Searcharxiv⌕ Search

arXiv subjects

Chao Zhang

Publications and source records attributed to Chao Zhang.

At least 163 records · Page 9Linked to original sources
arXiv2026

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

We introduce HY-World 2.0, a multi-modal world model framework that advances our prior project HY-World 1.0. HY-World 2.0 accommodates diverse input modalities, including text prompts, single-view images, multi-view images, and videos, and produces 3D world representations. With text or single-view image inputs, the model performs world generation, synthesizing high-fidelity, navigable 3D Gaussian Splatting (3DGS) scenes. This is achieved through a four-stage method: a) Panorama Generation with HY-Pano 2.0, b) Trajectory Planning with WorldNav, c) World Expansion with WorldStereo 2.0, and d) World Composition with WorldMirror 2.0. Specifically, we introduce key innovations to enhance panorama fidelity, enable 3D scene understanding and planning, and upgrade WorldStereo, our keyframe-based view generation model with consistent memory. We also upgrade WorldMirror, a feed-forward model for universal 3D prediction, by refining model architecture and learning strategy, enabling world reconstruction from multi-view images or videos. Also, we introduce WorldLens, a high-performance 3DGS rendering platform featuring a flexible engine-agnostic architecture, automatic IBL lighting, efficient collision detection, and training-rendering co-design, enabling interactive exploration of 3D worlds with character support. Extensive experiments demonstrate that HY-World 2.0 achieves state-of-the-art performance on several benchmarks among open-source approaches, delivering results comparable to the closed-source model Marble. We release all model weights, code, and technical details to facilitate reproducibility and support further research on 3D world models.

cs.CV↗
arXiv2026

A Metropolitan-scale Multiplexed Quantum Repeater with Bell Nonlocality

Quantum repeaters can overcome exponential photon loss in optical fibers, enabling heralded entanglement between distant quantum memories. The definitive benchmark for this entanglement is Bell nonlocality; however, recent metropolitan-scale demonstrations based on single-photon interference (SPI) schemes have been limited to generating low-quality entanglement, falling short of Bell nonlocality certification. Here, we introduce a multiplexed quantum repeater protocol based on time measurements (MQR-TM), successfully combining the high heralding rate of SPI schemes with the phase robustness of two-photon interference (TPI) schemes. This approach achieves heralded entanglement distribution between two solid-state quantum memories over a record 14.5~km separation, generating a Bell state with a fidelity of $78.6 \pm 2.0\%$. We observe a CHSH-Bell inequality violation by 3.7 standard deviations, marking the first certification of Bell nonlocality in metropolitan-scale quantum repeaters. Our architecture supports autonomous quantum node operation without fiber channel phase stabilization, offering a practical framework for scalable quantum-repeater networks.

quant-ph↗
arXiv2026

Subspace-Guided Feature Reconstruction for Unsupervised Anomaly Localization

Unsupervised anomaly localization aims to identify anomalous regions that deviate from normal sample patterns. Most recent methods perform feature matching or reconstruction for the target sample with pre-trained deep neural networks. However, they still struggle to address challenging anomalies because the deep embeddings stored in the memory bank can be less powerful and informative. Specifically, prior methods often overly rely on the finite resources stored in the memory bank, which leads to low robustness to unseen targets. In this paper, we propose a novel subspace-guided feature reconstruction framework to pursue adaptive feature approximation for anomaly localization. It first learns to construct low-dimensional subspaces from the given nominal samples, and then learns to reconstruct the given deep target embedding by linearly combining the subspace basis vectors using the self-expressive model. Our core is that, despite the limited resources in the memory bank, the out-of-bank features can be alternatively ``mimicked'' to adaptively model the target. Moreover, we propose a sampling method that leverages the sparsity of subspaces and allows the feature reconstruction to depend only on a small resource subset, contributing to less memory overhead. Extensive experiments on three benchmark datasets demonstrate that our approach generally achieves state-of-the-art anomaly localization performance.

cs.CV↗
arXiv2026

FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios

The manufacturing sector is increasingly adopting Multimodal Large Language Models (MLLMs) to transition from simple perception to autonomous execution, yet current evaluations fail to reflect the rigorous demands of real-world manufacturing environments. Progress is hindered by data scarcity and a lack of fine-grained domain semantics in existing datasets. To bridge this gap, we introduce FORGE. Wefirst construct a high-quality multimodal dataset that combines real-world 2D images and 3D point clouds, annotated with fine-grained domain semantics (e.g., exact model numbers). We then evaluate 18 state-of-the-art MLLMs across three manufacturing tasks, namely workpiece verification, structural surface inspection, and assembly verification, revealing significant performance gaps. Counter to conventional understanding, the bottleneck analysis shows that visual grounding is not the primary limiting factor. Instead, insufficient domain-specific knowledge is the key bottleneck, setting a clear direction for future research. Beyond evaluation, we show that our structured annotations can serve as an actionable training resource: supervised fine-tuning of a compact 3B-parameter model on our data yields up to 90.8% relative improvement in accuracy on held-out manufacturing scenarios, providing preliminary evidence for a practical pathway toward domain-adapted manufacturing MLLMs. The code and datasets are available at https://ai4manufacturing.github.io/forge-web.

cs.CV↗
arXiv2026

Dual-Rerank: Fusing Causality and Utility for Industrial Generative Reranking

Kuaishou serves over 400 million daily active users, processing hundreds of millions of search queries daily against a repository of tens of billions of short videos. As the final decision layer, the reranking stage determines user experience by optimizing whole-page utility. While traditional score-and-sort methods fail to capture combinatorial dependencies, Generative Reranking offers a superior paradigm by directly modeling the permutation probability. However, deploying Generative Reranking in such a high-stakes environment faces a fundamental dual dilemma: 1) the structural trade-off where Autoregressive (AR) models offer superior Sequential modeling but suffer from prohibitive latency, versus Non-Autoregressive (NAR) models that enable efficiency but lack dependency capturing; 2) the optimization gap where Supervised Learning faces challenges in directly optimizing whole-page utility, while Reinforcement Learning (RL) struggles with instability in high-throughput data streams. To resolve this, we propose Dual-Rerank, a unified framework designed for industrial reranking that bridges the structural gap via Sequential Knowledge Distillation and addresses the optimization gap using List-wise Decoupled Reranking Optimization (LDRO) for stable online RL. Extensive A/B testing on production traffic demonstrates that Dual-Rerank achieves State-of-the-Art performance, significantly improving User satisfaction and Watch Time while drastically reducing inference latency compared to AR baselines.

cs.IR↗
arXiv2026

Narrix: Remixing Narrative Strategies from Examples for Story Writing

Experienced storytellers decompose stories into local narrative strategies and how these strategies shape higher-level arcs. This decomposition helps writers recognize patterns in others' work and adapt those patterns to tell new stories. Novices, however, struggle to identify these strategies or to reuse them effectively. We present Narrix, a novel writing tool that helps novice writers recognize narrative strategies in example stories and repurpose these strategies in their own writing. Narrix analyzes strategies in example stories, highlights them with color-coded lexical cues and explanations, and situates them on an interactive story arc for exploration by emotional shifts and turning points. Writers then drag strategies onto multi-dimensional tracks and apply block-scoped edits to revise or continue their drafts through controlled generation steered by specified strategies. Through a within-subjects study (N=12), Narrix showed improved participants' retention, confidence, and creative adaptation of narrative strategies compared to a baseline chat-based writing interface.

cs.HC↗
arXiv2026

Periodic orbits and their gravitational wave radiations in $γ$-metric

The $γ$-metric, also known as Zipoy-Voorhees spacetime, is a static, axially symmetric vacuum solution to Einstein's field equations characterized by two parameters: mass and the deformation parameter $γ$. It reduces to the Schwarzschild metric when $γ= 1$. In this paper, we explore potential signatures of the $γ$-metric on periodic orbits and their gravitational-wave radiation. Periodic orbits are classified by a rotational number specified by three topological numbers $(z, w, v)$, each triple corresponding to characteristic zoom-whirl behavior. We show that deviations from $γ=1$ alter the radii and angular momentum of bound orbits and thereby shift the $(z, w, v)$ taxonomy. We also compute representative gravitational waveforms for certain periodic orbits and demonstrate that $γ\neq 1$ can induce phase shifts and amplitude modulations correlated with changes in the zoom-whirl structure. In particular, larger zoom numbers lead to increasingly complex substructures in the waveforms, and finite deviations from $γ=1$ can significantly modify these features. Our results indicate that precise measurements of waveform morphology from extreme-mass-ratio inspirals may constrain deviations from spherical symmetry encoded in $γ$.

gr-qc↗
arXiv2026

Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing

The rapid advancement of Large Language Models (LLMs) has created new opportunities for Automated Penetration Testing (AutoPT), spawning numerous frameworks aimed at achieving end-to-end autonomous attacks. However, despite the proliferation of related studies, existing research generally lacks systematic architectural analysis and large-scale empirical comparisons under a unified benchmark. Therefore, this paper presents the first Systematization of Knowledge (SoK) focusing on the architectural design and comprehensive empirical evaluation of current LLM-based AutoPT frameworks. At systematization level, we comprehensively review existing framework designs across six dimensions: agent architecture, agent plan, agent memory, agent execution, external knowledge, and benchmarks. At empirical level, we conduct large-scale experiments on 13 representative open-source AutoPT frameworks and 2 baseline frameworks utilizing a unified benchmark. The experiments consumed over 10 billion tokens in total and generated more than 1,500 execution logs, which were manually reviewed and analyzed over four months by a panel of more than 15 researchers with expertise in cybersecurity. By investigating the latest progress in this rapidly developing field, we provide researchers with a structured taxonomy to understand existing LLM-based AutoPT frameworks and a large-scale empirical benchmark, along with promising directions for future research.

cs.CR↗
arXiv2026

Training LLMs for Multi-Step Tool Orchestration with Constrained Data Synthesis and Graduated Rewards

Multi-step tool orchestration remains challenging for LLMs, as state-of-the-art models frequently fail on full sequence execution due to parameter errors. Training for these workflows faces two obstacles: the lack of environments supporting complex real-world API dependencies, and sparse binary rewards that provide no signal for partial correctness. We propose a reinforcement learning framework addressing both challenges. First, we construct a deterministic environment backed by a large-scale cache of real API responses, enabling constrained synthesis of valid multi-step traces with controllable complexity. Second, we introduce a graduated reward that decomposes correctness into atomic validity (call-level correctness at increasing granularity) and orchestration consistency (correct sequencing with dependency respect). On ComplexFuncBench, our approach substantially improves turn accuracy, with ablations confirming both reward components are essential. Cross-benchmark evaluation on BFCL v4 shows that the learned orchestration skills transfer to entirely different API ecosystems (e.g., agentic web search and memory management), yielding consistent gains while maintaining stable single-step performance. Code is available at https://github.com/horizon-rl/ToolOrchestrationReward

cs.LG↗
arXiv2026

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancement across both general and scientific domains. Beyond stronger reasoning and image-text understanding capabilities, its intelligence is augmented with advanced agent capabilities. Simultaneously, its scientific expertise has been vastly expanded to master over 100 specialized tasks across critical science fields, including chemistry, materials, life sciences, and earth sciences. Achieving this massive scale is made possible by the robust infrastructure support of XTuner and LMDeploy, which facilitates highly efficient Reinforcement Learning (RL) training at the 1-trillion parameter level while ensuring strict precision consistency between training and inference. By seamlessly integrating these advancements, Intern-S1-Pro further fortifies the fusion of general and specialized intelligence, working as a Specializable Generalist, demonstrating its position in the top tier of open-source models for general capabilities, while outperforming proprietary models in the depth of specialized scientific tasks.

cs.LG↗
arXiv2026

SmartPoC: Generating Executable and Validated PoCs for Smart Contract Bug Reports

Smart contracts are commonly audited through static analysis to explore vulnerabilities. However, static approaches typically produce heterogeneous findings rather than reproducible, executable proof-of-concept (PoC) test cases, leading to costly and ad hoc manual validation. Large language models (LLMs) offer a promising way to translate audit reports into PoC test cases, but face three major challenges: noisy inputs, lack of execution grounding, and missing runtime oracles. We present SmartPoC, an end-to-end approach for validating reported vulnerabilities in audit reports by generating and executing PoC test cases with automated exploitability verification. SmartPoC first extracts a focused function-level slice from each report to reduce noise, centering on the key functions referenced in a finding and augmenting them with execution-relevant neighbors. To improve executability, we wrap LLM-based PoC synthesis in a generate-repair-execute loop, combining deterministic pre-execution sanitization with feedback-driven post-execution debugging. We further use differential verification as an oracle to confirm the exploitability of generated test cases. On the SmartBugs-Vul and FORGE-Vul benchmarks, SmartPoC achieves confirmation precision of 98.32% and 98.65%, with recall of 84.17% and 85.28%, respectively. On a recent Etherscan verified-source corpus, SmartPoC confirms 64 bugs from 545 audit findings at an average cost of $0.03.

cs.SE↗
arXiv2026

Sketch It Out: Exploring Label-Free Structural Cues for Multimodal Gait Recognition

Gait recognition is a non-intrusive biometric technique for security applications, yet existing studies are dominated by silhouette- and parsing-based representations. Silhouettes are sparse and miss internal structural details, limiting discriminability. Parsing enriches silhouettes with part-level structures, but relies heavily on upstream human parsers (e.g., label granularity and boundary precision), leading to unstable performance across datasets and sometimes even inferior results to silhouettes. We revisit gait representations from a structural perspective and describe a design space defined by edge density and supervision form: silhouettes use sparse boundary edges with weak single-label supervision, while parsing uses denser cues with strong semantic priors. In this space, we identify an underexplored paradigm: dense part-level structure without explicit semantic labels, and introduce SKETCH as a new visual modality for gait recognition. Sketch extracts high-frequency structural cues (e.g., limb articulations and self-occlusion contours) directly from RGB images via edge-based detectors in a label-free manner. We further show that label-guided parsing and label-free sketch are semantically decoupled and structurally complementary. Based on this, we propose SKETCHGAIT, a hierarchically disentangled multi-modal framework with two independent streams for modality-specific learning and a lightweight early-stage fusion branch to capture structural complementarity. Extensive experiments on SUSTech1K and CCPG validate the proposed modality and framework: SketchGait achieves 92.9% Rank-1 on SUSTech1K and 93.1% mean Rank-1 on CCPG.

cs.CV↗
arXiv2026

Accelerating Scientific Discovery with Autonomous Goal-evolving Agents

There has been unprecedented interest in developing agents that expand the boundary of scientific discovery, primarily by optimizing quantitative objective functions specified by scientists. However, for grand challenges in science, these objectives may only be imperfect proxies. We argue that automating objective function design is a central, yet unmet need for scientific discovery agents. In this work, we introduce the Scientific Autonomous Goal-evolving Agent (SAGA) to address this challenge. SAGA employs a bi-level architecture in which an outer loop of LLM agents analyzes optimization outcomes, proposes new objectives, and converts them into computable scoring functions, while an inner loop performs solution optimization under the current objectives. This bi-level design enables systematic exploration of the space of objectives and their trade-offs, rather than treating them as fixed inputs. We demonstrate the framework through a wide range of design applications, including antibiotics, nanobodies, functional DNA sequences, inorganic materials, and chemical processes. Notably, our experimental validation identifies a structurally novel hit with promising potency and safety profiles for E. coli in the antibiotic design task, and three de novo PD-L1 binders in the nanobody design task. These results suggest that automating objective formulation can substantially improve the effectiveness of scientific discovery agents.

cs.AI↗
arXiv2026

Unbiased Multimodal Reranking for Long-Tail Short-Video Search

Kuaishou serving hundreds of millions of searches daily, the quality of short-video search is paramount. However, it suffers from a severe Matthew effect on long-tail queries: sparse user behavior data causes models to amplify low-quality content such as clickbait and shallow content. The recent advancements in Large Language Models (LLMs) offer a new paradigm, as their inherent world knowledge provides a powerful mechanism to assess content quality, agnostic to sparse user interactions. To this end, we propose a LLM-driven multimodal reranking framework, which estimates user experience without real user behavior. The approach involves a two-stage training process: the first stage uses multimodal evidence to construct high-quality annotations for supervised fine-tuning, while the second stage incorporates pairwise preference optimization to help the model learn partial orderings among candidates. At inference time, the resulting experience scores are used to promote high-quality but underexposed videos in reranking, and further guide page-level optimization through reinforcement learning. Experiments show that the proposed method achieves consistent improvements over strong baselines in offline metrics including AUC, NDCG@K, and human preference judgement. An online A/B test covering 15\% of traffic further demonstrates gains in both user experience and consumption metrics, confirming the practical value of the approach in long-tail video search scenarios.

cs.IR↗
arXiv2026

Hölder regularity for the parabolic perturbed fractional 1-Laplace equations

This paper studies the regularity of weak solutions to a class of parabolic perturbed fractional $1$-Laplace equations. Our analysis combines finite difference quotients, energy estimates, and iterative arguments, with a key step being the decomposition of the nonlocal integral into local and nonlocal components to handle their contributions separately. We aim to show the local Hölder continuity of weak solutions within the parabolic domain. More precisely, the solutions are spatially $α$-Hölder continuous with $0<α<\min\left\lbrace1, \frac{s_p p}{p-1} \right\rbrace$ and $γ$-Hölder continuous in time, where the value of $γ$ is determined by the fractional differentiability indexes $s_1$, $s_p$ and the exponent $p$. For both the super-quadratic case ($p\ge 2$) and the sub-quadratic case ($1<p<2$), we establish the Sobolev regularity of solutions, which underpins the derivation of Hölder continuity. All estimates are quantitative and depend only on the structural parameters of the equation. To the best of our knowledge, this is the first attempt to develop a regularity theory for such nonlocal parabolic equations.

math.AP↗
arXiv2026

GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks

This paper introduces GraphOmni, a comprehensive benchmark designed to evaluate the reasoning capabilities of LLMs on graph-theoretic tasks articulated in natural language. GraphOmni encompasses diverse graph types, serialization formats, and prompting schemes, significantly exceeding prior efforts in both scope and depth. Through extensive systematic evaluation, we identify critical interactions among these dimensions, demonstrating their substantial impact on model performance. Our experiments reveal that state-of-the-art models like Claude-3.5 and o4-mini consistently outperform other models, yet even these leading models exhibit substantial room for improvement. Performance variability is evident depending on the specific combinations of factors we considered, underscoring the necessity of comprehensive evaluations across these interconnected dimensions. Additionally, we observe distinct impacts of serialization and prompting strategies between open-source and closed-source models, encouraging the development of tailored approaches. Motivated by the findings, we also propose a reinforcement learning-inspired framework that adaptively selects the optimal factors influencing LLM reasoning capabilities. This flexible and extendable benchmark not only deepens our understanding of LLM performance on structured tasks but also provides a robust foundation for advancing research in LLM-based graph reasoning. The code and datasets are available at https://github.com/GAI-Community/GraphOmni.

cs.LG↗
arXiv2026

FuzzySQL: Uncovering Hidden Vulnerabilities in DBMS Special Features with LLM-Driven Fuzzing

Traditional database fuzzing techniques primarily focus on syntactic correctness and general SQL structures, leaving critical yet obscure DBMS features, such as system-level modes (e.g., GTID), programmatic constructs (e.g., PROCEDURE), advanced process commands (e.g., KILL), largely underexplored. Although rarely triggered by typical inputs, these features can lead to severe crashes or security issues when executed under edge-case conditions. In this paper, we present FuzzySQL, a novel LLM-powered adaptive fuzzing framework designed to uncover subtle vulnerabilities in DBMS special features. FuzzySQL combines grammar-guided SQL generation with logic-shifting progressive mutation, a novel technique that explores alternative control paths by negating conditions and restructuring execution logic, synthesizing structurally and semantically diverse test cases. To further ensure deeper execution coverage of the back end, FuzzySQL employs a hybrid error repair pipeline that unifies rule-based patching with LLM-driven semantic repair, enabling automatic correction of syntactic and context-sensitive failures. We evaluate FuzzySQL across multiple DBMSs, including MySQL, MariaDB, SQLite, PostgreSQL and Clickhouse, uncovering 64 vulnerabilities, 27 of which are tied to under-tested DBMS special features. As of this writing, 60 cases have been confirmed with 9 assigned CVE identifiers, 31 already fixed by vendors, and additional vulnerabilities scheduled to be patched in upcoming releases. Our results highlight the limitations of conventional fuzzers in semantic feature coverage and demonstrate the potential of LLM-based fuzzing to discover deeply hidden bugs in complex database systems.

cs.DB↗
arXiv2026

LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning

We introduce LongCat-Flash-Prover, a flagship 560-billion-parameter open-source Mixture-of- Experts (MoE) model that advances Native Formal Reasoning in Lean4 through agentic tool-integrated reasoning (TIR). We decompose the native formal reasoning task into three independent formal capabilities, i.e., auto-formalization, sketching, and proving. To facilitate these capabilities, we propose a Hybrid-Experts Iteration Framework to expand high-quality task trajectories, including generating a formal statement based on a given informal problem, producing a whole-proof directly from the statement, or a lemma-style sketch. During agentic RL, we present a Hierarchical Importance Sampling Policy Optimization (HisPO) algorithm, which aims to stabilize the MoE model training on such long-horizon tasks. It employs a gradient masking strategy that accounts for the policy staleness and the inherent train-inference engine discrepancies at both sequence and token levels. Additionally, we also incorporate theorem consistency and legality detection mechanisms to eliminate reward hacking issues. Extensive evaluations show that our LongCat-Flash-Prover sets a new state-of-the-art for open-weights models in both auto-formalization and theorem proving. Demonstrating remarkable sample efficiency, it achieves a 97.1% pass rate on MiniF2F-Test using only 72 inference budget per problem. On more challenging benchmarks, it solves 70.8% of ProverBench and 41.5% of PutnamBench with no more than 220 attempts per problem, significantly outperforming existing open-weights baselines.

cs.AI↗