Zechun Liu
36 papers · 2018–2026 · 10 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+14 more ↓ Show less ↑
π Conference Polyglot (10) π Academic Marathon (7) π Interdisciplinary Bridge π§ Keyword Pioneer π£ Hot Topic Early Bird
πΊοΈ
Taxonomy Completionist
(51)
π
Interdisciplinary Bridge
π
Conference Polyglot
(10)
π
Grand Slam
π§¬
Topic Evolution
π
Keyword Champion
(6)
π€
Dynamic Duo
(17)
π¬
Deep Specialist
(10)
ποΈ
Keyword Collector
(101)
β‘
Prolific Year
(8)
π
Conference Pioneer
π
Century Club
(35)
π₯
Unstoppable
(8)
π
Trend Setter
Conferences
ICML (7)
ECCV (5)
ACL (4)
CVPR (4)
EMNLP (4)
ICLR (4)
AAAI (3)
ICCV (2)
NIPS (2)
WACV (1)
Top co-authors
Keywords
model compression
(9)
weight quantization
(6)
binary neural network
(4)
model quantization
(4)
knowledge distillation
(4)
neural network
(3)
activation quantization
(3)
vision transformer
(3)
neural architecture search
(3)
neural network optimization
(3)
large language model
(3)
representation learning
(2)
architecture search
(2)
evolutionary search
(2)
contrastive learning
(2)
self-supervised learning
(2)
efficient computing
(2)
machine translation
(2)
domain adaptation
(1)
transfer learning
(1)
Papers
MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment
ACL 2026
R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference
ICLR 2025
Efficient Track Anything
ICCV 2025
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
ICML 2025
PARQ: Piecewise-Affine Regularized Quantization
ICML 2025
SpinQuant: LLM Quantization with Learned Rotations
ICLR 2025
Param$\Delta$ for Direct Mixing: Post-Train Large Language Model At Zero Cost
ICLR 2025
Agent-as-a-Judge: Evaluate Agents with Agents
ICML 2025
Target-Aware Language Modeling via Granular Data Sampling
EMNLP 2024
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
ACL 2024
Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts
ACL 2024
Scaling Parameter-Constrained Language Models with Quality Data
EMNLP 2024
RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization
EMNLP 2024
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
ICML 2024
Binary and Ternary Natural Language Generation
ACL 2023
LLM-FP4: 4-Bit Floating-Point Quantized Transformers
EMNLP 2023
Oscillation-free Quantization for Low-bit Vision Transformers
ICML 2023
Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space
CVPR 2022
Stereo Neural Vernier Caliper
AAAI 2022
BiT: Robustly Binarized Multi-distilled Transformer
NIPS 2022
Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation
CVPR 2022
Un-mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning
AAAI 2022
Sliced Recursive Transformer
ECCV 2022
Data-Free Neural Architecture Search via Recursive Label Calibration
ECCV 2022
SDQ: Stochastic Differentiable Quantization with Mixed Precision
ICML 2022
Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning
AAAI 2021
Conditional Link Prediction of Category-Implicit Keypoint Detection
WACV 2021
How Do Adam and Training Strategies Help BNNs Optimization
ICML 2021
Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study
ICLR 2021
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-Bit Neural Networks via Guided Distribution Calibration
CVPR 2021
ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions
ECCV 2020
Binarizing MobileNet via Evolution-Based Searching
CVPR 2020
Single Path One-Shot Neural Architecture Search with Uniform Sampling
ECCV 2020
Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization
NIPS 2019
MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
ICCV 2019
Bi-Real Net: Enhancing the Performance of 1-bit CNNs with Improved Representational Capability and Advanced Training Algorithm
ECCV 2018