arXiv subjects

Zibin Lin

Publications and source records attributed to Zibin Lin.

11 recordsLinked to original sources

arXiv2026

Workflow-Localized Mechanism Learning: Attribution-Guided Repair and Knowledge Reuse for Structured Agent Skills

Agent Skills package reusable procedural knowledge as external artifacts for frozen language-model agents, yet existing optimizers do not jointly resolve where a failure occurs in a workflow, which mechanism caused it, and how relevant knowledge from third-party Skills should be reused locally. We introduce Workflow-Localized Mechanism Learning (WML). Its Node--Mechanism Attribution identifies the failed workflow node, implicated mechanisms, and smallest valid edit target, routing single-mechanism defects to L3 resources and relational defects across mechanisms to L2 composition protocols. A six-module Workflow-Guided Skill Optimization (WGSO) loop then selects provenance- and scope-aware third-party knowledge, applies bounded patches, evaluates candidates, and stores verified outcomes in optimizer-side memory. On SpreadsheetBench, WML reaches 90.33 +/- 1.53 and 74.67 +/- 3.51 Hard Accuracy with DeepSeek and Qwen3.6-Flash, respectively; without additional optimization, the learned Skills transfer to WikiTableQuestions with 84.00 +/- 2.00 and 83.00 +/- 2.00 Denotation Accuracy. On Compiler-Supported50, WML attains both the highest hard-PASS rate and the lowest cost per successful task; compiled execution sharply reduces tokens and calls relative to a direct SkillAgent while retaining most of its successful tasks. Code and artifacts are available at https://github.com/xiaolin9595/workflow-localized-mechanism-learning.

cs.AI↗

arXiv2026

HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better

We present HunyuanOCR-1.5, a lightweight end-to-end OCR-specialized vision-language model. HunyuanOCR unifies document parsing, text spotting, information extraction, text-image translation, and multi-image document understanding within a single end-to-end VLM. Building upon the lightweight architecture of HunyuanOCR-1.0, HunyuanOCR-1.5 does not redesign the backbone, but systematically improves both efficiency and capability. For efficiency, we adapt DFlash to OCR decoding, significantly reducing the latency of long structured outputs such as dense documents, tables, and formulas while preserving output distribution. Powered by DFlash, HunyuanOCR-1.5 achieves a 6.37x Transformer inference speedup and a 2.14x speedup under vLLM, delivering the fastest inference among lightweight OCR VLMs. For capability, we propose Agentic Data Flow, an agent-driven data construction system that transforms model weaknesses into executable data requirements and autonomously performs material search, quality verification, and pipeline development. It substantially improves long-tail capabilities in ancient-script OCR, fine-grained chart and table parsing, multi-image text-centric QA, low-resource multilingual parsing, and document hallucination evaluation. HunyuanOCR-1.5 ranks among the top-tier end-to-end OCR solutions on OmniDocBench v1.6 while achieving new performance milestones across these long-tail tasks. Combined with an upgraded pretraining and post-training recipe, HunyuanOCR-1.5 further extends its capability in high-resolution, long-context, and multi-task scenarios. Experiments demonstrate faster inference, broader OCR capability coverage, and the deployment advantages of a lightweight end-to-end model. We will release the model weights and training code to support future research and real-world OCR applications.

cs.CV↗

arXiv2026

Distributed General-Purpose Agent Networks: Architecture, Key Mechanisms, and Prototypes

Large language models have accelerated the transition from passive conversational assistants to autonomous agents that can understand goals, plan actions, invoke tools, and execute multi-step tasks. Yet the capability of a single agent remains constrained by its local data, tool permissions, runtime environment, and governance boundary. This paper studies distributed general-purpose agent networks: open peer-to-peer networks in which heterogeneous agents deployed on personal devices, edge nodes, or autonomous computing environments can discover one another, establish trust, negotiate cooperation rules, and execute open-ended tasks. We argue that such networks cannot be obtained by simply combining existing peer-to-peer overlays with conventional multi-agent systems. Unlike traditional P2P networks, agent networks must propagate semantic declarations about intentions, capabilities, states, and cooperation constraints. We therefore propose a layered architecture centered on a protocol adaptation layer that connects upper-level task semantics with lower-level network operations. Based on this architecture, the paper identifies three core mechanism problems: semantic announcement propagation for collaborator discovery, verifiable identity and multi-topic reputation for cooperation governance, and semantic-gradient mechanism design for open task execution. For each problem, we present a technical route, including bodyless gossip with sequential logs, BAID-based identity binding with MG-EigenTrust reputation, and a Stackelberg-style mechanism-generation loop driven by semantic attribution feedback. We further report prototype overhead results for BAID-style tiered verification and mechanism-level simulations of MG-EigenTrust under cross-topic disguise-collusion attacks. The resulting framework provides a system-level foundation for open, trustworthy, and scalable agent collaboration.

cs.AI↗

arXiv2026

ZK-AMS: Credibly Anonymous Admission for Web 3.0 Platforms via Recursive Proof Aggregation

Web 3.0 platforms need an onboarding mechanism that can admit real users at scale without forcing them to reveal identity documents or pay one on-chain verification cost per user. Existing approaches typically rely on KYC-style disclosure, per-request on-chain verification, or trusted batching, making onboarding cost and latency difficult to predict under bursty demand. We present \textbf{ZK-AMS}, a credibly anonymous admission infrastructure that maps Personhood Credentials to anonymous on-chain Soul Accounts. Rather than introducing a new primitive, ZK-AMS composes zero-knowledge credential validation, permissionless batch submission, recursive proof aggregation, and anonymous post-admission account provisioning into one end-to-end workflow. Its key design feature is a confidential batching pipeline in which admission instances of a common relation are folded off-chain under multi-key homomorphic encryption, allowing an untrusted batch submitter to coordinate aggregation without direct access to individual user witnesses during batching; the confidentiality scope is characterized explicitly in the security analysis. The resulting batch is settled on-chain with constant verification cost per batch rather than per admitted user. We implement ZK-AMS on an Ethereum testbed and evaluate admission throughput, end-to-end latency, gas consumption, and parameter trade-offs. Results show stable batch-verification gas across evaluated batch sizes, substantially lower amortized on-chain cost than the non-recursive baseline, and practical cost-latency trade-offs for high-concurrency onboarding in Web 3.0 platforms.

cs.NI↗

arXiv2025

Binding Agent ID: Unleashing the Power of AI Agents with accountability and credibility

Autonomous AI agents lack traceable accountability mechanisms, creating a fundamental dilemma where systems must either operate as ``downgraded tools'' or risk real-world abuse. This vulnerability stems from the limitations of traditional key-based authentication, which guarantees neither the operator's physical identity nor the agent's code integrity. To bridge this gap, we propose BAID (Binding Agent ID), a comprehensive identity infrastructure establishing verifiable user-code binding. BAID integrates three orthogonal mechanisms: local binding via biometric authentication, decentralized on-chain identity management, and a novel zkVM-based Code-Level Authentication protocol. By leveraging recursive proofs to treat the program binary as the identity, this protocol provides cryptographic guarantees for operator identity, agent configuration integrity, and complete execution provenance, thereby effectively preventing unauthorized operation and code substitution. We implement and evaluate a complete prototype system, demonstrating the practical feasibility of blockchain-based identity management and zkVM-based authentication protocol.

cs.NI↗

arXiv2025

Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning

In this technical report, we present the Ring-linear model series, specifically including Ring-mini-linear-2.0 and Ring-flash-linear-2.0. Ring-mini-linear-2.0 comprises 16B parameters and 957M activations, while Ring-flash-linear-2.0 contains 104B parameters and 6.1B activations. Both models adopt a hybrid architecture that effectively integrates linear attention and softmax attention, significantly reducing I/O and computational overhead in long-context inference scenarios. Compared to a 32 billion parameter dense model, this series reduces inference cost to 1/10, and compared to the original Ring series, the cost is also reduced by over 50%. Furthermore, through systematic exploration of the ratio between different attention mechanisms in the hybrid architecture, we have identified the currently optimal model structure. Additionally, by leveraging our self-developed high-performance FP8 operator library-linghe, overall training efficiency has been improved by 50%. Benefiting from the high alignment between the training and inference engine operators, the models can undergo long-term, stable, and highly efficient optimization during the reinforcement learning phase, consistently maintaining SOTA performance across multiple challenging complex reasoning benchmarks.

cs.LG↗

arXiv2025

EmbedGrad: Gradient-Based Prompt Optimization in Embedding Space for Large Language Models

Effectively adapting powerful pretrained foundation models to diverse tasks remains a key challenge in AI deployment. Current approaches primarily follow two paradigms:discrete optimization of text prompts through prompt engineering, or continuous adaptation via additional trainable parameters. Both exhibit limitations-discrete methods lack refinement precision while parameter-based techniques increase complexity and reduce interpretability. To address these constraints, we propose EmbedGrad, a novel framework that optimizes text prompt embeddings through gradient-based refinement. Our approach uniquely decouples training from deployment:during optimization,labeled examples guide precise embedding adjustments while preserving semantic meaning; during inference, only optimized embeddings integrate with user queries. This enables fine-grained calibration impossible in text space, such as enhancing the reasoning capability of prompts like please reason step by step. Comprehensive evaluations across mathematical reasoning, sentiment analysis, and causal judgment tasks demonstrate EmbedGrad's effectiveness:optimizing this reasoning prompt for Qwen2.5-Math-1.5B increased accuracy from 14.74\% to 58.96\% on mathematical problems. Consistent improvements were observed across model scales (0.5B-14B) and all tasks, with particularly significant gains for smaller models on complex problems like causal judgment. By bridging prompt engineering and parameter efficiency without architectural changes, our work establishes embedding refinement as a powerful new paradigm for task adaptation.

cs.CL↗

arXiv2025

A Survey of Zero-Knowledge Proof Based Verifiable Machine Learning

Machine learning is increasingly deployed through outsourced and cloud-based pipelines, which improve accessibility but also raise concerns about computational integrity, data privacy, and model confidentiality. Zero-knowledge proofs (ZKPs) provide a compelling foundation for verifiable machine learning because they allow one party to certify that a training, testing, or inference result was produced by the claimed computation without revealing sensitive data or proprietary model parameters. Despite rapid progress in zero-knowledge machine learning (ZKML), the literature remains fragmented across different cryptographic settings, ML tasks, and system objectives. This survey presents a comprehensive review of ZKML research published from June 2017 to August 2025. We first introduce the basic ZKP formulations underlying ZKML and organize existing studies into three core tasks: verifiable training, verifiable testing, and verifiable inference. We then synthesize representative systems, compare their design choices, and analyze the main implementation bottlenecks, including limited circuit expressiveness, high proving cost, and deployment complexity. In addition, we summarize major techniques for improving generality and efficiency, review emerging commercial efforts, and discuss promising future directions. By consolidating the design space of ZKML, this survey aims to provide a structured reference for researchers and practitioners working on trustworthy and privacy-preserving machine learning.

cs.CR↗

arXiv2024

BioZero: Privacy-Preserving and Publicly Verifiable On-Chain Biometric Authentication via Homomorphic Commitments and Zero-Knowledge Proofs

Decentralized identity systems promise user-controlled identifiers and cross-domain verification without a shared identity provider, yet authentication still reduces to possession of keys or credentials once secrets are leaked, reused, or replayed. We present BioZero, a privacy-preserving biometric authentication protocol for decentralized identity that binds an enrolled identity to a biometric witness without revealing biometric templates, while enabling publicly verifiable on-chain decisions. BioZero combines Pedersen commitment-homomorphic computation, consistency spot-checks, and Groth16 zero-knowledge proofs to achieve identity-bound authentication with succinct on-chain verification. We analyze acceptance soundness, freshness, template privacy, and non-malleability under an open decentralized threat model including replay, timing, brute-force, oracle, and forgery attacks. On an Ethereum testbed, BioZero achieves up to 67.8x lower network-adjusted total authentication latency and up to 266.4x faster client-side proving than a zk-SNARK-only baseline. Verification stays in the millisecond range (28.8-41.2 ms vs. 35.4-77.6 ms). With lambda=1 spot-checking, gas grows from 336,778 to 954,066 as N increases from 2 to 128, becomes lower than the baseline from N>=16, and is 2.59x lower at N=128. LFW experiments on 128D and 512D models show accuracy loss below 1% across practical quantization ranges. These results indicate that BioZero is a practical authentication layer for decentralized biometric identity systems.

cs.CR↗

arXiv2024

Personalized Behavior-Aware Transformer for Multi-Behavior Sequential Recommendation

Sequential Recommendation (SR) captures users' dynamic preferences by modeling how users transit among items. However, SR models that utilize only single type of behavior interaction data encounter performance degradation when the sequences are short. To tackle this problem, we focus on Multi-Behavior Sequential Recommendation (MBSR) in this paper, which aims to leverage time-evolving heterogeneous behavioral dependencies for better exploring users' potential intents on the target behavior. Solving MBSR is challenging. On the one hand, users exhibit diverse multi-behavior patterns due to personal characteristics. On the other hand, there exists comprehensive co-influence between behavior correlations and item collaborations, the intensity of which is deeply affected by temporal factors. To tackle these challenges, we propose a Personalized Behavior-Aware Transformer framework (PBAT) for MBSR problem, which models personalized patterns and multifaceted sequential collaborations in a novel way to boost recommendation performance. First, PBAT develops a personalized behavior pattern generator in the representation layer, which extracts dynamic and discriminative behavior patterns for sequential learning. Second, PBAT reforms the self-attention layer with a behavior-aware collaboration extractor, which introduces a fused behavior-aware attention mechanism for incorporating both behavioral and temporal impacts into collaborative transitions. We conduct experiments on three benchmark datasets and the results demonstrate the effectiveness and interpretability of our framework. Our implementation code is released at https://github.com/TiliaceaeSU/PBAT.

cs.IR↗

arXiv2023

Linking Souls to Humans: Blockchain Accounts with Credible Anonymity for Web 3.0 Decentralized Identity

A decentralized identity system that can provide users with self-sovereign digital identities to facilitate complete control over their own data is paramount to Web 3.0. The account system on blockchain is an ideal archetype for realizing Web 3.0 decentralized identity. However, a disadvantage of such completely anonymous identity system is that users can create multiple accounts without authentication to obfuscate their activities on the blockchain. In particular, the current anonymous blockchain account system cannot accurately register the social relationships and interactions between real human users, given the amorphous mappings between users and blockchain identities. This work proposes zkBID, a zero-knowledge blockchain-account-based Web 3.0 decentralized identity scheme, to overcome endemic mistrust in blockchain account systems. zkBID links souls (blockchain accounts) to humans (users' personhood credentials) in a one-to-one manner to truly reflect the social relationships and interactions between humans on the blockchain. zkBID conceals the one-to-one relationships between blockchain accounts and users' personhood credentials for privacy protection using zero-knowledge proofs and linkable ring signatures. Thus, with zkBID, the users' blockchain accounts are credibly anonymous. Importantly, zkBID is fully decentralized: all user-related data are generated by users and verified by smart contracts on the blockchain. We implemented zkBID and built a blockchain test network for evaluation purposes. Our tests demonstrate the effectiveness of zkBID and suggest proper ways to configure zkBID system parameters.

cs.CR↗