Peisong Wang

27 papers · 2017–2026 · 10 conferences · across top CS/AI conferences

Achievements

+12 more ↓

🏃 Academic Marathon (9) 🌍 Conference Polyglot (10) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (14)

🌈 Renaissance Researcher (9) 🌍 Conference Polyglot (10) 🏃 Academic Marathon (9) 🤝 Dynamic Duo (22) 🔬 Deep Specialist (12) 🧬 Topic Evolution 🗃️ Keyword Collector (92) 📈 Trend Setter ⚡ Prolific Year (6) 🚀 Conference Pioneer 🔥 Unstoppable (10) 💎 Century Club (26)

Conferences

AAAI (5) CVPR (5) ACL (4) ICML (3) IJCAI (3) ECCV (2) NIPS (2) EMNLP (1) ICCV (1) WACV (1)

Top co-authors

Jian Cheng (22) Xiangyu He (8) Qinghao Hu (7) Weixiang Xu (6) Yifan Zhang (3) Jia Li (3) Zhengyang Zhuge (3) Anda Cheng (2) Gang Li (2) Zeyu Zhu (2)

Research topics

Differential Privacy (1)

Keywords

model compression (10) large language model (6) efficient computing (6) model quantization (4) post-training quantization (4) neural network quantization (3) efficient inference (2) network quantization (2) neural network optimization (2) differential privacy (2) graph neural network (2) memory efficiency (2) graph representation (2) weight quantization (2) neural network (2) attention mechanism (2) object detection (1) transfer learning (1) network architecture (1) vision transformer (1)

Papers

MemeBQ:Memory Efficient Binary Quantization of LLMs AAAI 2026 A Universal Self-Attention Enhancement for Bridging Low-bit Quantization and Vision Transformers WACV 2026 LoRaDA: Low-Rank Direct Attention Adaptation for Efficient LLM Fine-tuning EMNLP 2025 S2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning ACL 2025 Q-Mamba: Towards more efficient Mamba models via post-training quantization ACL 2025 RQT: Hierarchical Residual Quantization for Multi-Model Compression ACL 2025 FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing ICML 2025 EAC-MoE: Expert-Selection Aware Compressor for Mixture-of-Experts Large Language Models ACL 2025 GLBench: A Comprehensive Benchmark for Graph with Large Language Models NIPS 2024 A Survey of Graph Meets Large Language Model: Progress and Future Directions IJCAI 2024 Patch-Aware Sample Selection for Efficient Masked Image Modeling AAAI 2024 Towards Efficient Spiking Transformer: a Token Sparsification Framework for Training and Inference Acceleration ICML 2024 Towards Efficient and Accurate Winograd Convolution via Full Quantization NIPS 2023 Towards Fully Sparse Training: Information Restoration with Spatial Similarity AAAI 2022 Differentially Private Federated Learning With Local Regularization and Sparsification CVPR 2022 DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy AAAI 2022 Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization ICCV 2021 ProxyBNN: Learning Binarized Neural Networks via Proxy Matrices ECCV 2020 Towards Accurate Post-training Network Quantization via Bit-Split and Stitching ICML 2020 Sparsity-Inducing Binarized Neural Networks AAAI 2020 Soft Threshold Ternary Networks IJCAI 2020 K-Nearest Neighbors Hashing CVPR 2019 ODE-Inspired Network Design for Single Image Super-Resolution CVPR 2019 Reading selectively via Binary Input Gated Recurrent Unit IJCAI 2019 Two-Step Quantization for Low-Bit Neural Networks CVPR 2018 Training Binary Weight Networks via Semi-Binary Decomposition ECCV 2018 Fixed-Point Factorized Networks CVPR 2017