About Me

I am a master’s student in Computer Science and Technology at Wuhan University of Technology. My research focuses on Efficient Machine Learning and Trustworthy AI. I am broadly interested in building efficient, reliable, and deployable AI systems, especially for large language models, vision-language models, and vision-language-action models.

On the efficiency side, my work explores model compression and acceleration techniques, including quantization, sparsity, speculative decoding, and efficient inference for LLM/VLM/VLA. I am particularly interested in reducing memory footprint, computation cost, and inference latency while preserving model capability and robustness.

On the trustworthiness side, I study machine unlearning, uncertainty estimation, and related topics in trustworthy AI. My goal is to understand how efficient AI systems behave under compression and deployment constraints, and how to make them more accountable, privacy-aware, and reliable in real-world scenarios.

🔬 Research Interests

• Efficient Machine Learning
• Trustworthy AI
• Embodied AI
• AI for Science

📚 Selected Publications

• Yujia Tong, Yuze Wang, Jingling Yuan, Chuang Hu. “Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels.” ICCV, 2025. [Paper] [arXiv:2503.13917]

• Yujia Tong, Jingling Yuan, Chuang Hu. “Enhancing Quantization-Aware Training on Edge Devices via Relative Entropy Coreset Selection and Cascaded Layer Correction.” IEEE TMC, 2026. [DOI] [arXiv:2507.17768]

• Yujia Tong, Jingling Yuan, Tian Zhang, Jianquan Liu, Chuang Hu. “Data-Free Quantization of Vision Transformers via Easy-to-Hard Synthesis and Activation Correction.” ACM TOMM, 2025. [DOI] [arXiv:2507.14481]

• Tian Zhang, Yujia Tong, Junhao Dong, Ke Xu, Yuze Wang, Jingling Yuan. “Forget by Uncertainty: Orthogonal Entropy Unlearning for Quantized Neural Networks.” ICML, 2026. [arXiv:2602.00567]

• Yujia Tong, Tian Zhang, Jingling Yuan, Yuze Wang, Chuang Hu. “LetheViT: Selective Machine Unlearning for Vision Transformers via Attention-Guided Contrastive Learning.” Preprint, 2025. [arXiv:2508.01569]

• Yujia Tong, Tian Zhang, Yunyang Wan, Kaiwei Lin, Jingling Yuan, Chuang Hu. “SAGE: Accelerating Vision-Language Models via Entropy-Guided Adaptive Speculative Decoding.” Preprint, 2026. [arXiv:2602.00523]

• Yujia Tong, Yuxi Wang, Yunyang Wan, Tian Zhang, Junhao Dong, Jingling Yuan. “Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction.” Preprint, 2026. [arXiv:2606.01850]

• Yuze Wang, Yujia Tong, Xuan Liu, Junhao Dong. “SAU: Sparsity-Aware Unlearning for LLMs via Gradient Masking and Importance Redistribution.” Preprint, 2026. [arXiv:2602.00577]

👥 Academic Service

Conference Reviewer: ICML’26, NeurIPS’26, CVPR’25/26, ICCV’25, ECCV’26.

Journal Reviewer: IEEE Transactions on Circuits and Systems for Video Technology (TCSVT); IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).

🏆 Honors and Awards

• First Prize, Kingsoft Cloud LLM Inference Acceleration Competition, 2026
• Foresight Award (National Third Place), 5th SJTU-Winning Health Smart Healthcare Challenge, 2022
• National Second Prize, China Collegiate Computing Contest - Network Technology Challenge, 2023
• Provincial Second Prize, China Computer Design Competition, Central-South Region, 2023
• Provincial Third Prize, China Collegiate Computing Contest - Network Technology Challenge, 2023