刘学文
博士生
中国科学院自动化研究所
中科院工业视觉智能装备技术工程实验室
中国科学院大学
研究领域
- 高效深度学习，神经网络模型压缩
- 计算机视觉算法优化与硬件加速
教育经历
-
中国科学院自动化研究所 模式识别与智能系统, 2023-至今
中国科学院自动化研究所
学术发表
(2026).
K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge.
In ICLR 2026.
(2026).
PTQ4ARVG: Post-Training Quantization for AutoRegressive Visual Generation Models.
In ICLR 2026.
(2026).
Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval.
In ICLR 2026.
(2026).
SAQ-SAM: Semantically-Aligned Quantization for Segment Anything Model.
In AAAI 2026.
(2026).
Sparsity Induction for Accurate Post-Training Pruning of Large Language Models.
In ICASSP 2026.
(2025).
DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation.
In ACM MM 2025.
(2025).
CacheQuant: Comprehensively Accelerated Diffusion Models.
In CVPR 2025.
(2025).
K-sort arena: Efficient and reliable benchmarking for generative models via k-wise human preferences.
In CVPR 2025.
(2024).
DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation.
In arxiv preprint.
(2024).
RepQuant: Towards Accurate Post-Training Quantization of Large Transformer Models via Scale Reparameterization.
In arxiv preprint.
(2024).
EDA-DM: Enhanced distribution alignment for post-training quantization of diffusion models.
In arxiv preprint.