arXiv subjects

Xianfeng Cheng

Publications and source records attributed to Xianfeng Cheng.

4 recordsLinked to original sources

arXiv2026

DexTele: A Dual-Arm Dexterous Teleoperation System Based on Motion Retargeting and Adaptive Force Control

In dual-arm dexterous teleoperation, cross-platform generalization of motion retargeting and interactivity of grasping are crucial. However, the heterogeneity of robotic architectures and the wide variety of grasping objects pose significant challenges to achieving precise motion retargeting and compliant grasping in dual-arm dexterous teleoperation. To address these challenges, a dual-arm dexterous teleoperation system (DexTele) is proposed based on motion retargeting and adaptive force control. First, a vision-based motion retargeting module is designed to generate preliminary robot motions from human images. In this module, a motion-graph encoder and latent optimization are proposed for precise and convenient cross-platform motion retargeting. Second, an adaptive grasping module is designed to achieve compliant grasping. This module combines a vision-language model (VLM) with model predictive control (MPC), allowing the system to predict the required grasping force for a target object and perform gradient-based online optimization. Finally, extensive experiments demonstrate that the DexTele achieves precise motion retargeting and compliant grasping with generalization across multiple robot platforms.

cs.RO↗

arXiv2026

PEB Separation and State Migration: Unmasking the New Frontiers of DeFi AML Evasion

Transfer-based anti-money laundering (AML) systems monitor token flows through transaction-graph abstractions, implicitly assuming that economically meaningful value migration is sufficiently encoded in transfer-layer connectivity. In this paper, we demonstrate that this assumption, the bedrock of current industrial forensics, fundamentally collapses in composable smart-contract ecosystems. We formalize two structural mechanisms that undermine the completeness of transfer-layer attribution. First, we introduce Principal-Execution-Beneficiary (PEB) separation, where intent originators, transaction executors (e.g., MEV searchers), and ultimate beneficiaries are functionally decoupled. Second, we formalize state-mediated value migration, where economic coupling is enforced through invariant-driven contract state transitions (e.g., AMM reserve rebalancing) rather than explicit transfer continuity. Through a real-world case study of role-separated limit order execution and a constructive cross-pool arbitrage model, we prove that these mechanisms render transfer-layer observation neither attribution-complete nor causally closed. We further argue that simply expanding transfer-layer tracing capabilities fails to resolve the underlying attribution ambiguity inherent in structurally decoupled execution. Under modular composition and open participation markets, these mechanisms are structurally generative, implying that heuristic-based flow tracing has reached a formal observational boundary. We advocate for a paradigm shift toward AML based on execution semantics, focusing on the restitution of economic causality from atomic execution logic and state invariants rather than static graph connectivity.

cs.CR↗

arXiv2024

Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey

Visual Question Answering (VQA) is a challenge task that combines natural language processing and computer vision techniques and gradually becomes a benchmark test task in multimodal large language models (MLLMs). The goal of our survey is to provide an overview of the development of VQA and a detailed description of the latest models with high timeliness. This survey gives an up-to-date synthesis of natural language understanding of images and text, as well as the knowledge reasoning module based on image-question information on the core VQA tasks. In addition, we elaborate on recent advances in extracting and fusing modal information with vision-language pretraining models and multimodal large language models in VQA. We also exhaustively review the progress of knowledge reasoning in VQA by detailing the extraction of internal knowledge and the introduction of external knowledge. Finally, we present the datasets of VQA and different evaluation metrics and discuss possible directions for future work.

cs.CL↗

arXiv2021

Flashot: A Snapshot of Flash Loan Attack on DeFi Ecosystem

Flash Loan attack can grab millions of dollars from decentralized vaults in one single transaction, drawing increasing attention from the Decentralized Finance (DeFi) players. It has also demonstrated an exciting opportunity that a huge wealth could be created by composing DeFi's building blocks and exploring the arbitrage change. However, a fundamental framework to study the field of DeFi has not yet reached a consensus and there's a lack of standard tools or languages to help better describe, design and improve the running processes of the infant DeFi systems, which naturally makes it harder to understand the basic principles behind the complexity of Flash Loan attacks. In this paper, we are the first to propose Flashot, a prototype that is able to transparently illustrate the precise asset flows intertwined with smart contracts in a standardized diagram for each Flash Loan event. Some use cases are shown and specifically, based on Flashot, we study a typical Pump and Arbitrage case and present in-depth economic explanations to the attacker's behaviors. Finally, we conclude the development trends of Flash Loan attacks and discuss the great impact on DeFi ecosystem brought by Flash Loan. We envision a brand new quantitative financial industry powered by highly efficient automatic risk and profit detection systems based on the blockchain.

q-fin.CP↗