Zhenhua Liu
19 papers · 2016–2026 · 9 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 ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (39) π Academic Marathon Β· Half π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π§¬
Topic Evolution
π
Keyword Champion
ποΈ
Keyword Collector
(81)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
π
Renaissance Researcher
(6)
Top co-authors
Research topics
Artificial Intelligence
(10)
Deep Learning
(9)
Machine Learning
(9)
Core AI
(8)
Natural Language Processing
(5)
Application Areas
(5)
Architectures
(4)
Resources & Methods
(4)
Learning Types Β· Deep Learning
(3)
Learning Types Β· Machine Learning
(3)
Techniques
(3)
Computer Vision
(2)
Optimization & Theory
(2)
Computer Science
(1)
Data Science & Analytics
(1)
Keywords
large language model
(5)
inference acceleration
(3)
speculative decoding
(2)
diffusion model
(2)
model compression
(2)
benchmark evaluation
(1)
model probing
(1)
transformer architecture
(1)
transfer learning
(1)
variational inference
(1)
image restoration
(1)
question answering
(1)
dialogue generation
(1)
information retrieval
(1)
post-training quantization
(1)
factual knowledge
(1)
supervised learning
(1)
self-attention mechanism
(1)
network pruning
(1)
text summarization
(1)
Papers
Double Rounding: Nearly Lossless Adaptive Bit Switching for QAT
AAAI 2026
Evolutionary Guided Decoding: Iterative Value Refinement for LLMs
ACL 2026
Jakiro: Boosting Speculative Decoding via Decoupled MoE
ACL 2026
Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models
AAAI 2026
Learning to Refuse: Towards Mitigating Privacy Risks in LLMs
COLING 2025
UAQFact: Evaluating Factual Knowledge Utilization of LLMs on Unanswerable Questions
ACL 2025
DiffusionDialog: A Diffusion Model for Diverse Dialog Generation with Latent Space
COLING 2024
Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting
NeurIPS 2024
Probing Language Models for Pre-training Data Detection
ACL 2024
Applied Online Algorithms with Heterogeneous Predictors
ICML 2023
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
ICCV 2023
Instance-Aware Dynamic Neural Network Quantization
CVPR 2022
P-STMO: Pre-trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation
ECCV 2022
Tencent-MVSE: A Large-Scale Benchmark Dataset for Multi-Modal Video Similarity Evaluation
CVPR 2022
LICHEE: Improving Language Model Pre-training with Multi-grained Tokenization
ACL 2021
Post-Training Quantization for Vision Transformer
NeurIPS 2021
Pre-Trained Image Processing Transformer
CVPR 2021
Frequency-Domain Dynamic Pruning for Convolutional Neural Networks
NeurIPS 2018
HUG: Multi-Resource Fairness for Correlated and Elastic Demands
NSDI 2016