Author name cluster

Yunlong Zhao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

AAAI Conference 2026 Conference Paper

ROVER: Robust Generative Continual Identity Unlearning Against Relearning Attacks

Tairan Huang
Qiang Chen
Beibei Hu
Yunlong Zhao
Hongyan Xu
Zhiyuan Chen
Yi Chen
Xiu Su

Recent generative unlearning models synthesize high quality samples while protecting private information by unlearning the identity. However, existing generative identity unlearning methods face two challenges in multi-identity unlearning: 1) identity conflicts, which cause conflicts of model parameters in the continuous erasure of multiple identities; 2) fragile unlearning, where the model's unlearning ability deteriorates or fails under malicious attacks. In this paper, we introduce a critical yet under-explored task called robust multi-identity unlearning, with the goals of resolving identity conflicts to achieve interference-free unlearning and protecting against malicious attacks to achieve robust unlearning. To satisfy these goals, we propose a novel framework, RObust generatiVE continual identity unlearning against Relearning attacks (ROVER). By filtering unlearning requests with latent similarity, our method effectively isolates benign unlearning from malicious attacks to preserve identity removal integrity. Meanwhile, residual orthogonal resonator resolves identity conflicts in the continuous erasure of multiple identities, preserving stability in benign continual unlearning. Moreover, we introduce the phantom guard network to block malicious attacks by absorbing adversarial gradients, ensuring irreversible identity unlearning. The extensive experiments demonstrate that our proposed method achieves state-of-the-art performance on the task of robust multi-identity unlearning against relearning attacks.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Speech-Aware Long Context Pruning and Integration for Contextualized Automatic Speech Recognition

Yiming Rong
Yixin Zhang
Ziyi Wang
Deyang Jiang
Yunlong Zhao
Haoran Wu
Shiyu Zhou
Bo Xu

Automatic speech recognition (ASR) systems have achieved remarkable performance in common conditions but often struggle to leverage long-context information in contextualized scenarios that require domain-specific knowledge, such as conference presentations. This challenge arises primarily due to constrained model context windows and the sparsity of relevant information within extensive contextual noise. To solve this, we propose the SAP^2 method, a novel framework that dynamically prunes and integrates relevant contextual keywords in two stages. Specifically, each stage leverages our proposed Speech-Driven Attention-based Pooling mechanism, enabling efficient compression of context embeddings while preserving speech-salient information. Experimental results demonstrate state-of-the-art performance of SAP^2 on the SlideSpeech and LibriSpeech datasets, achieving word error rates (WER) of 7.71% and 1.12%, respectively. On SlideSpeech, our method notably reduces biased keyword error rates (B-WER) by 41.1% compared to non-contextual baselines. SAP^2 also exhibits robust scalability, consistently maintaining performance under extensive contextual input conditions on both datasets.

PDF Details DOI

EAAI Journal 2025 Journal Article

Cooperative reconnaissance coverage for heterogeneous unmanned aerial vehicle swarm in unknown communication interference environments

Yongjian Fan
Bing Chen
Yunlong Zhao
Feng Hu
Chunyan Liu
Yang Li

In complex environments with uncertain communication interference, heterogeneous unmanned aerial vehicle (HUAV) swarm often encounter the challenge of communication disruptions while collaboratively executing reconnaissance and coverage missions, hindering efficient information sharing and subsequently leading to substantial issues of redundant coverage. Given that existing research overlooks the impact of communication interference, this paper proposes a Coverage-Oriented Multi-Agent Cooperative Artificial Potential Field (MACAPF) algorithm. Firstly, a communication model for HUAV swarm under communication interference is considered to accurately reflect real-time communication status. Secondly, an autonomous collaborative distributed-concentrated architecture is devised, which dynamically adjusts the distributed-concentrated state of the swarm based on varying communication conditions, providing support for resolving communication disruptions faced by the HUAV swarm. Lastly, addressing the limitations of traditional artificial potential field (APF) algorithm in unknown communication interference environments, individualized definitions of the HUAV potential field are introduced, and the MACAPF algorithm is designed based on the autonomous collaborative distributed-concentrated architecture. This algorithm effectively guides HUAVs experiencing communication disruptions to restore communication, enhancing the communication efficiency and cooperative operation capabilities of the HUAV swarm. Simulation results demonstrate that the proposed MACAPF algorithm exhibits significant advantages over other state of the art (SOTA) algorithms across multiple dimensions under various signal interference intensities.

Details DOI

AAAI Conference 2025 Conference Paper

Leveraging Attention to Effectively Compress Prompts for Long-Context LLMs

Yunlong Zhao
Haoran Wu
Bo Xu

Prompt compression is increasingly studied for its potential to reduce computational costs and alleviate the burden on language models when processing lengthy prompts. Prior research has assessed token retention and removal by calculating information entropy. However, prompt compression encounters two significant challenges: (1) Information entropy, while widely used, may not be the optimal compression metric; and (2) The semantic significance of tokens is context-dependent, which renders independent token retention decisions inadequate. We posit that the solution to these challenges lies in the intrinsic mechanism of language models. Large language models (LLMs) exhibit robust contextual processing capabilities, with recent studies on their internal dynamics revealing that the attention mechanism plays a crucial role in modeling how LLMs leverage long contexts. Building on this insight, we introduce AttnComp, a novel approach that exploits the attention mechanism within language models to guide prompt compression. Our method employs causal cross-attention from the query to the context to evaluate the significance of each token, and we develop a graph-based algorithm to efficiently cluster tokens into semantic units, thus mitigating the issue of independent dependencies. We conduct experiments on datasets for retrieval-augmented generation and multiple long tasks involving single or multi-document QA. Our proposed method, AttnComp, outperforms previous baselines and validates the contributions of our components through analytical experiments. Compared to other methods that use a causal LM for prompt compression, our approach results in shorter latency and improved performance.

PDF Details DOI

YNIMG Journal 2024 Journal Article

Noninvasive microvascular imaging in newborn rats using high-frequency ultrafast ultrasound

Yunlong Zhao
Jiabin Zhang
Hao Yu
Xinlin Hou
Jue Zhang

Ultrasound imaging stands as the predominant modality for neonatal health assessment, with recent advancements in ultrafast Doppler (μDoppler) technology offering significant promise in fields such as neonatal brain imaging. Combining μDoppler with high-frequency ultrasound (HF-μDoppler) presents a potential efficient avenue to enhance in vivo microvascular imaging in small animals, notably newborn rats, a crucial preclinical animal model for neonatal disease and development research. It is necessary to verify the imaging performance of HF-μDoppler in preclinical trials. This study investigates the microvascular imaging capabilities of HF-μDoppler using a 30 MHz high-frequency linear array probe in newborn rats. Results demonstrate the clarity of cerebral microvascular imaging in rats aged 1 to 7 postnatal days, extending to whole-body microvascular imaging, encompassing the central nervous system, including the brain and spinal cord. In conclusion, HF-μDoppler technology emerges as a reliable imaging tool, offering a new perspective for preclinical investigations into neonatal diseases and development.

Details DOI

EAAI Journal 2021 Journal Article

A hybrid particle swarm optimization with crisscross learning strategy

Baoxian Liang
Yunlong Zhao
Yang Li

As an efficient and simple optimization algorithm, particle swarm optimization (PSO) has been widely applied to solve various real optimization problems. However, avoiding premature convergence and balancing the global exploration and local exploitation capabilities of the PSO remains two crucial problems. To overcome these drawbacks of PSO, a hybrid particle swarm optimization with crisscross learning strategy (PSO-CL) algorithm is proposed in this paper. In PSO-CL, in order to well balance the global exploration and local exploitation capabilities of PSO, a search direction adjustment mechanism based on subpopulation division operation is proposed. Meantime, to avoid the premature convergence and enhance the global search ability, a crossover-based comprehensive learning strategy (CCL) is adopted. Additionally, a stochastic example learning strategy (SEL) is introduced, which can assist collective information to be spread among separate sub-swarms, improve the local exploitation ability of the algorithm. 15 classic benchmark functions, CEC2017 test suite and two real-world optimization problems are utilized to verify the promising performance of PSO-CL, experimental results and statistical analysis indicate that PSO-CL has competitive performance compared with state-of-the-art PSO variants.

Details DOI