arXiv subjects

Tianyuan Yu

Publications and source records attributed to Tianyuan Yu.

17 recordsLinked to original sources

arXiv2026

SRAN: Scaling NDN Routing via Map-and-Attach

Network routing scalability becomes difficult when forwarding state scales with an external identifier space rather than network topology. Named Data Networking (NDN) faces this challenge acutely because routing directly on application name prefixes ties forwarding state to an unbounded namespace. This paper presents SRAN, an intra-domain NDN routing architecture that applies the routing-scalability principle underlying Map-and-Encap through Map-and-Attach: application prefixes are mapped to egress routers, and the resulting mapping information is attached to the original Interest. This enables network routing and forwarding to operate on topological identifiers while keeping NDN Interests intact and preserving native NDN communication semantics, including Interest/Data exchange, in-network caching, and data-centric security. SRAN further uses the same prefix-to-egress mapping to realize Bit Index Explicit Replication (BIER) for scalable NDN Interest multicast. SRAN leverages existing NDN mechanisms to securely maintain prefix-to-router mappings among user-facing routers without introducing new protocols. Evaluation on Rocketfuel topologies shows that routers' forwarding state scales with network topology rather than application-prefix count, while prefix updates are disseminated in real time with low communication overhead.

cs.NI↗

arXiv2026

Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent

Online off-policy reinforcement learning (RL) is shaped by two coupled choices: the policy class and the update rule. Gaussian policies are fast and have tractable entropy, but struggle with multimodal action distributions. Generative policies are more expressive, but often require iterative sampling or lack tractable entropy estimates. On the optimisation side, SAC-style soft policy improvement and mirror descent (MD) can be viewed as minimising different KL divergences: the former moves the policy towards a value-induced Boltzmann distribution, while the latter regularises each update against the previous policy. Combining entropy regularisation with an MD constraint is therefore attractive, as it supports exploration while stabilising policy improvement; however, the resulting target can be multimodal and is poorly matched by unimodal Gaussian policies. We propose Stochastic MeanFlow Policies (SMFP), a one-step generative policy class that maps Gaussian noise to actions through a MeanFlow transformation. This stochastic reparameterisation yields a tractable entropy surrogate and allows MeanFlow policies to be trained within off-policy mirror descent under a unified objective for exploratory yet stable improvement. Across seven MuJoCo benchmarks, SMFP improves over Gaussian and generative baselines while retaining single-step inference efficiency.

cs.LG↗

arXiv2026

From Map-and-Encap to BIER: Observations on Network Routing Scalability

The TCP/IP protocol stack uses IP addresses for two distinct roles: identifying hosts and locating their attachment points in the network topology. This dual purpose creates a fundamental tension that has led to routing and forwarding scalability challenges throughout the history of the Internet in unicast packet delivery and, more notably, in multicast delivery. This paper reviews the evolution of routing scalability solutions over the years and makes four observations. First, map-and-encap is a recurring architectural solution shared by all scalable unicast and multicast delivery methods, developed independently across different problem contexts. Second, a new solution tends to succeed when it can bring immediate local gains to early adopters without requiring coordination across administrative domains. Third, network routing and forwarding designs that depend on external factors, such as the number of distinct end sites or even application-specific deliveries, inherently preclude an upper bound on their scalability. Fourth, today's inter-domain routing protocol, BGP, lacks a topological abstraction equivalent to an egress router within a routing domain, thereby inherently preventing a map-and-encap solution for scalability. These observations offer insights into the design of future scalable routing system architectures.

cs.NI↗

arXiv2025

SRM at 30: Lessons from Early Data-Centric Networking and Their Impact on Named Data Networking

A 1995 SIGCOMM paper, "A Reliable Multicast Framework for Light-weight Sessions and Application-Level Framing", commonly known as SRM, explored a fundamentally new approach to reliable multiparty data delivery. Rather than adapting established sender-driven reliable unicast mechanisms to multicast, as most contemporaneous proposals did, SRM introduced a data-centric model in which data receivers recover losses by explicitly requesting missing data. Thirty years later, we revisit the SRM framework, examining the challenges it faced, the lessons learned, and its influence on the later development of Named Data Networking (NDN). Experimentations with SRM revealed a fundamental semantic mismatch between its data-centric framework and IP's address-based delivery; while the application layer named data, the network layer remained 'blind' to those names, resulting in inefficient loss recovery. NDN resolves this architectural friction by aligning network delivery with the data-retrieval model and by securing data directly rather than securing communication channels. This retrospective highlights how early insights from SRM informed key design decisions in NDN and illustrates how NDN's design emerged from the cumulative insights gained over decades of networking research and development.

cs.NI↗

arXiv2025

One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow

We introduce a one-step generative policy for offline reinforcement learning that maps noise directly to actions via a residual reformulation of MeanFlow, making it compatible with Q-learning. While one-step Gaussian policies enable fast inference, they struggle to capture complex, multimodal action distributions. Existing flow-based methods improve expressivity but typically rely on distillation and two-stage training when trained with Q-learning. To overcome these limitations, we propose to reformulate MeanFlow to enable direct noise-to-action generation by integrating the velocity field and noise-to-action transformation into a single policy network-eliminating the need for separate velocity estimation. We explore several reformulation variants and identify an effective residual formulation that supports expressive and stable policy learning. Our method offers three key advantages: 1) efficient one-step noise-to-action generation, 2) expressive modelling of multimodal action distributions, and 3) efficient and stable policy learning via Q-learning in a single-stage training setup. Extensive experiments on 73 tasks across the OGBench and D4RL benchmarks demonstrate that our method achieves strong performance in both offline and offline-to-online reinforcement learning settings. Code is available at https://github.com/HiccupRL/MeanFlowQL.

cs.LG↗

arXiv2025

FoCLIP: A Feature-Space Misalignment Framework for CLIP-Based Image Manipulation and Detection

The well-aligned attribute of CLIP-based models enables its effective application like CLIPscore as a widely adopted image quality assessment metric. However, such a CLIP-based metric is vulnerable for its delicate multimodal alignment. In this work, we propose \textbf{FoCLIP}, a feature-space misalignment framework for fooling CLIP-based image quality metric. Based on the stochastic gradient descent technique, FoCLIP integrates three key components to construct fooling examples: feature alignment as the core module to reduce image-text modality gaps, the score distribution balance module and pixel-guard regularization, which collectively optimize multimodal output equilibrium between CLIPscore performance and image quality. Such a design can be engineered to maximize the CLIPscore predictions across diverse input prompts, despite exhibiting either visual unrecognizability or semantic incongruence with the corresponding adversarial prompts from human perceptual perspectives. Experiments on ten artistic masterpiece prompts and ImageNet subsets demonstrate that optimized images can achieve significant improvement in CLIPscore while preserving high visual fidelity. In addition, we found that grayscale conversion induces significant feature degradation in fooling images, exhibiting noticeable CLIPscore reduction while preserving statistical consistency with original images. Inspired by this phenomenon, we propose a color channel sensitivity-driven tampering detection mechanism that achieves 91% accuracy on standard benchmarks. In conclusion, this work establishes a practical pathway for feature misalignment in CLIP-based multimodal systems and the corresponding defense method.

cs.CV↗

arXiv2025

Revisit the Imbalance Optimization in Multi-task Learning: An Experimental Analysis

Multi-task learning (MTL) aims to build general-purpose vision systems by training a single network to perform multiple tasks jointly. While promising, its potential is often hindered by "unbalanced optimization", where task interference leads to subpar performance compared to single-task models. To facilitate research in MTL, this paper presents a systematic experimental analysis to dissect the factors contributing to this persistent problem. Our investigation confirms that the performance of existing optimization methods varies inconsistently across datasets, and advanced architectures still rely on costly grid-searched loss weights. Furthermore, we show that while powerful Vision Foundation Models (VFMs) provide strong initialization, they do not inherently resolve the optimization imbalance, and merely increasing data quantity offers limited benefits. A crucial finding emerges from our analysis: a strong correlation exists between the optimization imbalance and the norm of task-specific gradients. We demonstrate that this insight is directly applicable, showing that a straightforward strategy of scaling task losses according to their gradient norms can achieve performance comparable to that of an extensive and computationally expensive grid search. Our comprehensive analysis suggests that understanding and controlling gradient dynamics is a more direct path to stable MTL than developing increasingly complex methods.

cs.CV↗

arXiv2025

COLA: Context-aware Language-driven Test-time Adaptation

Test-time adaptation (TTA) has gained increasing popularity due to its efficacy in addressing ``distribution shift'' issue while simultaneously protecting data privacy. However, most prior methods assume that a paired source domain model and target domain sharing the same label space coexist, heavily limiting their applicability. In this paper, we investigate a more general source model capable of adaptation to multiple target domains without needing shared labels. This is achieved by using a pre-trained vision-language model (VLM), \egno, CLIP, that can recognize images through matching with class descriptions. While the zero-shot performance of VLMs is impressive, they struggle to effectively capture the distinctive attributes of a target domain. To that end, we propose a novel method -- Context-aware Language-driven TTA (COLA). The proposed method incorporates a lightweight context-aware module that consists of three key components: a task-aware adapter, a context-aware unit, and a residual connection unit for exploring task-specific knowledge, domain-specific knowledge from the VLM and prior knowledge of the VLM, respectively. It is worth noting that the context-aware module can be seamlessly integrated into a frozen VLM, ensuring both minimal effort and parameter efficiency. Additionally, we introduce a Class-Balanced Pseudo-labeling (CBPL) strategy to mitigate the adverse effects caused by class imbalance. We demonstrate the effectiveness of our method not only in TTA scenarios but also in class generalisation tasks. The source code is available at https://github.com/NUDT-Bai-Group/COLA-TTA.

cs.CV↗

arXiv2025

On the hydrostatic approximation of 3D Oldroyd-B model

In this paper, we study the hydrostatic approximation for the 3D Oldroyd-B model. Firstly, we derive the hydrostatic approximate system for this model and prove the global well-posedness of the limit system with small analytic initial data in horizontal variable. Then we justify the hydrostatic limit strictly from the re-scaled Oldroyd-B model to the hydrostatic Oldroyd-B model and obtain the precise convergence rate.

math.AP↗

arXiv2024

Secure Web Objects: Building Blocks for Metaverse Interoperability and Decentralization

This position paper explores how to support the Web's evolution through an underlying data-centric approach that better matches the data-orientedness of modern and emerging applications. We revisit the original vision of the Web as a hypermedia system that supports document composability and application interoperability via name-based data access. We propose the use of secure web objects (SWO), a data-oriented communication approach that can reduce complexity, centrality, and inefficiency, particularly for collaborative and local-first applications, such as the Metaverse and other collaborative applications. SWO are named, signed, application-defined objects that are secured independently of their containers or communications channels, an approach that leverages the results from over a decade-long data-centric networking research. This approach does not require intermediation by aggregators of identity, storage, and other services that are common today. We present a brief design overview, illustrated through prototypes for two editors of shared hypermedia documents: one for 3D and one for LaTeX. We also discuss our findings and suggest a roadmap for future research.

cs.NI↗

arXiv2024

Exploring the Design of Collaborative Applications via the Lens of NDN Workspace

Metaverse applications desire to communicate with semantically identified objects among a diverse set of cyberspace entities, such as cameras for collecting images from, sensors for sensing environment, and users collaborating with each other, all could be nearby or far away, in a timely and secure way. However, supporting the above function faces networking challenges. Today's metaverse implementations are, by and large, use secure transport connections to communicate with cloud servers instead of letting participating entities communicate directly. In this paper, we use the design and implementation of NDN Workspace, a web-based, multi-user collaborative app to showcase a new way to networking that supports many-to-many secure data exchanges among communicating entities directly. NDN Workspace users establish trust relations among each other, exchange URI-identified objects directly, and can collaborate through intermittent connectivity, all in the absence of cloud servers. Its data-centric design offers an exciting new approach to metaverse app development.

cs.NI↗

arXiv2023

Enhancing NAC-ABE to Support Access Control for mHealth Applications and Beyond

Name-based access control (NAC) over NDN provides fine-grained data confidentiality and access control by encrypting and signing data at the time of data production. NAC utilizes specially crafted naming conventions to define and enforce access control policies. NAC-ABE, an extension to NAC, uses an attribute-based encryption (ABE) scheme to support access control with improved scalability and flexibility. However, existing NAC-ABE libraries are based on ciphertext-policy ABE (CP-ABE), which requires knowledge of the access policy when encrypting data packets. In some applications, including mHealth, the data access policy is unknown at the time of data generation, while data attributes and properties are known. In this paper, we present an extension to the existing NDN-ABE library which can be used by mHealth and other applications to enforce fine-granularity access control in data sharing. We also discuss the challenges we encountered during the application deployment, and remaining open issues together with potential solution directions.

cs.CR↗

arXiv2023

On the Security Bootstrapping in Named Data Networking

By requiring all data packets been cryptographically authenticatable, the Named Data Networking (NDN) architecture design provides a basic building block for secured networking. This basic NDN function requires that all entities in an NDN network go through a security bootstrapping process to obtain the initial security credentials. Recent years have witnessed a number of proposed solutions for NDN security bootstrapping protocols. Built upon the existing results, in this paper we take the next step to develop a systematic model of security bootstrapping: Trust-domain Entity Bootstrapping (TEB). This model is based on the emerging concept of trust domain and describes the steps and their dependencies in the bootstrapping process. We evaluate the expressiveness and sufficiency of this model by using it to describe several current bootstrapping protocols.

cs.CR↗

arXiv2022

Hydra -- A Federated Data Repository over NDN

Today's big data science communities manage their data publication and replication at the application layer. These communities utilize myriad mechanisms to publish, discover, and retrieve datasets - the result is an ecosystem of either centralized, or otherwise a collection of ad-hoc data repositories. Publishing datasets to centralized repositories can be process-intensive, and those repositories do not accept all datasets. The ad-hoc repositories are difficult to find and utilize due to differences in data names, metadata standards, and access methods. To address the problem of scientific data publication and storage, we have designed Hydra, a secure, distributed, and decentralized data repository made of a loose federation of storage servers (nodes) provided by user communities. Hydra runs over Named Data Networking (NDN) and utilizes the State Vector Sync (SVS) protocol that lets individual nodes maintain a "global view" of the system. Hydra provides a scalable and resilient data retrieval service, with data distribution scalability achieved via NDN's built-in data anycast and in-network caching and resiliency against individual server failures through automated failure detection and maintaining a specific degree of replication. Hydra utilizes "Favor", a locally calculated numerical value to decide which nodes will replicate a file. Finally, Hydra utilizes data-centric security for data publication and node authentication. Hydra uses a Network Operation Center (NOC) to bootstrap trust in Hydra nodes and data publishers. The NOC distributes user and node certificates and performs the proof-of-possession challenges. This technical report serves as the reference for Hydra. It outlines the design decisions, the rationale behind them, the functional modules, and the protocol specifications.

cs.NI↗

arXiv2021

Hybrid Graph Neural Networks for Few-Shot Learning

Graph neural networks (GNNs) have been used to tackle the few-shot learning (FSL) problem and shown great potentials under the transductive setting. However under the inductive setting, existing GNN based methods are less competitive. This is because they use an instance GNN as a label propagation/classification module, which is jointly meta-learned with a feature embedding network. This design is problematic because the classifier needs to adapt quickly to new tasks while the embedding does not. To overcome this problem, in this paper we propose a novel hybrid GNN (HGNN) model consisting of two GNNs, an instance GNN and a prototype GNN. Instead of label propagation, they act as feature embedding adaptation modules for quick adaptation of the meta-learned feature embedding to new tasks. Importantly they are designed to deal with a fundamental yet often neglected challenge in FSL, that is, with only a handful of shots per class, any few-shot classifier would be sensitive to badly sampled shots which are either outliers or can cause inter-class distribution overlapping. %Our two GNNs are designed to address these two types of poorly sampled few-shots respectively and their complementarity is exploited in the hybrid GNN model. Extensive experiments show that our HGNN obtains new state-of-the-art on three FSL benchmarks.

cs.CV↗

arXiv2020

Sovereign: User-Controlled Smart Homes

Recent years have witnessed the rapid deployment of smart homes; most of them are controlled by remote servers in the cloud. Such designs raise security and privacy concerns for end users. In this paper, we describe the design of Sovereign, a home IoT system framework that provides end users complete control of their home IoT systems. Sovereign lets home IoT devices and applications communicate via application-named data and secures data directly. This enables direct, secure, one-to-one and one-to-many device-to-device communication over wireless broadcast media. Sovereign utilizes semantic names to construct usable security solutions. We implement Sovereign as a publish-subscribe-based development platform together with a prototype home IoT controller. Our preliminary evaluation shows that Sovereign provides a systematic, easy-to-use solution to user-controlled, self-contained smart homes running on existing IoT hardware without imposing noticeable overhead.

cs.NI↗

arXiv2011

Affine nonmagnetic transformation optics and its application to a practical bending adapter design

One of the bottlenecks that limit the transition of transformation-optics devices from concepts to practical use is the non-unit magnetic permeability generally required from a mathematical transformation. Simple renormalization of permeability, as used in many previous designs and experiments, introduces impedance mismatch and thus degrades the functional photonic performance. Here we propose an area-preserving affine coordinate transformation as a general method to solve this problem. Ideal transformation-optics functions can be preserved while nonmagnetism is achieved. As a specific example, we illustrate how to apply this affine method into the design of a two-dimensional electromagnetic beam bending adapter. Concerns related to fabrication, such as anisotropy degree and bending angles, are fully discussed. Our study is a significant step toward practical use of ideal transformation optics devices that can be implemented directly with existing dielectric materials.

physics.optics↗