arXiv subjects

Minling Zhang

Publications and source records attributed to Minling Zhang.

7 recordsLinked to original sources

arXiv2026

Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation

Large reasoning models (LRMs) achieved remarkable performance via chain-of-thought (CoT), but recent studies showed that such enhanced reasoning capabilities are at the expense of significantly degraded safety capabilities. In this paper, we reveal that LRMs' safety degradation occurs only after CoT is enabled, and this degradation is not observed when CoT is disabled. This observation motivates us to consider encouraging LRMs to make safety decisions before CoT generation. To this end, we propose a novel safety alignment method that promotes the safety decision-making of LRMs before starting CoT generation. Specifically, we first utilize a Bert-based classifier to extract safety decision signals from a safe model (e.g., a CoT-disabled LRM) and then integrate these signals into LRMs' safety alignment as auxiliary supervision. In this way, the safety gradients can be backpropagated to the LRMs' latent representations, effectively strengthening the LRMs' safety decision-making abilities against CoT generation. Extensive experiments demonstrate that our method substantially improves the safety capabilities of LRMs while effectively maintaining LRMs' general reasoning performance.

cs.AI↗

arXiv2025

Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation

Learning with high-resource data has demonstrated substantial success in artificial intelligence (AI); however, the costs associated with data annotation and model training remain significant. A fundamental objective of AI research is to achieve robust generalization with limited-resource data. This survey employs agnostic active sampling theory within the Probably Approximately Correct (PAC) framework to analyze the generalization error and label complexity associated with learning from low-resource data in both model-agnostic supervised and unsupervised settings. Based on this analysis, we investigate a suite of optimization strategies tailored for low-resource data learning, including gradient-informed optimization, meta-iteration optimization, geometry-aware optimization, and LLMs-powered optimization. Furthermore, we provide a comprehensive overview of multiple learning paradigms that can benefit from low-resource data, including domain transfer, reinforcement feedback, and hierarchical structure modeling. Finally, we conclude our analysis and investigation by summarizing the key findings and highlighting their implications for learning with low-resource data.

cs.LG↗

arXiv2025

Design of A New Multiple-Chirp-Rate Index Modulation for LoRa Networks

We propose a multiple chirp rate index modulation (MCR-IM) system based on Zadoff-Chu (ZC) sequences that overcomes the problems of low transmission rate and large-scale access in classical LoRa networks. We demonstrate the extremely low cross-correlation of MCR-IM signals across different spread factors, showing that the proposed MCR-IM system also inherits the characteristics of ZC sequences modulation. Moreover, we derive an approximate closed-form expression for the bit-error rate (BER) of the proposed MCR-IM system over Nakagami-m fading channels. Simulation results confirm the accuracy of the derived closed-form expression and demonstrate that the MCR-IM system achieves higher levels of spectral efficiency (SE) compared to existing systems. In this context, assigning multiple chirp rates to each user results in a reduction in the number of parallel channels. To mitigate this issue, we propose a peak detection based successive interference cancellation (PD-SIC) algorithm to accommodate more users. Compared to orthogonal scatter chirp spreading spectrum system that names OrthoRa, the MCR-IM system with PD-SIC algorithm achieves lower BER levels. For a similar number of collision signals, the throughput of the MCR-IM system is enhanced by 16% to 21%. Owing to these advantages, the proposed MCR-IM is well suited for large-scale, high-rate LoRa network applications.

eess.SP↗

arXiv2025

APVR: Hour-Level Long Video Understanding with Adaptive Pivot Visual Information Retrieval

Current multimodal large language models (MLLMs) struggle with hour-level video understanding, facing significant challenges not only in modeling the substantial information volume of long videos but also in overcoming the memory wall and resource constraints during both training and inference. Although recent training-free approaches have alleviated resource demands by compressing visual features, their reliance on incomplete visual information limits the performance potential. To address these limitations, we propose Adaptive Pivot Visual information Retrieval (APVR), a training-free framework that hierarchically retrieves and retains sufficient and important visual information. It breakthroughs the memory wall limitation via two complementary components: Pivot Frame Retrieval employs query expansion and iterative spatio-semantic confidence scoring to identify relevant video frames, and Pivot Token Retrieval performs query-aware attention-driven token selection within up to 1024 pivot frames. This dual granularity approach enables the processing of hour-long videos while maintaining semantic fidelity. Experimental validations on three different baseline MLLMs demonstrate significant performance improvements up to 9.5\%, 4.6\% and 9.7\% on LongVideoBench, VideoMME and MLVU, respectively. APVR achieves state-of-the-art results for both training-free and training-based approaches.

cs.CV↗

arXiv2024

Towards Few-Shot Learning in the Open World: A Review and Beyond

Human intelligence is characterized by our ability to absorb and apply knowledge from the world around us, especially in rapidly acquiring new concepts from minimal examples, underpinned by prior knowledge. Few-shot learning (FSL) aims to mimic this capacity by enabling significant generalizations and transferability. However, traditional FSL frameworks often rely on assumptions of clean, complete, and static data, conditions that are seldom met in real-world environments. Such assumptions falter in the inherently uncertain, incomplete, and dynamic contexts of the open world. This paper presents a comprehensive review of recent advancements designed to adapt FSL for use in open-world settings. We categorize existing methods into three distinct types of open-world few-shot learning: those involving varying instances, varying classes, and varying distributions. Each category is discussed in terms of its specific challenges and methods, as well as its strengths and weaknesses. We standardize experimental settings and metric benchmarks across scenarios, and provide a comparative analysis of the performance of various methods. In conclusion, we outline potential future research directions for this evolving field. It is our hope that this review will catalyze further development of effective solutions to these complex challenges, thereby advancing the field of artificial intelligence.

cs.LG↗

arXiv2023

On the Performance of LoRa Empowered Communication for Wireless Body Area Networks

To remotely monitor the physiological status of the human body, long range (LoRa) communication has been considered as an eminently suitable candidate for wireless body area networks (WBANs). Typically, a Rayleigh-lognormal fading channel is encountered by the LoRa links of the WBAN. In this context, we characterize the performance of the LoRa system in WBAN scenarios with an emphasis on the physical (PHY) layer and medium access control (MAC) layer in the face of Rayleigh-lognormal fading channels and the same spreading factor interference. Specifically, closed-form approximate bit error probability (BEP) expressions are derived for the LoRa system. The results show that increasing the SF and reducing the interference efficiently mitigate the shadowing effects. Moreover, in the quest for the most suitable MAC protocol for LoRa based WBANs, three MAC protocols are critically appraised, namely the pure ALOHA, slotted ALOHA, and carrier-sense multiple access. The coverage probability, energy efficiency, throughput, and system delay of the three MAC protocols are analyzed in Rayleigh-lognormal fading channel. Furthermore, the performance of the equal-interval-based and equal-area-based schemes is analyzed to guide the choice of the SF. Our simulation results confirm the accuracy of the mathematical analysis and provide some useful insights for the future design of LoRa based WBANs.

cs.IT↗

arXiv2023

A Survey of Learning on Small Data: Generalization, Optimization, and Challenge

Learning on big data brings success for artificial intelligence (AI), but the annotation and training costs are expensive. In future, learning on small data that approximates the generalization ability of big data is one of the ultimate purposes of AI, which requires machines to recognize objectives and scenarios relying on small data as humans. A series of learning topics is going on this way such as active learning and few-shot learning. However, there are few theoretical guarantees for their generalization performance. Moreover, most of their settings are passive, that is, the label distribution is explicitly controlled by finite training resources from known distributions. This survey follows the agnostic active sampling theory under a PAC (Probably Approximately Correct) framework to analyze the generalization error and label complexity of learning on small data in model-agnostic supervised and unsupervised fashion. Considering multiple learning communities could produce small data representation and related topics have been well surveyed, we thus subjoin novel geometric representation perspectives for small data: the Euclidean and non-Euclidean (hyperbolic) mean, where the optimization solutions including the Euclidean gradients, non-Euclidean gradients, and Stein gradient are presented and discussed. Later, multiple learning communities that may be improved by learning on small data are summarized, which yield data-efficient representations, such as transfer learning, contrastive learning, graph representation learning. Meanwhile, we find that the meta-learning may provide effective parameter update policies for learning on small data. Then, we explore multiple challenging scenarios for small data, such as the weak supervision and multi-label. Finally, multiple data applications that may benefit from efficient small data representation are surveyed.

cs.LG↗