arXiv subjects

Tao Zhang

Publications and source records attributed to Tao Zhang.

At least 307 records · Page 17Linked to original sources

arXiv2025

Baichuan-Omni-1.5 Technical Report

We introduce Baichuan-Omni-1.5, an omni-modal model that not only has omni-modal understanding capabilities but also provides end-to-end audio generation capabilities. To achieve fluent and high-quality interaction across modalities without compromising the capabilities of any modality, we prioritized optimizing three key aspects. First, we establish a comprehensive data cleaning and synthesis pipeline for multimodal data, obtaining about 500B high-quality data (text, audio, and vision). Second, an audio-tokenizer (Baichuan-Audio-Tokenizer) has been designed to capture both semantic and acoustic information from audio, enabling seamless integration and enhanced compatibility with MLLM. Lastly, we designed a multi-stage training strategy that progressively integrates multimodal alignment and multitask fine-tuning, ensuring effective synergy across all modalities. Baichuan-Omni-1.5 leads contemporary models (including GPT4o-mini and MiniCPM-o 2.6) in terms of comprehensive omni-modal capabilities. Notably, it achieves results comparable to leading models such as Qwen2-VL-72B across various multimodal medical benchmarks.

cs.CL↗

arXiv2025

Ocean-OCR: Towards General OCR Application via a Vision-Language Model

Multimodal large language models (MLLMs) have shown impressive capabilities across various domains, excelling in processing and understanding information from multiple modalities. Despite the rapid progress made previously, insufficient OCR ability hinders MLLMs from excelling in text-related tasks. In this paper, we present \textbf{Ocean-OCR}, a 3B MLLM with state-of-the-art performance on various OCR scenarios and comparable understanding ability on general tasks. We employ Native Resolution ViT to enable variable resolution input and utilize a substantial collection of high-quality OCR datasets to enhance the model performance. We demonstrate the superiority of Ocean-OCR through comprehensive experiments on open-source OCR benchmarks and across various OCR scenarios. These scenarios encompass document understanding, scene text recognition, and handwritten recognition, highlighting the robust OCR capabilities of Ocean-OCR. Note that Ocean-OCR is the first MLLM to outperform professional OCR models such as TextIn and PaddleOCR.

cs.CV↗

arXiv2025

Efficient and Trustworthy Block Propagation for Blockchain-enabled Mobile Embodied AI Networks: A Graph Resfusion Approach

By synergistically integrating mobile networks and embodied artificial intelligence (AI), Mobile Embodied AI Networks (MEANETs) represent an advanced paradigm that facilitates autonomous, context-aware, and interactive behaviors within dynamic environments. Nevertheless, the rapid development of MEANETs is accompanied by challenges in trustworthiness and operational efficiency. Fortunately, blockchain technology, with its decentralized and immutable characteristics, offers promising solutions for MEANETs. However, existing block propagation mechanisms suffer from challenges such as low propagation efficiency and weak security for block propagation, which results in delayed transmission of vehicular messages or vulnerability to malicious tampering, potentially causing severe traffic accidents in blockchain-enabled MEANETs. Moreover, current block propagation strategies cannot effectively adapt to real-time changes of dynamic topology in MEANETs. Therefore, in this paper, we propose a graph Resfusion model-based trustworthy block propagation optimization framework for consortium blockchain-enabled MEANETs. Specifically, we propose an innovative trust calculation mechanism based on the trust cloud model, which comprehensively accounts for randomness and fuzziness in the miner trust evaluation. Furthermore, by leveraging the strengths of graph neural networks and diffusion models, we develop a graph Resfusion model to effectively and adaptively generate the optimal block propagation trajectory. Simulation results demonstrate that the proposed model outperforms other routing mechanisms in terms of block propagation efficiency and trustworthiness. Additionally, the results highlight its strong adaptability to dynamic environments, making it particularly suitable for rapidly changing MEANETs.

cs.AI↗

arXiv2025

Generative AI-driven Cross-layer Covert Communication: Fundamentals, Framework and Case Study

Ensuring end-to-end cross-layer communication security in military networks by selecting covert schemes between nodes is a key solution for military communication security. With the development of communication technology, covert communication has expanded from the physical layer to the network and application layers, utilizing methods such as artificial noise, private networks, and semantic coding to transmit secret messages. However, as adversaries continuously eavesdrop on specific communication channels, the accumulation of sufficient data may reveal underlying patterns that influence concealment, and establishing a cross-layer covert communication mechanism emerges as an effective strategy to mitigate these regulatory challenges. In this article, we first survey the communication security solution based on covert communication, specifically targeting three typical scenarios: device-to-device, private network communication, and public network communication, and analyze their application scopes. Furthermore, we propose an end-to-end cross-layer covert communication scheme driven by Generative Artificial Intelligence (GenAI), highlighting challenges and their solutions. Additionally, a case study is conducted using diffusion reinforcement learning to sovle cloud edge internet of things cross-layer secure communication.

cs.CR↗

arXiv2025

Achieving Network Resilience through Graph Neural Network-enabled Deep Reinforcement Learning

Deep reinforcement learning (DRL) has been widely used in many important tasks of communication networks. In order to improve the perception ability of DRL on the network, some studies have combined graph neural networks (GNNs) with DRL, which use the GNNs to extract unstructured features of the network. However, as networks continue to evolve and become increasingly complex, existing GNN-DRL methods still face challenges in terms of scalability and robustness. Moreover, these methods are inadequate for addressing network security issues. From the perspective of security and robustness, this paper explores the solution of combining GNNs with DRL to build a resilient network. This article starts with a brief tutorial of GNNs and DRL, and introduces their existing applications in networks. Furthermore, we introduce the network security methods that can be strengthened by GNN-DRL approaches. Then, we designed a framework based on GNN-DRL to defend against attacks and enhance network resilience. Additionally, we conduct a case study using an encrypted traffic dataset collected from real IoT environments, and the results demonstrated the effectiveness and superiority of our framework. Finally, we highlight key open challenges and opportunities for enhancing network resilience with GNN-DRL.

cs.CR↗

arXiv2025

Zeroth-Order Actor-Critic: An Evolutionary Framework for Sequential Decision Problems

Evolutionary algorithms (EAs) have shown promise in solving sequential decision problems (SDPs) by simplifying them to static optimization problems and searching for the optimal policy parameters in a zeroth-order way. While these methods are highly versatile, they often suffer from high sample complexity due to their ignorance of the underlying temporal structures. In contrast, reinforcement learning (RL) methods typically formulate SDPs as Markov Decision Process (MDP). Although more sample efficient than EAs, RL methods are restricted to differentiable policies and prone to getting stuck in local optima. To address these issues, we propose a novel evolutionary framework Zeroth-Order Actor-Critic (ZOAC). We propose to use step-wise exploration in parameter space and theoretically derive the zeroth-order policy gradient. We further utilize the actor-critic architecture to effectively leverage the Markov property of SDPs and reduce the variance of gradient estimators. In each iteration, ZOAC employs samplers to collect trajectories with parameter space exploration, and alternates between first-order policy evaluation (PEV) and zeroth-order policy improvement (PIM). To evaluate the effectiveness of ZOAC, we apply it to a challenging multi-lane driving task, optimizing the parameters in a rule-based, non-differentiable driving policy that consists of three sub-modules: behavior selection, path planning, and trajectory tracking. We also compare it with gradient-based RL methods on three Gymnasium tasks, optimizing neural network policies with thousands of parameters. Experimental results demonstrate the strong capability of ZOAC in solving SDPs. ZOAC significantly outperforms EAs that treat the problem as static optimization and matches the performance of gradient-based RL methods even without first-order information, in terms of total average return across all tasks.

cs.LG↗

arXiv2024

Defending Against Network Attacks for Secure AI Agent Migration in Vehicular Metaverses

Vehicular metaverses, blending traditional vehicular networks with metaverse technology, are expected to revolutionize fields such as autonomous driving. As virtual intelligent assistants in vehicular metaverses, Artificial Intelligence (AI) agents powered by large language models can create immersive 3D virtual spaces for passengers to enjoy on-broad vehicular applications and services. To provide users with seamless and engaging virtual interactions, resource-limited vehicles offload AI agents to RoadSide Units (RSUs) with adequate communication and computational capabilities. Due to the mobility of vehicles and the limited coverage of RSUs, AI agents need to migrate from one RSU to another RSU. However, potential network attacks pose significant challenges to ensuring reliable and efficient AI agent migration. In this paper, we first explore specific network attacks including traffic-based attacks (i.e., DDoS attacks) and infrastructure-based attacks (i.e., malicious RSU attacks). Then, we model the AI agent migration process as a Partially Observable Markov Decision Process (POMDP) and apply multi-agent proximal policy optimization algorithms to mitigate DDoS attacks. In addition, we propose a trust assessment mechanism to counter malicious RSU attacks. Numerical results validate that the proposed solutions effectively defend against these network attacks and reduce the total latency of AI agent migration by approximately 43.3%.

cs.NI↗

arXiv2024

Baichuan-Omni Technical Report

The salient multimodal capabilities and interactive experience of GPT-4o highlight its critical role in practical applications, yet it lacks a high-performing open-source counterpart. In this paper, we introduce Baichuan-omni, the first open-source 7B Multimodal Large Language Model (MLLM) adept at concurrently processing and analyzing modalities of image, video, audio, and text, while delivering an advanced multimodal interactive experience and strong performance. We propose an effective multimodal training schema starting with 7B model and proceeding through two stages of multimodal alignment and multitask fine-tuning across audio, image, video, and text modal. This approach equips the language model with the ability to handle visual and audio data effectively. Demonstrating strong performance across various omni-modal and multimodal benchmarks, we aim for this contribution to serve as a competitive baseline for the open-source community in advancing multimodal understanding and real-time interaction.

cs.AI↗

arXiv2024

Deep Smart Contract Intent Detection

In recent years, research in software security has concentrated on identifying vulnerabilities in smart contracts to prevent significant losses of crypto assets on blockchains. Despite early successes in this area, detecting developers' intents in smart contracts has become a more pressing issue, as malicious intents have caused substantial financial losses. Unfortunately, existing research lacks effective methods for detecting development intents in smart contracts. To address this gap, we propose \textsc{SmartIntentNN} (Smart Contract Intent Neural Network), a deep learning model designed to automatically detect development intents in smart contracts. \textsc{SmartIntentNN} leverages a pre-trained sentence encoder to generate contextual representations of smart contracts, employs a K-means clustering model to identify and highlight prominent intent features, and utilizes a bidirectional LSTM-based deep neural network for multi-label classification. We trained and evaluated \textsc{SmartIntentNN} on a dataset containing over 40,000 real-world smart contracts, employing self-comparison baselines in our experimental setup. The results show that \textsc{SmartIntentNN} achieves an F1-score of 0.8633 in identifying intents across 10 distinct categories, outperforming all baselines and addressing the gap in smart contract detection by incorporating intent analysis.

cs.SE↗

arXiv2024

Baichuan Alignment Technical Report

We introduce Baichuan Alignment, a detailed analysis of the alignment techniques employed in the Baichuan series of models. This represents the industry's first comprehensive account of alignment methodologies, offering valuable insights for advancing AI research. We investigate the critical components that enhance model performance during the alignment process, including optimization methods, data strategies, capability enhancements, and evaluation processes. The process spans three key stages: Prompt Augmentation System(PAS), Supervised Fine-Tuning(SFT), and Preference Alignment. The problems encountered, the solutions applied, and the improvements made are thoroughly recorded. Through comparisons across well-established benchmarks, we highlight the technological advancements enabled by Baichuan Alignment. Baichuan-Instruct is an internal model, while Qwen2-Nova-72B and Llama3-PBM-Nova-70B are instruct versions of the Qwen2-72B and Llama-3-70B base models, optimized through Baichuan Alignment. Baichuan-Instruct demonstrates significant improvements in core capabilities, with user experience gains ranging from 17% to 28%, and performs exceptionally well on specialized benchmarks. In open-source benchmark evaluations, both Qwen2-Nova-72B and Llama3-PBM-Nova-70B consistently outperform their respective official instruct versions across nearly all datasets. This report aims to clarify the key technologies behind the alignment process, fostering a deeper understanding within the community. Llama3-PBM-Nova-70B model is available at https://huggingface.co/PKU-Baichuan-MLSystemLab/Llama3-PBM-Nova-70B.

cs.LG↗

arXiv2024

Searching for Neutrinoless Double-Beta Decay of $^{136}$Xe with PandaX-4T

We report the search for neutrinoless double-beta decay of $^{136}$Xe from the PandaX-4T experiment with a 3.7-tonne natural xenon target. The data reconstruction and the background modeling are optimized in the MeV energy region. A blind analysis is performed with data from the commissioning run and the first science run. No significant excess of signal over the background is observed. A lower limit on the half-life of $^{136}$Xe neutrinoless double-beta decay is established to be $2.1 \times 10^{24}$~yr at the 90\% confidence level, with a $^{136}$Xe exposure of 44.6~kg$\cdot$year. Our result represents the most stringent constraint from a natural xenon detector to date.

nucl-ex↗

arXiv2024

Customized calibration sources in the JUNO experiment

We customized a laser calibration system and four radioactive $γ$-ray calibration sources for the Jiangmen Underground Neutrino Observatory (JUNO), a 20-kton liquid scintillator-based neutrino detector. The laser source system was updated to realize the isotropic light emission timing within $\pm0.25$~nsec level and to allow the tuning of the laser intensity covering more than four orders of magnitude. In addition, methods to prepare four different radioactive sources ($^{18}{\rm F}$, $^{40}{\rm K}$, $^{226}{\rm Ra}$, and $^{241}{\rm Am}$), covering energies from O(10)~keV to O(1)~MeV, for the JUNO detector were established in this study. The radioactivity of each source and the risk of impurities leaking into the detector from the source were confirmed to meet the experimental requirements.

physics.ins-det↗

arXiv2024

RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement

Existing large language models (LLMs) show exceptional problem-solving capabilities but might struggle with complex reasoning tasks. Despite the successes of chain-of-thought and tree-based search methods, they mainly depend on the internal knowledge of LLMs to search over intermediate reasoning steps, limited to dealing with simple tasks involving fewer reasoning steps. In this paper, we propose \textbf{RAG-Star}, a novel RAG approach that integrates the retrieved information to guide the tree-based deliberative reasoning process that relies on the inherent knowledge of LLMs. By leveraging Monte Carlo Tree Search, RAG-Star iteratively plans intermediate sub-queries and answers for reasoning based on the LLM itself. To consolidate internal and external knowledge, we propose an retrieval-augmented verification that utilizes query- and answer-aware reward modeling to provide feedback for the inherent reasoning of LLMs. Our experiments involving Llama-3.1-8B-Instruct and GPT-4o demonstrate that RAG-Star significantly outperforms previous RAG and reasoning methods.

cs.CL↗

arXiv2024

GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models

Large Language Models (LLMs) are prone to generating content that exhibits gender biases, raising significant ethical concerns. Alignment, the process of fine-tuning LLMs to better align with desired behaviors, is recognized as an effective approach to mitigate gender biases. Although proprietary LLMs have made significant strides in mitigating gender bias, their alignment datasets are not publicly available. The commonly used and publicly available alignment dataset, HH-RLHF, still exhibits gender bias to some extent. There is a lack of publicly available alignment datasets specifically designed to address gender bias. Hence, we developed a new dataset named GenderAlign, aiming at mitigating a comprehensive set of gender biases in LLMs. This dataset comprises 8k single-turn dialogues, each paired with a "chosen" and a "rejected" response. Compared to the "rejected" responses, the "chosen" responses demonstrate lower levels of gender bias and higher quality. Furthermore, we categorized the gender biases in the "rejected" responses of GenderAlign into 4 principal categories. The experimental results show the effectiveness of GenderAlign in reducing gender bias in LLMs.

cs.CL↗

arXiv2024

PandaX-xT: a Multi-ten-tonne Liquid Xenon Observatory at the China Jinping Underground Laboratory

We propose a major upgrade to the existing PandaX-4T experiment in the China Jinping Underground Laboratory. The new experiment, PandaX-xT, will be a multi-ten-tonne liquid xenon, ultra-low background, and general-purpose observatory. The full-scaled PandaX-xT contains a 43-tonne liquid xenon active target. Such an experiment will significantly advance our fundamental understanding of particle physics and astrophysics. The sensitivity of dark matter direct detection will be improved by nearly two orders of magnitude compared to the current best limits, approaching the so-called "neutrino floor" for a dark matter mass above 10 GeV/$c^2$, providing a decisive test to the Weakly Interacting Massive Particle paradigm. By searching for the neutrinoless double beta decay of $^{136}$Xe isotope in the detector, the effective Majorana neutrino mass can be measured to a [10 -- 41] meV/$c^2$ sensitivity, providing a key test to the Dirac/Majorana nature of neutrino s. Astrophysical neutrinos and other ultra-rare interactions can also be measured and searched for with an unprecedented background level, opening up new windows of discovery. Depending on the findings, PandaX-xT will seek the next stage upgrade utilizing isotopic separation on natural xenon.

hep-ex↗

arXiv2024

P2PFormer: A Primitive-to-polygon Method for Regular Building Contour Extraction from Remote Sensing Images

Extracting building contours from remote sensing imagery is a significant challenge due to buildings' complex and diverse shapes, occlusions, and noise. Existing methods often struggle with irregular contours, rounded corners, and redundancy points, necessitating extensive post-processing to produce regular polygonal building contours. To address these challenges, we introduce a novel, streamlined pipeline that generates regular building contours without post-processing. Our approach begins with the segmentation of generic geometric primitives (which can include vertices, lines, and corners), followed by the prediction of their sequence. This allows for the direct construction of regular building contours by sequentially connecting the segmented primitives. Building on this pipeline, we developed P2PFormer, which utilizes a transformer-based architecture to segment geometric primitives and predict their order. To enhance the segmentation of primitives, we introduce a unique representation called group queries. This representation comprises a set of queries and a singular query position, which improve the focus on multiple midpoints of primitives and their efficient linkage. Furthermore, we propose an innovative implicit update strategy for the query position embedding aimed at sharpening the focus of queries on the correct positions and, consequently, enhancing the quality of primitive segmentation. Our experiments demonstrate that P2PFormer achieves new state-of-the-art performance on the WHU, CrowdAI, and WHU-Mix datasets, surpassing the previous SOTA PolyWorld by a margin of 2.7 AP and 6.5 AP75 on the largest CrowdAI dataset

cs.CV↗

arXiv2024

Self-supervised Video Instance Segmentation Can Boost Geographic Entity Alignment in Historical Maps

Tracking geographic entities from historical maps, such as buildings, offers valuable insights into cultural heritage, urbanization patterns, environmental changes, and various historical research endeavors. However, linking these entities across diverse maps remains a persistent challenge for researchers. Traditionally, this has been addressed through a two-step process: detecting entities within individual maps and then associating them via a heuristic-based post-processing step. In this paper, we propose a novel approach that combines segmentation and association of geographic entities in historical maps using video instance segmentation (VIS). This method significantly streamlines geographic entity alignment and enhances automation. However, acquiring high-quality, video-format training data for VIS models is prohibitively expensive, especially for historical maps that often contain hundreds or thousands of geographic entities. To mitigate this challenge, we explore self-supervised learning (SSL) techniques to enhance VIS performance on historical maps. We evaluate the performance of VIS models under different pretraining configurations and introduce a novel method for generating synthetic videos from unlabeled historical map images for pretraining. Our proposed self-supervised VIS method substantially reduces the need for manual annotation. Experimental results demonstrate the superiority of the proposed self-supervised VIS approach, achieving a 24.9\% improvement in AP and a 0.23 increase in F1 score compared to the model trained from scratch.

cs.CV↗

arXiv2024

Dg Loday-Pirashvili modules over Lie algebras

A Loday-Pirashvili module over a Lie algebra $\mathfrak{g}$ is a Lie algebra object $\bigl(G\xrightarrow{X} \mathfrak{g} \bigr)$ in the category of linear maps, or equivalently, a $\mathfrak{g}$-module $G$ which admits a $\mathfrak{g}$-equivariant linear map $X:G\to \mathfrak{g}$. We study dg Loday-Pirashvili modules over Lie algebras, which is a generalization of Loday-Pirashvili modules in a natural way, and establish several equivalent characterizations of dg Loday-Pirashvili modules. To provide a concise characterization, a dg Loday-Pirashvili module is a non-negative and bounded dg $\mathfrak{g}$-module $V$ paired with a weak morphism of dg $\mathfrak{g}$-modules $α\colon V\rightsquigarrow \mathfrak{g}$. Such a dg Loday-Pirashvili module resolves an arbitrarily specified classical Loday-Pirashvili module in the sense that it exists and is unique (up to homotopy). Dg Loday-Pirashvili modules can be characterized through dg derivations. This perspective allows the calculation of the corresponding twisted Atiyah classes. By leveraging the Kapranov functor on the dg derivation arising from a dg Loday-Pirashvili module $(V,α)$, a Leibniz$_\infty[1]$ algebra structure can be derived on $\wedge^\bullet \mathfrak{g}^\vee\otimes V[1]$. The binary bracket of this structure corresponds to the twisted Atiyah cocycle. To exemplify these intricate algebraic structures through specific cases, we utilize this machinery to a particular type of dg Loday-Pirashvili modules stemming from Lie algebra pairs.

math.RA↗