arXiv subjects

Hang Zheng

Publications and source records attributed to Hang Zheng.

At least 19 recordsLinked to original sources

arXiv2026

SoK: Cross-Chain Transaction Identification and Matching

Cross-chain bridges, instant cryptocurrency exchanges, and centralized cross-ledger platforms move assets across an increasingly multi-chain ecosystem. However, these systems have repeatedly become targets of high-value attacks and channels for cross-chain money laundering. Cross-chain transactions are substantially harder to analyze than single-chain transactions: no single ledger records an entire cross-chain transfer, its evidence is scattered across the source chain, the destination chain, and off-chain systems, and the availability and reliability of that evidence vary widely across systems. In this paper, we present a systematization of knowledge (SoK) on cross-chain transaction identification and matching. First, we classify deposit and withdrawal identification methods into four approaches and transaction matching methods into three mechanisms: deterministic identifier matching, field-constraint heuristics, and model-assisted matching. We find that their applicability and reported performance are shaped mainly by the evidence the underlying system exposes, and we further examine how matched pairs support downstream attack detection and fund tracing. Second, we assess the availability of existing datasets and artifacts, finding that fewer than half remain obtainable, and distill three artifact failure modes. Finally, we outline four open challenges toward auditable, reproducible, and actionable cross-chain analysis.

cs.CR↗

arXiv2026

CylindTrack: Depth-Aware Cylindrical Motion Modeling for Panoramic Multi-Object Tracking

Multi-Object Tracking (MOT) is essential for persistent embodied perception in camera-equipped consumer and service robots. Panoramic cameras offer wide surrounding coverage, but equirectangular projection introduces a periodic horizontal domain in which conventional planar motion models and IoU-based association become unreliable near the 0{\deg}/360{\deg} seam. In addition, large-field-of-view scenes exhibit frequent interactions, scale variation, and occlusion, while frame-wise monocular depth estimates may fluctuate over time. To address these challenges, we propose CylindTrack, a depth-aware cylindrical tracking-by-detection framework for panoramic MOT. CylindTrack introduces Depth-Temporal Trajectory Modeling (DTM) to propagate instance depth as a temporally filtered trajectory-level state, providing more stable geometric cues for association. It further incorporates Spherical Spatio-Temporal Consistency Learning (SSTC), which combines a Temporal Mixer with Spherical Geometry-Aware Attention to improve temporal coherence and panoramic geometric alignment of depth-aware representations. Finally, the Topology-Aware Cylindrical Motion Model (TCMM) lifts horizontal motion into a continuous angular state space and performs seam-consistent prediction and association under panoramic periodicity. By jointly modeling depth dynamics and panoramic topology, CylindTrack improves identity preservation and trajectory continuity. Experiments on QuadTrack and JRDB achieve 33.67/31.12 HOTA and 40.45/34.33 IDF1 at 28.56/21.34 FPS, demonstrating the effectiveness and practical online efficiency of CylindTrack as a persistent perception module for panoramic consumer and service robots. The source code will be released at https://github.com/warriordby/CylindTrack.

cs.CV↗

arXiv2026

No Action Without a NOD: A Heterogeneous Multi-Agent Architecture for Reliable Service Agents

Large language model (LLM) agents have increasingly advanced service applications, such as booking flight tickets. However, these service agents suffer from unreliability in long-horizon tasks, as they often produce policy violations, tool hallucinations, and misaligned actions, which greatly impedes their real-world deployment. To address these challenges, we propose NOD (Navigator-Operator-Director), a heterogeneous multi-agent architecture for service agents. Instead of maintaining task state implicitly in dialogue context as in prior work, we externalize a structured Global State to enable explicit task state tracking and consistent decision-making by the Navigator. Besides, we introduce selective external oversight before critical actions, allowing an independent Director agent to verify execution and intervene when necessary. As such, NOD effectively mitigates error propagation and unsafe behavior in long-horizon tasks. Experiments on $\tau^2$-Bench demonstrate that NOD achieves higher task success rates and critical action precision over baselines. More importantly, NOD improves the reliability of service agents by reducing policy violations, tool hallucinations, and user-intent misalignment.

cs.AI↗

arXiv2026

Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agents

The implicit policy of maintaining relatively stable acceptance rates at top AI conferences, despite exponentially growing submissions, introduces a critical structural vulnerability. This position paper characterizes a new systemic threat we term Agentic Denominator Gaming, in which a malicious actor deploys AI agents to generate and submit a large volume of superficially plausible but low-quality papers. Crucially, their objective is not the acceptance of low-quality papers, but rather to inflate the submission denominator and overwhelm reviewing capacity. Under a relatively stable acceptance rate, this dilution can systematically increase the publication probability of a small, targeted set of legitimate papers. We analyze the practical feasibility of this threat and its broader consequences, including intensified reviewer burnout, degraded review quality, and the emergence of industrialized automated agent mills. Finally, we propose and evaluate a range of mitigation strategies, and argue that durable protection will require system-level policy and incentive reforms, rather than relying primarily on technical detection alone.

cs.CL↗

arXiv2026

CapsID: Soft-Routed Variable-Length Semantic IDs for Generative Recommendation

Generative recommendation maps each item to a sequence of Semantic IDs (SIDs) and recasts retrieval as autoregressive token generation. In this paradigm the main bottleneck is the tokenizer rather than the Transformer: residual vector quantization with a hard nearest-neighbor assignment at every layer collapses multi-faceted item semantics at cluster boundaries and propagates early errors to later SID positions. A common workaround is to append a dense vector or attribute prefix to the SID, but this dual-representation design inflates inference cost and gives up the simplicity of a generative interface. We address the bottleneck at the tokenizer itself. CAPSID replaces hard residual quantization with capsule routing: at each layer an item probabilistically routes to several semantic capsules, the residual is updated by the routed reconstruction rather than by a single winning code, and the SID terminates once the active capsule's confidence is high enough. On top of CAPSID, SEMANTICBPE composes adjacent SID tokens into reusable subwords by combining their co-occurrence with their embedding compatibility. On Amazon Beauty, Sports, Toys, and a 35M-item proprietary industrial catalog, CAPSID+SEMANTICBPE improves Recall at 10 by 9.6% on average over ReSID, the strongest single-representation baseline, and matches or exceeds a COBRA-style sparse-dense system on every public benchmark while running at 51% of its inference latency. Ablations show that soft routing, iterative agreement, and confidence-driven length each contribute independently, and the gains are largest on tail items where boundary semantics dominate.

cs.IR↗

arXiv2025

Bohrium + SciMaster: Building the Infrastructure and Ecosystem for Agentic Science at Scale

AI agents are emerging as a practical way to run multi-step scientific workflows that interleave reasoning with tool use and verification, pointing to a shift from isolated AI-assisted steps toward \emph{agentic science at scale}. This shift is increasingly feasible, as scientific tools and models can be invoked through stable interfaces and verified with recorded execution traces, and increasingly necessary, as AI accelerates scientific output and stresses the peer-review and publication pipeline, raising the bar for traceability and credible evaluation. However, scaling agentic science remains difficult: workflows are hard to observe and reproduce; many tools and laboratory systems are not agent-ready; execution is hard to trace and govern; and prototype AI Scientist systems are often bespoke, limiting reuse and systematic improvement from real workflow signals. We argue that scaling agentic science requires an infrastructure-and-ecosystem approach, instantiated in Bohrium+SciMaster. Bohrium acts as a managed, traceable hub for AI4S assets -- akin to a HuggingFace of AI for Science -- that turns diverse scientific data, software, compute, and laboratory systems into agent-ready capabilities. SciMaster orchestrates these capabilities into long-horizon scientific workflows, on which scientific agents can be composed and executed. Between infrastructure and orchestration, a \emph{scientific intelligence substrate} organizes reusable models, knowledge, and components into executable building blocks for workflow reasoning and action, enabling composition, auditability, and improvement through use. We demonstrate this stack with eleven representative master agents in real workflows, achieving orders-of-magnitude reductions in end-to-end scientific cycle time and generating execution-grounded signals from real workloads at multi-million scale.

cs.AI↗

arXiv2025

DiSRouter: Distributed Self-Routing for LLM Selections

The proliferation of Large Language Models (LLMs) has created a diverse ecosystem of models with highly varying performance and costs, necessitating effective query routing to balance performance and expense. Current routing systems often rely on a centralized external router trained on a fixed set of LLMs, making them inflexible and prone to poor performance since the small router can not fully understand the knowledge boundaries of different LLMs. We introduce DiSRouter (Distributed Self-Router), a novel paradigm that shifts from centralized control to distributed routing. In DiSRouter, a query traverses a network of LLM agents, each independently deciding whether to answer or route to other agents based on its own self-awareness, its ability to judge its competence. This distributed design offers superior flexibility, scalability, and generalizability. To enable this, we propose a two-stage Self-Awareness Training pipeline that enhances each LLM's self-awareness. Extensive experiments demonstrate that DiSRouter significantly outperforms existing routing methods in utility across various scenarios, effectively distinguishes between easy and hard queries, and shows strong generalization to out-of-domain tasks. Our work validates that leveraging an LLM's intrinsic self-awareness is more effective than external assessment, paving the way for more modular and efficient multi-agent systems.

cs.CL↗

arXiv2025

Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling

Large language models (LLMs) are prone to hallucination stemming from misaligned self-awareness, particularly when processing queries exceeding their knowledge boundaries. While existing mitigation strategies employ uncertainty estimation or query rejection mechanisms, they suffer from computational efficiency and sacrificed helpfulness. To address these issues, we propose the Explicit Knowledge Boundary Modeling (EKBM) framework, integrating fast and slow reasoning systems to harmonize reliability and usability. The framework first employs a fast-thinking model to generate confidence-labeled responses, enabling immediate utilization of high-confidence outputs, whereas uncertain predictions trigger a slow refinement model for accuracy improvement. To align model behavior with our proposed object, we propose a hybrid training pipeline, enhancing self-awareness without degrading task performance. Evaluations on dialogue state tracking tasks demonstrate that EKBM achieves superior model reliability over uncertainty-based baselines. Further analysis reveals that refinement substantially boosts accuracy while maintaining low computational overhead. The framework establishes a scalable paradigm for deploying reliable LLMs in error-sensitive applications, effectively balancing accuracy and practical utility.

cs.CL↗

arXiv2025

AirQA: A Comprehensive QA Dataset for AI Research with Instance-Level Evaluation

The growing volume of academic papers has made it increasingly difficult for researchers to efficiently extract key information. While large language models (LLMs) based agents are capable of automating question answering (QA) workflows for scientific papers, there still lacks a comprehensive and realistic benchmark to evaluate their capabilities. Moreover, training an interactive agent for this specific task is hindered by the shortage of high-quality interaction trajectories. In this work, we propose AirQA, a human-annotated comprehensive paper QA dataset in the field of artificial intelligence (AI), with 13,956 papers and 1,246 questions, that encompasses multi-task, multi-modal and instance-level evaluation. Furthermore, we propose ExTrActor, an automated framework for instruction data synthesis. With three LLM-based agents, ExTrActor can perform example generation and trajectory collection without human intervention. Evaluations of multiple open-source and proprietary models show that most models underperform on AirQA, demonstrating the quality of our dataset. Extensive experiments confirm that ExTrActor consistently improves the multi-turn tool-use capability of small models, enabling them to achieve performance comparable to larger ones.

cs.CL↗

arXiv2025

Performance Review on LLM for solving leetcode problems

This paper presents a comprehensive performance evaluation of Large Language Models (LLMs) in solving programming challenges from Leetcode, a widely used platform for algorithm practice and technical interviews. We began by crawling the Leetcode website to collect a diverse set of problems encompassing various difficulty levels and topics. Using this dataset, we generated solutions with multiple LLMs, including GPT-4 and GPT-3.5-turbo (ChatGPT-turbo). The generated solutions were systematically evaluated for correctness and efficiency. We employed the pass@k metric to assess the success rates within a given number of attempts and analyzed the runtime performance of the solutions. Our results highlight the strengths and limitations of current LLMs [10] in code generation and problem-solving tasks, providing insights into their potential applications and areas for improvement in automated programming assistance.

cs.SE↗

arXiv2025

A Challenge of Developing a Classifier for Multi-Band Classification of Variable Stars

Variable stars play a very important role in our understanding of the Milky Way and the universe. In recent years, many survey projects have generated a large amount of photometric data, necessitating classifiers that can quickly identify various types of variable stars. However, obtaining these classifiers often requires substantial manpower and computational resources. To conserve these resources, it would be best to have a classifier that can be used across surveys. We explore the possibility that a classifier created in one optical band can also work in other bands, likely from different survey facilities. We construct a random forest classifier based on photometric data in ASAS-SN V-band and OGLE I-band, and apply the classifier on ASAS-SN V-band and ZTF r-band light curves of variable star samples. We explore the classification differences of using the magnitude light-curves or the normalized flux light-curves, the periods derived from single band light-curves or the periods derived from the multi-band combined light-curves, and with or without color-related features. We find it feasible to develop a classifier capable of working in both V and r bands for certain types of variable stars, such as RRAB variables. For other types of variable stars, like Cepheids, the classifier is unable to make accurate identifications.

astro-ph.IM↗

arXiv2024

The Economic Analysis of the Common Pool Method through the HARA Utility Functions

Water market is a contemporary marketplace for water trading and is deemed to one of the most efficient instruments to improve the social welfare. In modern water markets, the two widely used trading systems are an improved pair-wise trading, and a 'smart market' or common pool method. In comparison with the economic model, this paper constructs a conceptual mathematic model through the HARA utility functions. Mirroring the concepts such as Nash Equilibrium, Pareto optimal and stable matching in economy, three significant propositions are acquired which illustrate the advantages of the common pool method compared with the improved pair-wise trading.

econ.GN↗

arXiv2024

Uni-Mol2: Exploring Molecular Pretraining Model at Scale

In recent years, pretraining models have made significant advancements in the fields of natural language processing (NLP), computer vision (CV), and life sciences. The significant advancements in NLP and CV are predominantly driven by the expansion of model parameters and data size, a phenomenon now recognized as the scaling laws. However, research exploring scaling law in molecular pretraining models remains unexplored. In this work, we present Uni-Mol2 , an innovative molecular pretraining model that leverages a two-track transformer to effectively integrate features at the atomic level, graph level, and geometry structure level. Along with this, we systematically investigate the scaling law within molecular pretraining models, characterizing the power-law correlations between validation loss and model size, dataset size, and computational resources. Consequently, we successfully scale Uni-Mol2 to 1.1 billion parameters through pretraining on 800 million conformations, making it the largest molecular pretraining model to date. Extensive experiments show consistent improvement in the downstream tasks as the model size grows. The Uni-Mol2 with 1.1B parameters also outperforms existing methods, achieving an average 27% improvement on the QM9 and 14% on COMPAS-1D dataset.

cs.LG↗

arXiv2024

Efficient and Precise Force Field Optimization for Biomolecules Using DPA-2

Molecular simulations are essential tools in computational chemistry, enabling the prediction and understanding of molecular interactions and thermodynamic properties of biomolecules. However, traditional force fields face significant challenges in accurately representing novel molecules and complex chemical environments due to the labor-intensive process of manually setting optimization parameters and the high computational cost of quantum mechanical calculations. To overcome these difficulties, we fine-tuned a high-accuracy DPA-2 pre-trained model and applied it to optimize force field parameters on-the-fly, significantly reducing computational costs. Our method combines this fine-tuned DPA-2 model with a node-embedding-based similarity metric, allowing seamless augmentation to new chemical species without manual intervention. We applied this process to the TYK2 inhibitor and PTP1B systems and demonstrated its effectiveness through the improvement of free energy perturbation calculation results. This advancement contributes valuable insights and tools for the computational chemistry community.

physics.chem-ph↗

arXiv2024

Uni-Mol Docking V2: Towards Realistic and Accurate Binding Pose Prediction

In recent years, machine learning (ML) methods have emerged as promising alternatives for molecular docking, offering the potential for high accuracy without incurring prohibitive computational costs. However, recent studies have indicated that these ML models may overfit to quantitative metrics while neglecting the physical constraints inherent in the problem. In this work, we present Uni-Mol Docking V2, which demonstrates a remarkable improvement in performance, accurately predicting the binding poses of 77+% of ligands in the PoseBusters benchmark with an RMSD value of less than 2.0 Å, and 75+% passing all quality checks. This represents a significant increase from the 62% achieved by the previous Uni-Mol Docking model. Notably, our Uni-Mol Docking approach generates chemically accurate predictions, circumventing issues such as chirality inversions and steric clashes that have plagued previous ML models. Furthermore, we observe enhanced performance in terms of high-quality predictions (RMSD values of less than 1.0 Å and 1.5 Å) and physical soundness when Uni-Mol Docking is combined with more physics-based methods like Uni-Dock. Our results represent a significant advancement in the application of artificial intelligence for scientific research, adopting a holistic approach to ligand docking that is well-suited for industrial applications in virtual screening and drug design. The code, data and service for Uni-Mol Docking are publicly available for use and further development in https://github.com/dptech-corp/Uni-Mol.

q-bio.BM↗

arXiv2024

Solitary wave solutions of the delayed KP-BBM equation

In this paper, we consider a kind of shallow water wave model called the Kadomtsev-Petviashvili-Benjamin-Bona-Mahony (KP-BBM) equation. We firstly consider the unperturbed KP-BBM equation. Then by using the geometric singular perturbation (GSP) theory, especially the invariant manifold theory, method of dynamical system and Melnikov function, the existence of solitary wave solutions of perturbed KP-BBM equation is proved. In other words, we dissuss the equation under different nonlinear terms. Finally, we validate our results with numerical simulations.

math.AP↗

arXiv2024

Dflow, a Python framework for constructing cloud-native AI-for-Science workflows

In the AI-for-science era, scientific computing scenarios such as concurrent learning and high-throughput computing demand a new generation of infrastructure that supports scalable computing resources and automated workflow management on both cloud and high-performance supercomputers. Here we introduce Dflow, an open-source Python toolkit designed for scientists to construct workflows with simple programming interfaces. It enables complex process control and task scheduling across a distributed, heterogeneous infrastructure, leveraging containers and Kubernetes for flexibility. Dflow is highly observable and can scale to thousands of concurrent nodes per workflow, enhancing the efficiency of complex scientific computing tasks. The basic unit in Dflow, known as an Operation (OP), is reusable and independent of the underlying infrastructure or context. Dozens of workflow projects have been developed based on Dflow, spanning a wide range of projects. We anticipate that the reusability of Dflow and its components will encourage more scientists to publish their workflows and OP components. These components, in turn, can be adapted and reused in various contexts, fostering greater collaboration and innovation in the scientific community.

cs.DC↗

arXiv2024

Physical Parameters of 11,100 Short-Period ASAS-SN Eclipsing Contact Binaries

Starting from more than 11,200 short-period (less than 0.5 days) EW-type eclipsing binary candidates with the All-Sky Automated Survey for Supernovae (ASAS-SN) V-band light curves, we use MCMC and neural networks (NNs) to obtain the mass ratio ($q$), orbital inclination ($incl$), fill-out factor ($f$) and temperature ratio ($T_s/T_p$). After cross-matching with the Gaia DR3 database, the final sample contains parameters of 2,399 A-type and 8,712 W-type contact binaries (CBs). We present the distributions of parameters of these 11,111 short-period CBs. The mass ratio ($q$) and fill-out factor ($f$) are found to obey log-normal distributions, and the remaining parameters obey normal distributions. There is a significant period-temperature correlation of these CBs. Additionally, the temperature ratio (${T_s}$/${T_p}$) tends to increase as the orbital period decreases for W-type CBs. There is no significant correlation between them for A-type CBs. The mass ratio and fill-out factor ($q-f$) diagram suggest there is no significant correlation between these two parameters. A clear correlation exists between the mass ratio and radius ratio. The radius ratio increases with the mass ratio. Moreover, the deep fill-out CBs tend to fall on the upper boundary of the $q$$-$${R_s}$/${R_p}$ distribution, while the shallow fill-out CBs fall on the lower boundary.

astro-ph.SR↗