arXiv subjects
Publications and source records attributed to Yanze Wang.
We construct a projective klt generalized pair over the complex numbers whose generalized log canonical ring is not finitely generated. The main result of this paper is obtained by generative AI, particularly GPT-5.6-sol-ultra, Fable 5, and the Danus system.
We prove that a general pencil of plane cubics over $\mathbb C$ has exactly $12$ common flex lines. This answers a question of Ciliberto, Miranda, and Ro\'e. The main result of this paper was obtained using generative AI, particularly ChatGPT 5.5 Pro and the Danus system.
Agent skills, SKILL files that package reusable procedural knowledge for an LLM agent, are a popular mechanism for extending agent capabilities. Public repositories now host them in large and growing numbers, yet these artifacts are fragmented, redundant, and uneven in quality, and their value in practice is unclear. A core question remains open, namely how to consolidate this open-source SKILL ecosystem into a single usable corpus, and what bounds its benefit on real-world agent tasks. We present SkillCorpus, a framework that aggregates, curates, matches, and evaluates the open skill ecosystem at scale. It filters ~821,000 crawled skills through a multi-stage pipeline into 96,401 skills organised by a 16-class taxonomy and three quality facets (utility, robustness, safety), and pairs them with a fine-tuned retrieval-and-selection stack that matches task-relevant skills. We evaluate end-to-end across three benchmarks (SkillsBench, GDPVal, QwenClawBench), two harnesses, and two open backbones with a frontier robustness check. Integrating SkillCorpus yields consistent gains across all three benchmarks, largest on SkillsBench (+7.5 pp). An operational analysis traces the gains to a coverage boundary and a harness boundary. SkillCorpus is, to our knowledge, the first end-to-end account of when a curated, retrieval-served community corpus improves real agent tasks, and where it does not. The dataset, models, and code are available at https://github.com/EverMind-AI/SkillCorpus.
We disprove the odd-dimensional extension, conjectured by Moraga and recorded by Koll\'ar and Zhuang, of the rank bound for faithful abelian $p$-group actions on smooth Calabi--Yau varieties. The main result of this paper was obtained by ChatGPT 5.5 pro, and the Danus system based on the Rethlas system.
Large Language Models (LLMs) are increasingly vulnerable to adversarial attacks that can subtly manipulate their outputs. While various defense mechanisms have been proposed, many operate as black boxes, lacking transparency in their decision-making. This paper introduces ExplainableGuard, an interpretable adversarial defense framework leveraging the chain-of-thought (CoT) reasoning capabilities of DeepSeek-Reasoner. Our approach not only detects and neutralizes adversarial perturbations in text but also provides step-by-step explanations for each defense action. We demonstrate how tailored CoT prompts guide the LLM to perform a multi-faceted analysis (character, word, structural, and semantic) and generate a purified output along with a human-readable justification. Preliminary results on the GLUE Benchmark and IMDB Movie Reviews dataset show promising defense efficacy. Additionally, a human evaluation study reveals that ExplainableGuard's explanations outperform ablated variants in clarity, specificity, and actionability, with a 72.5% deployability-trust rating, underscoring its potential for more trustworthy LLM deployments.
By applying the theory of the minimal model program for adjoint foliated structures, we establish the Sarkisov program for algebraically integrable foliations on klt varieties: any two Mori fiber spaces of such structure are connected by a sequence of Sarkisov links. Combining with a result of R. Mascharak, we establish the Sarkisov program for foliations in dimension at most $3$ with mild singularities. Log version and adjoint foliated version of the aformentioned Sarkisov programs are also established.
An increasingly common socio-technical problem is people being taken in by offers that sound ``too good to be true'', where persuasion and trust shape decision-making. This paper investigates how \abr{ai} can help detect these deceptive scenarios. We analyze how humans strategically deceive each other in \textit{Diplomacy}, a board game that requires both natural language communication and strategic reasoning. This requires extracting logical forms of proposed agreements in player communications and computing the relative rewards of the proposal using agents' value functions. Combined with text-based features, this can improve our deception detection. Our method detects human deception with a high precision when compared to a Large Language Model approach that flags many true messages as deceptive. Future human-\abr{ai} interaction tools can build on our methods for deception detection by triggering \textit{friction} to give users a chance of interrogating suspicious proposals.
Simulating transition dynamics between metastable states is a fundamental challenge in dynamical systems and stochastic processes with wide real-world applications in understanding protein folding, chemical reactions and neural activities. However, the computational challenge often lies on sampling exponentially many paths in which only a small fraction ends in the target metastable state due to existence of high energy barriers. To amortize the cost, we propose a data-driven approach to warm-up the simulation by learning nonlinear interpolations from local dynamics. Specifically, we infer a potential energy function from local dynamics data. To find plausible paths between two metastable states, we formulate a generalized flow matching framework that learns a vector field to sample propable paths between the two marginal densities under the learned energy function. Furthermore, we iteratively refine the model by assigning importance weights to the sampled paths and buffering more likely paths for training. We validate the effectiveness of the proposed method to sample probable paths on both synthetic and real-world molecular systems.
We prove that for any two minimal models of an lc algebraically integrable foliated triple on potentially klt varieties, there exist small birational models that are connected by a sequence of flops. In particular, any two minimal models of lc algebraically integrable foliated triples on $\mathbb Q$-factorial klt varieties are connected by a sequence of flops. We also discuss the connection between minimal models for possibly non-algebraically integrable foliations on threefolds, assuming the minimal model program for generalized foliated quadruples.
Developing an efficient method to accelerate the speed of molecular dynamics is a central theme in the field of molecular simulation. One category among the methods are collective-variable-based methods, which rely on predefined collective variables (CVs). The difficulty of selecting a few important CVs hinders the methods to be applied to large systems easily. Here we present a CV-based enhanced sampling method RiD-kit, which could handle a large number of CVs and perform efficient sampling. The method could be applied to various kinds of systems, including biomolecules, chemical reactions and materials. In this protocol, we guide the users through all phases of the RiD-kit workflow, from preparing the input files, setting the simulation parameters and analyzing the results. The RiD-kit workflow provides an efficient and user-friendly command line tool which could submit jobs to various kinds of platforms including the high-performance computers (HPC), cloud server and local machines.
The boardgame Diplomacy is a challenging setting for communicative and cooperative artificial intelligence. The most prominent communicative Diplomacy AI, Cicero, has excellent strategic abilities, exceeding human players. However, the best Diplomacy players master communication, not just tactics, which is why the game has received attention as an AI challenge. This work seeks to understand the degree to which Cicero succeeds at communication. First, we annotate in-game communication with abstract meaning representation to separate in-game tactics from general language. Second, we run two dozen games with humans and Cicero, totaling over 200 human-player hours of competition. While AI can consistently outplay human players, AI-Human communication is still limited because of AI's difficulty with deception and persuasion. This shows that Cicero relies on strategy and has not yet reached the full promise of communicative and cooperative AI.
We investigate multi-agent reinforcement learning for stochastic games with complex tasks, where the reward functions are non-Markovian. We utilize reward machines to incorporate high-level knowledge of complex tasks. We develop an algorithm called Q-learning with reward machines for stochastic games (QRM-SG), to learn the best-response strategy at Nash equilibrium for each agent. In QRM-SG, we define the Q-function at a Nash equilibrium in augmented state space. The augmented state space integrates the state of the stochastic game and the state of reward machines. Each agent learns the Q-functions of all agents in the system. We prove that Q-functions learned in QRM-SG converge to the Q-functions at a Nash equilibrium if the stage game at each time step during learning has a global optimum point or a saddle point, and the agents update Q-functions based on the best-response strategy at this point. We use the Lemke-Howson method to derive the best-response strategy given current Q-functions. The three case studies show that QRM-SG can learn the best-response strategies effectively. QRM-SG learns the best-response strategies after around 7500 episodes in Case Study I, 1000 episodes in Case Study II, and 1500 episodes in Case Study III, while baseline methods such as Nash Q-learning and MADDPG fail to converge to the Nash equilibrium in all three case studies.
Traceability systems are important for solving problems due to the increasing scale of the global supply chain, such as food safety crises and market disorder. Blockchain, as an immutable and decentralized ledger, is able to optimize the traditional traceability system by ensuring the transparency and reliability of the system data. However, the use of blockchain technology may lead to a rapid increase in the complexity of system design and development. It is challenging to address widespread and complicated business, changeable processes, and massive data in practice, which are the main factors restricting the wide application of a blockchain-based traceability system (BTS). Therefore, in this paper, we reviewed relevant studies and proposed a reference architecture for BTSs. The proposed reference architecture can improve the cohesiveness, maintainability, and extensibility of BTSs through domain-driven design (DDD) and microservices. Considering the efficiency reduction caused by massive data and complicated data structure, we further changed the traditional single blockchain framework into multiple sub-chain networks, which could improve development efficiency and system performance. With the guidance of the architecture trade-off analysis method (ATAM), we evaluated our reference architecture and implemented a prototype in the salmon supply chain scenario. The results show that our solution is effective and adaptable to meet the requirements of BTSs.
Accurate forecasting of multivariate time series is an extensively studied subject in finance, transportation, and computer science. Fully mining the correlation and causation between the variables in a multivariate time series exhibits noticeable results in improving the performance of a time series model. Recently, some models have explored the dependencies between variables through end-to-end graph structure learning without the need for predefined graphs. However, current models do not incorporate the trade-off between efficiency and flexibility and lack the guidance of domain knowledge in the design of graph structure learning algorithms. This paper alleviates the above issues by proposing Balanced Graph Structure Learning for Forecasting (BGSLF), a novel deep learning model that joins graph structure learning and forecasting. Technically, BGSLF leverages the spatial information into convolutional operations and extracts temporal dynamics using the diffusion convolutional recurrent network. The proposed framework balance the trade-off between efficiency and flexibility by introducing Multi-Graph Generation Network (MGN) and Graph Selection Module. In addition, a method named Smooth Sparse Unit (SSU) is designed to sparse the learned graph structures, which conforms to the sparse spatial correlations in the real world. Extensive experiments on four real-world datasets demonstrate that our model achieves state-of-the-art performances with minor trainable parameters. Code will be made publicly available.
Enhanced sampling methods such as metadynamics and umbrella sampling have become essential tools for exploring the configuration space of molecules and materials. At the same time, they have long faced a number of issues such as the inefficiency when dealing with a large number of collective variables (CVs) or systems with high free energy barriers. In this work, we show that with \redc{the clustering and adaptive tuning techniques}, the reinforced dynamics (RiD) scheme can be used to efficiently explore the configuration space and free energy landscapes with a large number of CVs or systems with high free energy barriers. We illustrate this by studying various representative and challenging examples. Firstly we demonstrate the efficiency of adaptive RiD compared with other methods, and construct the 9-dimensional free energy landscape of peptoid trimer which has energy barriers of more than 8 kcal/mol. We then study the folding of the protein chignolin using 18 CVs. In this case, both the folding and unfolding rates are observed to be equal to 4.30~$μs^{-1}$. Finally, we propose a protein structure refinement protocol based on RiD. This protocol allows us to efficiently employ more than 100 CVs for exploring the landscape of protein structures and it gives rise to an overall improvement of 14.6 units over the initial Global Distance Test-High Accuracy (GDT-HA) score.