Hao Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hao Wu has a total of 111 co-authors. Here are the top co-authors by number of shared publications:
- Fengyuan Xu
National Key Lab for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China
15 shared publications - Sheng Zhong
State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China
14 shared publications - Feng Lyu
Central South University
12 shared publications - Shucheng Li
Central South University
10 shared publications - Fan Wu
Central South University, Changsha, China
4 shared publications - Mingliu Liu
State Grid Hubei Electric Power Research Institute, Wuhan, China
4 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25  (12) , 24073-24087
Scaling LLMs via Collaboration: Efficient LLM Inference Across Resource-Constrained Devices
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25  (12) , 24073-24087
Scaling LLMs via Collaboration: Efficient LLM Inference Across Resource-Constrained Devices
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 660-674
A 2 : Characterizing and Mitigating Imbalanced Reclaim in MGLRU via Active Aging at Production Scale
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 660-674
Open AccessA 2 : Characterizing and Mitigating Imbalanced Reclaim in MGLRU via Active Aging at Production Scale
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1492-1506
FeatureFuzz: Treating Bug-prone Features as Core Primitives for Compiler Fuzzing
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1492-1506
Open AccessFeatureFuzz: Treating Bug-prone Features as Core Primitives for Compiler Fuzzing
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4148-4162
Mind the Gap: Action Rebinding Attacks against Android GUI Agents
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4148-4162
Open AccessMind the Gap: Action Rebinding Attacks against Android GUI Agents
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5484-5493
MetaNav: Metacognitive Vision-Language Navigation via Reflective Exploration
Training-free Vision-Language Navigation (VLN) agents powered by foundation models can follow instructions and explore 3D environments. However, existing approaches rely on greedy frontier selection and passive spatial memory, leading to inefficient behaviors such as local oscillation and redundant revisiting. We argue that this stems from a lack of metacognitive capabilities: the agent cannot monitor its exploration progress, diagnose strategy failures, or adapt accordingly. To address this, we propose MetaNav, a metacognitive navigation agent integrating spatial memory, history-aware planning, and reflective correction. Spatial memory builds a persistent 3D semantic map. History-aware planning penalizes revisiting to improve efficiency. Reflective correction detects stagnation and uses an LLM to generate corrective rules that guide future frontier selection. Experiments on GOAT-Bench, HM3D-OVON, and A-EQA show that MetaNav achieves state-of-the-art performance while reducing VLM queries by 20.7%, demonstrating that metacognitive reasoning significantly improves robustness and efficiency. The code is available at https://github.com/perfectlxy7/MetaNav.
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5484-5493
Open AccessMetaNav: Metacognitive Vision-Language Navigation via Reflective Exploration
Training-free Vision-Language Navigation (VLN) agents powered by foundation models can follow instructions and explore 3D environments. However, existing approaches rely on greedy frontier selection and passive spatial memory, leading to inefficient behaviors such as local oscillation and redundant revisiting. We argue that this stems from a lack of metacognitive capabilities: the agent cannot monitor its exploration progress, diagnose strategy failures, or adapt accordingly. To address this, we propose MetaNav, a metacognitive navigation agent integrating spatial memory, history-aware planning, and reflective correction. Spatial memory builds a persistent 3D semantic map. History-aware planning penalizes revisiting to improve efficiency. Reflective correction detects stagnation and uses an LLM to generate corrective rules that guide future frontier selection. Experiments on GOAT-Bench, HM3D-OVON, and A-EQA show that MetaNav achieves state-of-the-art performance while reducing VLM queries by 20.7%, demonstrating that metacognitive reasoning significantly improves robustness and efficiency. The code is available at https://github.com/perfectlxy7/MetaNav.
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23  (6) , 12990-13006
ImgSan: Utility-Based Image Privacy Sanitizer for Online Visual Question Answering
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23  (6) , 12990-13006
ImgSan: Utility-Based Image Privacy Sanitizer for Online Visual Question Answering
- Open Access
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 360-374
A 3 TP: Automated, Accurate, and Adaptive UAV Task Planning for Power Transmission Networks Inspection
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 360-374
Open AccessA 3 TP: Automated, Accurate, and Adaptive UAV Task Planning for Power Transmission Networks Inspection
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 16-28
Trace-Driven Automated PoC Synthesis for On-Chain Attacks
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 16-28
Open AccessTrace-Driven Automated PoC Synthesis for On-Chain Attacks
- Open Access
- 1 October 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3  (ISSTA) , 1147-1170
SAGE: Signal-Amplified Guided Embeddings for Vulnerability Detection
Software vulnerabilities are a primary threat to modern infrastructure. While static analysis and Graph Neural Networks have long served as the foundation for vulnerability detection, the emergence of Large Language Models (LLMs) has introduced a transformative paradigm driven by superior semantic reasoning and cross-environment generalization. However, in the context of LLM-based vulnerability detection, we identify a fundamental bottleneck in these models termed Signal Submersion : a state where features related to vulnerability are activated internally but numerically overwhelmed by dominant functional semantics. To address this, we propose SAGE ( S ignal- A mplified G uided E mbeddings), a framework that shifts from passive signal submersion to active signal recovery. SAGE integrates task-conditional Sparse Autoencoders (SAEs) to isolate and amplify these faint vulnerability signals. Extensive evaluations on BigVul, PrimeVul, and PreciseBugs demonstrate that SAGE achieves state-of-the-art performance. Notably, SAGE mitigates Signal Submersion by increasing the internal Signal-to-Noise Ratio (SNR) by 12.7× via sparse manifold projection. This mechanistic intervention enables a 7B model to achieve up to 318% Matthews Correlation Coefficient (MCC) gains on unseen distributions and a 319% gain on classic datasets. By maintaining robust performance across 13 programming languages and outperforming 34B baselines, SAGE establishes a more efficient and scalable path to software security than simple parameter scaling.
- 1 October 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3  (ISSTA) , 1147-1170
Open AccessSAGE: Signal-Amplified Guided Embeddings for Vulnerability Detection
Software vulnerabilities are a primary threat to modern infrastructure. While static analysis and Graph Neural Networks have long served as the foundation for vulnerability detection, the emergence of Large Language Models (LLMs) has introduced a transformative paradigm driven by superior semantic reasoning and cross-environment generalization. However, in the context of LLM-based vulnerability detection, we identify a fundamental bottleneck in these models termed Signal Submersion : a state where features related to vulnerability are activated internally but numerically overwhelmed by dominant functional semantics. To address this, we propose SAGE ( S ignal- A mplified G uided E mbeddings), a framework that shifts from passive signal submersion to active signal recovery. SAGE integrates task-conditional Sparse Autoencoders (SAEs) to isolate and amplify these faint vulnerability signals. Extensive evaluations on BigVul, PrimeVul, and PreciseBugs demonstrate that SAGE achieves state-of-the-art performance. Notably, SAGE mitigates Signal Submersion by increasing the internal Signal-to-Noise Ratio (SNR) by 12.7× via sparse manifold projection. This mechanistic intervention enables a 7B model to achieve up to 318% Matthews Correlation Coefficient (MCC) gains on unseen distributions and a 319% gain on classic datasets. By maintaining robust performance across 13 programming languages and outperforming 34B baselines, SAGE establishes a more efficient and scalable path to software security than simple parameter scaling.
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13  (20) , 47208-47222
Who’s Who Across Networks? Cross-Operator Identity Recognition From Dual-SIM Trajectories
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13  (20) , 47208-47222
Who’s Who Across Networks? Cross-Operator Identity Recognition From Dual-SIM Trajectories