← Authors

Pu Zhao

53 papers · 2019–2025 · 13 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (10) 🧭 Keyword Pioneer 🌍 Conference Polyglot (13) πŸƒ Academic Marathon (6) 🐝 Cross-Pollinator (11) πŸ† Grand Slam 🀝 Dynamic Duo (26) πŸ”¬ Deep Specialist (15) 🧬 Topic Evolution πŸ’Ž Century Club (53) ⚑ Prolific Year (12) πŸ—ƒοΈ Keyword Collector (206) πŸ”₯ Unstoppable (7)

Conferences

EMNLP (9) IJCAI (9) AAAI (8) ICLR (7) NIPS (5) CVPR (3) ECCV (3) ICCV (3) ACL (2) ICML (1) NAACL (1) OSDI (1) WACV (1)

Top co-authors

Yanzhi Wang (26) Xue Lin (22) Qingwei Lin (21) Wei Niu (13) Zhenglun Kong (11) Zheng Zhan (11) Xuan Shen (11) Dongmei Zhang (11) Fangkai Yang (10) Changdi Yang (10)

Keywords

model compression (14) large language model (8) reinforcement learning (5) neural architecture search (5) inference acceleration (4) model pruning (4) adversarial attack (3) vision transformer (3) mobile inference (3) structured pruning (3) neural network optimization (3) bayesian optimization (3) model efficiency (3) adversarial robustness (3) retrieval-augmented generation (3) real-time inference (3) cloud computing (3) edge computing (3) black-box attack (2) resource allocation (2)

Papers

QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge CVPR 2025
AdaptFlow: Adaptive Workflow Optimization via Meta-Learning EMNLP 2025
Q-TempFusion: Quantization-Aware Temporal Multi-Sensor Fusion on Bird's-Eye View Representation WACV 2025
Token-level Proximal Policy Optimization for Query Generation EMNLP 2025
Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation EMNLP 2025
FairSMOE: Mitigating Multi-Attribute Fairness Problem with Sparse Mixture-of-Experts IJCAI 2025
Taming Diffusion for Dataset Distillation with High Representativeness ICML 2025
ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation EMNLP 2025
WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct ICLR 2025
Sparse Learning for State Space Models on Mobile ICLR 2025
Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment AAAI 2025
LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers AAAI 2025
Numerical Pruning for Efficient Autoregressive Models AAAI 2025
SELF-EVOLVED REWARD LEARNING FOR LLMS ICLR 2025
WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models ACL 2025
ICL-Bandit: Relevance Labeling in Advertisement Recommendation Systems via LLM EMNLP 2025
Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation EMNLP 2025
InstructGIE: Towards Generalizable Image Editing ECCV 2024
Fast and Memory-Efficient Video Diffusion Using Streamlined Inference NIPS 2024
Exploring Token Pruning in Vision State Space Models NIPS 2024
WizardArena: Post-training Large Language Models via Simulated Offline Chatbot Arena NIPS 2024
Search for Efficient Large Language Models NIPS 2024
DiffClass: Diffusion-Based Class Incremental Learning ECCV 2024
Rethinking Token Reduction for State Space Models EMNLP 2024
Pruning Foundation Models for High Accuracy without Retraining EMNLP 2024
WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions ICLR 2024
WizardCoder: Empowering Code Large Language Models with Evol-Instruct ICLR 2024
FasterVD: On Acceleration of Video Diffusion Models IJCAI 2024
SELF-GUARD: Empower the LLM to Safeguard Itself NAACL 2024
Pruning Parameterization With Bi-Level Optimization for Efficient Semantic Segmentation on the Edge CVPR 2023
LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Sparse Retrieval ICCV 2023
Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering EMNLP 2023
MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation ACL 2023
Towards Real-Time Segmentation on the Edge AAAI 2023
Advancing Model Pruning via Bi-level Optimization NIPS 2022
Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization IJCAI 2022
T-SMOTE: Temporal-oriented Synthetic Minority Oversampling Technique for Imbalanced Time Series Classification IJCAI 2022
Learning to Generate Image Source-Agnostic Universal Adversarial Perturbations IJCAI 2022
Compiler-Aware Neural Architecture Search for On-Mobile Real-Time Super-Resolution ECCV 2022
NPAS: A Compiler-Aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration CVPR 2021
Achieving On-Mobile Real-Time Super-Resolution With Neural Architecture and Pruning Search ICCV 2021
Correlation-Aware Heuristic Search for Intelligent Virtual Machine Provisioning in Cloud Systems AAAI 2021
PULNS: Positive-Unlabeled Learning with Effective Negative Sample Selector AAAI 2021
Characteristic Examples: High-Robustness, Low-Transferability Fingerprinting of Neural Networks IJCAI 2021
A Compression-Compilation Framework for On-mobile Real-time BERT Applications IJCAI 2021
Towards Real-Time DNN Inference on Mobile Platforms with Model Pruning and Compiler Optimization IJCAI 2020
Intelligent Virtual Machine Provisioning in Cloud Computing IJCAI 2020
Towards Certificated Model Robustness Against Weight Perturbations AAAI 2020
Predictive and Adaptive Failure Mitigation to Avert Production Cloud VM Interruptions OSDI 2020
Towards Query-Efficient Black-Box Adversary with Zeroth-Order Natural Gradient Descent AAAI 2020
Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness ICLR 2020
Structured Adversarial Attack: Towards General Implementation and Better Interpretability ICLR 2019
On the Design of Black-Box Adversarial Examples by Leveraging Gradient-Free Optimization and Operator Splitting Method ICCV 2019