Fangxin Liu

5 papers · 2021–2026 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

Venues

AAAI (2) ACL (1) EMNLP (1) ICCV (1)

Top co-authors

Li Jiang (5) Zongwu Wang (4) Haibing Guan (3) Wenbo Zhao (2) Yanzhi Wang (1) JinJin Li (1) Zhixiong Zhao (1) Xiaoyao Liang (1) Jian Liu (1) Changzhi Dai (1)

Research topics

Machine Learning (4) Artificial Intelligence (3) Deep Learning (3) Application Areas (3) Core AI (3) Natural Language Processing (2) Optimization & Theory · Deep Learning (2) Resources & Methods (2) Architectures (1) Generation (1) Optimization & Theory · Machine Learning (1) Techniques (1)

Keywords

model quantization (2) efficient inference (2) model compression (2) temporal encoding (1) fourier analysis (1) fourier transform (1) image recognition (1) spectral decomposition (1) integrate-and-fire neuron (1) spiking neural network (1) artificial neural network (1) inference efficiency (1) weight quantization (1) inference acceleration (1) mixed-precision quantization (1) speculative decoding (1) inference speed (1) ann-snn conversion (1) candidate selection (1) activation quantization (1)

Papers

Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient Inference ACL 2026 SpecQuant: Spectral Decomposition and Adaptive Truncation for Ultra-Low-Bit LLMs Quantization AAAI 2026 FlexQuant: A Flexible and Efficient Dynamic Precision Switching Framework for LLM Quantization EMNLP 2025 SpikeConverter: An Efficient Conversion Framework Zipping the Gap between Artificial Neural Networks and Spiking Neural Networks AAAI 2022 Improving Neural Network Efficiency via Post-Training Quantization With Adaptive Floating-Point ICCV 2021