arXiv subjects

Minghua Zhang

Publications and source records attributed to Minghua Zhang.

13 recordsLinked to original sources

arXiv2026

SCOPE: A Lightweight-training LLM Framework for Air Traffic Control Readback Monitoring

Pilot readback of Air Traffic Control (ATC) voice instructions is a primary safeguard against miscommunication in air transportation. However, readback anomalies remain implicated in approximately 80% of aviation incidents. This vulnerability is further exacerbated by rising traffic volume and elevated cognitive workload, thereby motivating automated readback monitoring by machine. Traditional rule-based and machine learning approaches struggle to generalize across the highly variable and evolving phraseology of air traffic controller-pilot communications. While Large Language Models (LLMs) have opened a new avenue through their strong reasoning and generalization capabilities, existing approaches still face deployment and computational barriers in practice. In this work, we propose Semantic reasoning for Communication via Open-set Plug-in with Examples (SCOPE), a novel lightweight-training LLM framework that advances both the efficiency and accuracy of machine-based ATC readback monitoring. The core idea is to couple a plug-in open-set classifier with a carefully designed in-context learning mechanism on top of a frozen LLM. Extensive experiments on the semi-synthetic communication dataset show that SCOPE attains superior accuracy while delivering the low-latency response required for operational environments. Under a few-shot setting, SCOPE achieves 91.05% accuracy in open-set detection and corrects 96.63% of anomalous readbacks, thereby outperforming the strongest available baselines while providing explanations for its decisions. These findings demonstrate the potential of our framework as a practical pathway toward interpretable and controllable ATC readback monitoring.

cs.LG↗

arXiv2026

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

General reasoning represents a long-standing and formidable challenge in artificial intelligence. Recent breakthroughs, exemplified by large language models (LLMs) and chain-of-thought prompting, have achieved considerable success on foundational reasoning tasks. However, this success is heavily contingent upon extensive human-annotated demonstrations, and models' capabilities are still insufficient for more complex problems. Here we show that the reasoning abilities of LLMs can be incentivized through pure reinforcement learning (RL), obviating the need for human-labeled reasoning trajectories. The proposed RL framework facilitates the emergent development of advanced reasoning patterns, such as self-reflection, verification, and dynamic strategy adaptation. Consequently, the trained model achieves superior performance on verifiable tasks such as mathematics, coding competitions, and STEM fields, surpassing its counterparts trained via conventional supervised learning on human demonstrations. Moreover, the emergent reasoning patterns exhibited by these large-scale models can be systematically harnessed to guide and enhance the reasoning capabilities of smaller models.

cs.CL↗

arXiv2025

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

We introduce DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance. The key technical breakthroughs of DeepSeek-V3.2 are as follows: (1) DeepSeek Sparse Attention (DSA): We introduce DSA, an efficient attention mechanism that substantially reduces computational complexity while preserving model performance in long-context scenarios. (2) Scalable Reinforcement Learning Framework: By implementing a robust reinforcement learning protocol and scaling post-training compute, DeepSeek-V3.2 performs comparably to GPT-5. Notably, our high-compute variant, DeepSeek-V3.2-Speciale, surpasses GPT-5 and exhibits reasoning proficiency on par with Gemini-3.0-Pro, achieving gold-medal performance in both the 2025 International Mathematical Olympiad (IMO) and the International Olympiad in Informatics (IOI). (3) Large-Scale Agentic Task Synthesis Pipeline: To integrate reasoning into tool-use scenarios, we developed a novel synthesis pipeline that systematically generates training data at scale. This methodology facilitates scalable agentic post-training, yielding substantial improvements in generalization and instruction-following robustness within complex, interactive environments.

cs.CL↗

arXiv2025

An Empirical Study on the Robustness of YOLO Models for Underwater Object Detection

Underwater object detection (UOD) remains a critical challenge in computer vision due to underwater distortions which degrade low-level features and compromise the reliability of even state-of-the-art detectors. While YOLO models have become the backbone of real-time object detection, little work has systematically examined their robustness under these uniquely challenging conditions. This raises a critical question: Are YOLO models genuinely robust when operating under the chaotic and unpredictable conditions of underwater environments? In this study, we present one of the first comprehensive evaluations of recent YOLO variants (YOLOv8-YOLOv12) across six simulated underwater environments. Using a unified dataset of 10,000 annotated images from DUO and Roboflow100, we not only benchmark model robustness but also analyze how distortions affect key low-level features such as texture, edges, and color. Our findings show that (1) YOLOv12 delivers the strongest overall performance but is highly vulnerable to noise, and (2) noise disrupts edge and texture features, explaining the poor detection performance in noisy images. Class imbalance is a persistent challenge in UOD. Experiments revealed that (3) image counts and instance frequency primarily drive detection performance, while object appearance exerts only a secondary influence. Finally, we evaluated lightweight training-aware strategies: noise-aware sample injection, which improves robustness in both noisy and real-world conditions, and fine-tuning with advanced enhancement, which boosts accuracy in enhanced domains but slightly lowers performance in original data, demonstrating strong potential for domain adaptation, respectively. Together, these insights provide practical guidance for building resilient and cost-efficient UOD systems.

cs.CV↗

arXiv2025

A Structured Review of Underwater Object Detection Challenges and Solutions: From Traditional to Large Vision Language Models

Underwater object detection (UOD) is vital to diverse marine applications, including oceanographic research, underwater robotics, and marine conservation. However, UOD faces numerous challenges that compromise its performance. Over the years, various methods have been proposed to address these issues, but they often fail to fully capture the complexities of underwater environments. This review systematically categorizes UOD challenges into five key areas: Image quality degradation, target-related issues, data-related challenges, computational and processing constraints, and limitations in detection methodologies. To address these challenges, we analyze the progression from traditional image processing and object detection techniques to modern approaches. Additionally, we explore the potential of large vision-language models (LVLMs) in UOD, leveraging their multi-modal capabilities demonstrated in other domains. We also present case studies, including synthetic dataset generation using DALL-E 3 and fine-tuning Florence-2 LVLM for UOD. This review identifies three key insights: (i) Current UOD methods are insufficient to fully address challenges like image degradation and small object detection in dynamic underwater environments. (ii) Synthetic data generation using LVLMs shows potential for augmenting datasets but requires further refinement to ensure realism and applicability. (iii) LVLMs hold significant promise for UOD, but their real-time application remains under-explored, requiring further research on optimization techniques.

cs.CV↗

arXiv2025

DeepSeek-V3 Technical Report

We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2. Furthermore, DeepSeek-V3 pioneers an auxiliary-loss-free strategy for load balancing and sets a multi-token prediction training objective for stronger performance. We pre-train DeepSeek-V3 on 14.8 trillion diverse and high-quality tokens, followed by Supervised Fine-Tuning and Reinforcement Learning stages to fully harness its capabilities. Comprehensive evaluations reveal that DeepSeek-V3 outperforms other open-source models and achieves performance comparable to leading closed-source models. Despite its excellent performance, DeepSeek-V3 requires only 2.788M H800 GPU hours for its full training. In addition, its training process is remarkably stable. Throughout the entire training process, we did not experience any irrecoverable loss spikes or perform any rollbacks. The model checkpoints are available at https://github.com/deepseek-ai/DeepSeek-V3.

cs.CL↗

arXiv2024

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

We present DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training and efficient inference. It comprises 236B total parameters, of which 21B are activated for each token, and supports a context length of 128K tokens. DeepSeek-V2 adopts innovative architectures including Multi-head Latent Attention (MLA) and DeepSeekMoE. MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation. Compared with DeepSeek 67B, DeepSeek-V2 achieves significantly stronger performance, and meanwhile saves 42.5% of training costs, reduces the KV cache by 93.3%, and boosts the maximum generation throughput to 5.76 times. We pretrain DeepSeek-V2 on a high-quality and multi-source corpus consisting of 8.1T tokens, and further perform Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) to fully unlock its potential. Evaluation results show that, even with only 21B activated parameters, DeepSeek-V2 and its chat versions still achieve top-tier performance among open-source models.

cs.CL↗

arXiv2024

DeepSeek LLM: Scaling Open-Source Language Models with Longtermism

The rapid development of open-source large language models (LLMs) has been truly remarkable. However, the scaling law described in previous literature presents varying conclusions, which casts a dark cloud over scaling LLMs. We delve into the study of scaling laws and present our distinctive findings that facilitate scaling of large scale models in two commonly used open-source configurations, 7B and 67B. Guided by the scaling laws, we introduce DeepSeek LLM, a project dedicated to advancing open-source language models with a long-term perspective. To support the pre-training phase, we have developed a dataset that currently consists of 2 trillion tokens and is continuously expanding. We further conduct supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) on DeepSeek LLM Base models, resulting in the creation of DeepSeek Chat models. Our evaluation results demonstrate that DeepSeek LLM 67B surpasses LLaMA-2 70B on various benchmarks, particularly in the domains of code, mathematics, and reasoning. Furthermore, open-ended evaluations reveal that DeepSeek LLM 67B Chat exhibits superior performance compared to GPT-3.5.

cs.CL↗

arXiv2023

CPS-MEBR: Click Feedback-Aware Web Page Summarization for Multi-Embedding-Based Retrieval

Embedding-based retrieval (EBR) is a technique to use embeddings to represent query and document, and then convert the retrieval problem into a nearest neighbor search problem in the embedding space. Some previous works have mainly focused on representing the web page with a single embedding, but in real web search scenarios, it is difficult to represent all the information of a long and complex structured web page as a single embedding. To address this issue, we design a click feedback-aware web page summarization for multi-embedding-based retrieval (CPS-MEBR) framework which is able to generate multiple embeddings for web pages to match different potential queries. Specifically, we use the click data of users in search logs to train a summary model to extract those sentences in web pages that are frequently clicked by users, which are more likely to answer those potential queries. Meanwhile, we introduce sentence-level semantic interaction to design a multi-embedding-based retrieval (MEBR) model, which can generate multiple embeddings to deal with different potential queries by using frequently clicked sentences in web pages. Offline experiments show that it can perform high quality candidate retrieval compared to single-embedding-based retrieval (SEBR) model.

cs.IR↗

arXiv2019

Question-type Driven Question Generation

Question generation is a challenging task which aims to ask a question based on an answer and relevant context. The existing works suffer from the mismatching between question type and answer, i.e. generating a question with type $how$ while the answer is a personal name. We propose to automatically predict the question type based on the input answer and context. Then, the question type is fused into a seq2seq model to guide the question generation, so as to deal with the mismatching problem. We achieve significant improvement on the accuracy of question type prediction and finally obtain state-of-the-art results for question generation on both SQuAD and MARCO datasets.

cs.CL↗

arXiv2019

Multi-Task Learning with Language Modeling for Question Generation

This paper explores the task of answer-aware questions generation. Based on the attention-based pointer generator model, we propose to incorporate an auxiliary task of language modeling to help question generation in a hierarchical multi-task learning structure. Our joint-learning model enables the encoder to learn a better representation of the input sequence, which will guide the decoder to generate more coherent and fluent questions. On both SQuAD and MARCO datasets, our multi-task learning model boosts the performance, achieving state-of-the-art results. Moreover, human evaluation further proves the high quality of our generated questions.

cs.CL↗

arXiv2018

Learning Universal Sentence Representations with Mean-Max Attention Autoencoder

In order to learn universal sentence representations, previous methods focus on complex recurrent neural networks or supervised learning. In this paper, we propose a mean-max attention autoencoder (mean-max AAE) within the encoder-decoder framework. Our autoencoder rely entirely on the MultiHead self-attention mechanism to reconstruct the input sequence. In the encoding we propose a mean-max strategy that applies both mean and max pooling operations over the hidden vectors to capture diverse information of the input. To enable the information to steer the reconstruction process dynamically, the decoder performs attention over the mean-max representation. By training our model on a large collection of unlabelled data, we obtain high-quality representations of sentences. Experimental results on a broad range of 10 transfer tasks demonstrate that our model outperforms the state-of-the-art unsupervised single methods, including the classical skip-thoughts and the advanced skip-thoughts+LN model. Furthermore, compared with the traditional recurrent neural network, our mean-max AAE greatly reduce the training time.

cs.CL↗

arXiv2018

An Unsupervised Model with Attention Autoencoders for Question Retrieval

Question retrieval is a crucial subtask for community question answering. Previous research focus on supervised models which depend heavily on training data and manual feature engineering. In this paper, we propose a novel unsupervised framework, namely reduced attentive matching network (RAMN), to compute semantic matching between two questions. Our RAMN integrates together the deep semantic representations, the shallow lexical mismatching information and the initial rank produced by an external search engine. For the first time, we propose attention autoencoders to generate semantic representations of questions. In addition, we employ lexical mismatching to capture surface matching between two questions, which is derived from the importance of each word in a question. We conduct experiments on the open CQA datasets of SemEval-2016 and SemEval-2017. The experimental results show that our unsupervised model obtains comparable performance with the state-of-the-art supervised methods in SemEval-2016 Task 3, and outperforms the best system in SemEval-2017 Task 3 by a wide margin.

cs.CL↗