zheyang li
9 papers · 2018–2025 · 6 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 ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (18) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver
🚀
Conference Pioneer
🗃️
Keyword Collector
(52)
Top co-authors
Research topics
Machine Learning
(7)
Application Areas
(7)
Deep Learning
(6)
Artificial Intelligence
(4)
Computer Vision
(4)
Analysis
(4)
Core AI · Artificial Intelligence
(4)
Optimization & Theory
(4)
Learning Types · Deep Learning
(2)
Techniques
(2)
Architectures
(1)
Core AI · Computer Vision
(1)
Learning Types · Machine Learning
(1)
Keywords
model compression
(5)
post-training quantization
(2)
model quantization
(2)
semantic segmentation
(1)
multimodal learning
(1)
multi-task learning
(1)
object detection
(1)
point cloud registration
(1)
sparse optimization
(1)
knowledge distillation
(1)
neural network optimization
(1)
cross-modal learning
(1)
referring expression
(1)
visual grounding
(1)
efficient inference
(1)
binary classification
(1)
loss landscape
(1)
low-rank approximation
(1)
neural network pruning
(1)
neural network quantization
(1)
Papers
1+1>2: A Synergistic Sparse and Low-Rank Compression Method for Large Language Models
EMNLP 2025
Beyond Dynamic Quantization: An Efficient Static Hierarchical Mix-precision Framework for Near-Lossless LLM Compression
EMNLP 2025
Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization
CVPR 2023
Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection
ICCV 2023
Language Adaptive Weight Generation for Multi-Task Visual Grounding
CVPR 2023
Learning Symmetry-Aware Geometry Correspondences for 6D Object Pose Estimation
ICCV 2023
SAViT: Structure-Aware Vision Transformer Pruning via Collaborative Optimization
NeurIPS 2022
Towards Accurate Low Bit-Width Quantization with Multiple Phase Adaptations
AAAI 2020
Extreme Network Compression via Filter Group Approximation
ECCV 2018