduce a universal relaxation theory (URT), which reformulates SLCC feasibility as an equivalent bilinear optimization problem with linear constraints in a lifted space. We then analyze the resulting bilinear model and derive necessary and sufficient optimality conditions for its global solutions. Based on these theoretical insights, we introduce a relaxation-rectification (ReCR) framework for finding a feasible solution to a given SLCC instance or certifying infeasibility. We develop several ReCR methods that differ in their working spaces and subproblem formulations and analyze their convergence properties. We also develop a numerical procedure for obtaining an infeasibility certificate when the ReCR methods do not find a feasible solution. We conduct numerical experiments to evaluate the reliability, robustness, and scalability of the proposed ReCR methods and compare them with existing SLCC solvers. On the tested small- and large-scale LCP instances from the literature, the proposed ReCR methods typically find feasible solutions in a few iterations. We also extend the benchmark with more challenging medium-scale SLCC instances, on which the proposed hybrid ReCR (H-ReCR) method exhibits promising performance.

math.OC↗

arXiv2026

Low-threshold efficient N${_2^+}$ lasing driven by sub-cycle soliton dynamics in a hollow waveguide

The phenomenon of N${_2^+}$ lasing, observed in femtosecond-laser filamentation, attract considerable interests in recent several years, with great application potentials in fields of remote sensing and ultrafast spectroscopy. Efficient N${_2^+}$ lasing at relatively-low pump energies and with high beam quality, while being highly-demanded for applications, remains, however, quite challenging in practical experiments. Here, we demonstrate a new route of generating low-threshold N${_2^+}$ lasing with unprecedently-high efficiency, which is enabled by soliton dynamics in a gas-filled hollow-tapered-capillary system. High-order-soliton compression of a 12-fs, 10-${\mu}$J-level pump pulse forms a sub-cycle asymmetric transient that tunnel-ionizes N${_2}$ to N${_2^+}$ and, through direct, single-photon resonant excitation, creates population inversion between the ground state ${X^2\Sigma_g^+}$ and the excited state ${B^2\Sigma_u^+}$${-}$a dynamic process distinct from the widely adopted three-state coupling picture${-}$and remarkably at unexpectedly low pump energy. In the experiments, we obtained 100-nJ-level N${_2^+}$ lasing pulses at 391 nm with conversion efficiencies up to 3.3$\times$10$^{-3}$, at pump energies of less than 50 ${\mu}$J. These results represent improvement of more than one orders of magnitude in both generation efficiency and lasing threshold, compared with prevailing filamentation-based schemes. Our study bridges two generally-disparate fields (sub-cycle soliton dynamics and N${_2^+}$ lasing), and paves the way for narrow-band, high-beam-quality lasing pulses that may find wide applications in advanced spectroscopy and nonlinear pump-probe experiments.

physics.optics↗

arXiv2026

Scaling Learning-based AEB with Massive Unlabeled Data

This paper studies how to scale learning-based automatic emergency braking (AEB) with massive unlabeled fleet data under production constraints. Our approach is based on meta-feedback semi-supervised learning (MF-SSL), where a teacher generates pseudo labels for unlabeled driving data and is updated using a small labeled anchor set as safety-critical feedback. In production, anchor ambiguity and labeled-unlabeled mismatch can amplify systematic pseudo-label errors, leading to spurious triggers. We propose a stabilized MF-SSL framework with (i) Noise-Aware Decoupling, which removes ambiguity-prone anchors from the teacher's supervised update path, and (ii) kinematics-gated pseudo-labeling with a teacher conflict penalty to suppress mismatch-induced risk hallucinations on unlabeled data while maintaining broad coverage. Extensive experiments show consistent gains as unlabeled data scale from 1M to 1B windows, improving safety while keeping comfort stable. The 1B-trained student model is deployed to hundreds of thousands of vehicles and validated over \$10^9$ km of driving, achieving a positive-to-false activation ratio exceeding 100:1 and a 35% improvement in accident-free driving mileage over a production rule-only baseline.

cs.LG↗

arXiv2026

Learning to Annotate Delayed and False AEB Events: A Practical System for Extreme Class Imbalance and Asymmetric Label Noise

Autonomous Emergency Braking (AEB) optimization relies on accurately annotated real-world trigger events, particularly rare but critical delayed and false AEB triggers that expose system deficiencies. However, these minority samples comprise less than 5% of thousands of daily triggers, making manual annotation prohibitively expensive at scale. We present the first automated AEB annotation framework to address this problem. During development, we identified two fundamental challenges that severely impair delayed/false trigger annotation accuracy: (1) Extreme class imbalance where delayed/false triggers are overwhelmed by true triggers; (2) Asymmetric label noise where mislabeled majority samples (true triggers) suppress minority samples (delayed/false triggers) learning. To overcome these challenges, we propose two key innovations: (1) Specific data augmentation that synthesizes realistic samples by manipulating focal target attributes, transplanting ego-vehicle dynamics, and masking non-focal agents; (2) noise suppression using stable hardness estimation and probe-guided adaptive threshold to clean mislabeled true trigger samples. Crucially, we deploy our model as a practical annotation system with full-stack architecture, efficiently identifying critical delayed/false triggers from thousands of daily AEB events. Production results demonstrate 80% improvement in recall of delayed/false triggers and 50% reduction in manual workload. Beyond immediate gains, the system enables continuous self-improvement through accumulated high-quality annotations, establishing a necessary data foundation for on-vehicle AEB system optimization

cs.RO↗

arXiv2026

Sinkhorn-CPD: Robust point cloud registration via unbalanced entropic optimal transport

Coherent Point Drift (CPD) is widely used for rigid point cloud registration because of its soft correspondences and closed-form parameter updates. However, CPD's target-side marginal constraint forces every observation, including outliers, to receive exactly unit probability mass. This assumption degrades registration accuracy under heavy outliers and partial overlap. Optimal transport (OT) methods can handle missing mass through unbalanced formulations, but require hand-tuned annealing schedules. In this paper, we propose Sinkhorn-CPD, which replaces CPD's target-side marginal constraint with dual Kullback-Leibler penalties, allowing the algorithm to discard outliers on both sides. The resulting formulation is a fully unbalanced entropic optimal transport problem, which can be efficiently solved by generalized Sinkhorn iterations. Moreover, Sinkhorn-CPD preserves the closed-form Procrustes and variance updates of CPD. In our method, the variance sigma^2 plays the role of the entropic regularization parameter, which induces an automatic annealing schedule from diffuse to sharp correspondences without manual temperature tuning. Experiments on synthetic, cross-category, and scan-to-CAD benchmarks show that Sinkhorn-CPD achieves state-of-the-art accuracy, with strong robustness to outliers and partial overlap.

cs.CV↗

arXiv2026

See More, Match Better: Multi-Source Feature Fusion for Two-View Correspondence Learning

Two-view correspondence learning aims to distinguish true correspondences (inliers) from false ones (outliers) in image pairs by leveraging their underlying differences. Existing methods mainly rely on coordinate-based geometric consistency. However, they often struggle with pseudo-consistent outliers in scenes containing repetitive structures, textureless regions, or locally similar geometric patterns. To address this limitation, we propose TriMatch, a multi-source feature fusion framework for two-view correspondence learning, which consists of two parts: feature extraction and feature refinement. In feature extraction, TriMatch jointly extracts geometric, texture semantic, and structural semantic features to provide complementary evidence for correspondence discrimination. To bridge the gap between semantic and geometric features, texture and structural semantic features are aligned with geometric features through dedicated Texture-Geometric Alignment and Structural-Geometric Alignment modules, respectively. We further introduce a Semantic-Guided Correspondence Modulation module, which modulates geometric features using semantic information to suppress geometrically plausible but semantically inconsistent correspondences. In feature refinement, a Hierarchical Semantic-Enhanced Correspondence Refinement strategy progressively models correspondence dependencies and recalibrates multi-context feature responses, enabling more reliable inlier-outlier discrimination. Extensive experiments demonstrate the effectiveness, robustness, and generalization capability of TriMatch.

cs.CV↗

arXiv2026

YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition

Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory overhead, which inflates infrastructure costs and throttles scalability. To address this, we propose YouZhi-LLM, a highly efficient financial LLM empowered by a comprehensive structural transition and training pipeline natively built on the Huawei Ascend ecosystem. At its algorithmic core, YouZhi-LLM features a layer-adaptive GQA-to-MLA transition framework that dynamically assigns per-layer FreqFold sizes, maximizing KV-cache compression while minimizing perplexity degradation. To recover representation capacity and inject domain expertise, the Ascend-based training pipeline seamlessly integrates generalized knowledge distillation with financial-specific supervised fine-tuning. Evaluations demonstrate the superiority of this systematic approach, with the adaptive transition reducing perplexity degradation by up to 35% over uniform baselines. Crucially, when evaluated on Ascend NPUs via vLLM-Ascend, the massive KV-cache reduction translates directly into deployment efficiency. Compared to their respective base models, YouZhi-7B yields a 12.3% improvement in average financial benchmark score alongside a 2.69$\times$ increase in maximum concurrency; similarly, YouZhi-14B achieves a 7.0% accuracy gain and a 2.43$\times$ concurrency boost, establishing a new paradigm for cost-effective, high-throughput financial inference.

cs.CL↗

arXiv2026

Exact Bulk-Boundary Pairs in AdS/CFT

We show that for a CFT$_D$ on a flat open solid torus, the two point function in the Weyl frame is exactly paired with a finite geodesic lying entirely in the AdS$_{D+1}$ bulk interior. This relation is exact and requires neither large $N$, strong coupling, nor heavy operators. The exactness is that of conformal kinematics; no semiclassical bulk dynamics is assumed. The standard boundary-anchored relation is a singular limit of the exact pair. For the free scalar, a mode expansion along $S^1$ generates an infinite tower of effective masses on $H_{D-1}$, whose intricate propagators resum exactly to the same simple higher-dimensional geodesic expression. Together with another exact pair between disjoint entanglement entropy and entanglement wedge cross-section found on the same open solid torus, this result points toward a broader exact-pair program in AdS/CFT.

hep-th↗

arXiv2026

Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice

Accurate and effective discrete image tokenization is crucial for long image sequence processing. However, current methods rigidly compress all content at a fixed rate, ignoring the variable information density of images and leading to either redundancy or information loss. Inspired by information entropy, we propose TaTok, a Theoretically grounded adaptive image Tokenization framework. We rigorously identify two key drawbacks in existing methods: information insufficiency when reconstructing images with patch tokens alone, and information redundancy among patch tokens. To address these, we introduce global tokens that model mutual information across patch tokens, and a Dynamic Token Filtering (DTF) algorithm based on cumulative conditional entropy to eliminate redundancy. Experiments confirm TaTok's state-of-the-art performance, delivering a 1.3x gFID improvement and 8.7x inference speedup. By allocating tokens according to information richness, TaTok enables more compressed yet accurate image tokenization, offering valuable insights for future research.

cs.CV↗

arXiv2026

Predictive and feedback signals differently shape the formation of group-level and individualized language representations

Adults vary greatly in how effectively they learn a new language, but the signals driving the learning processes and individual differences remain unclear. Over seven days, we tracked behavioral learning and collected fMRI data from 102 adults as they learned an artificial language with corrective feedback. We trained matched transformer models with prediction, feedback, or combined objectives and compared their internal representations to brain activity. Representations derived from the prediction-focused model accounted for the largest share of unique neural variance at the group level, despite the human task being feedback-based. Throughout model training, both objectives showed a shift in brain-model alignment from sensory to higher-order language and associative networks, indicating abstraction processing. Conversely, neural patterns related to the feedback model were most useful for predicting individual generalization outcomes on Day 7. These findings support a multi-signal model of adult language learning, in which prediction shapes a common neural learning architecture across learners, whereas feedback-related mechanisms better explain individual differences over time.

q-bio.NC↗

arXiv2026

Enhancement of vacuum-ultraviolet dispersive-wave emission using gas-filled tapered hollow-core fibers

The recent breakthroughs in laser-driving 229Th nuclear transition have created an urgent demand for coherent vacuum-ultraviolet (VUV) sources delivering high spectral brightness at the critical 148.38 nm isomer energy. However, generating sufficient photon flux to overcome the low nuclear excitation probability remains a challenge for compact setups. While resonant dispersive wave emission in gas-filled hollow-core fibers offers a promising route, standard capillaries face a fundamental trade-off: maximizing input coupling requires large core diameters, whereas efficient nonlinear VUV conversion demands the high intensities using small cores. Here, we resolve this conflict using a gas-filled tapered capillary fiber. This architecture utilizes a longitudinally decreasing core diameter to combine a large input aperture with adiabatic field concentration, thereby continuously enhancing the nonlinear interaction. Experimentally, we demonstrate a widely tunable source (135-240 nm) that achieves a twofold efficiency enhancement specifically at the 148.38 nm wavelength compared to uniform geometries. By providing a scalable route to high-flux VUV generation, this work establishes a critical tabletop tool for advancing solid-state nuclear clocks and time-resolved spectroscopy.

physics.optics↗