Wei Zhu

Dissecting Failure Dynamics in Large Language Model Reasoning ACL 2026 DynamicFace: High-Quality and Consistent Face Swapping for Image and Video using Composable 3D Facial Priors ICCV 2025 HierPrompt: Zero-Shot Hierarchical Text Classification with LLM-Enhanced Prototypes EMNLP 2025 AMAS: Adaptively Determining Communication Topology for LLM-based Multi-agent System EMNLP 2025 FT-MDT: Extracting Decision Trees from Medical Texts via a Novel Low-rank Adaptation Method EMNLP 2025 SMTPD: A New Benchmark for Temporal Prediction of Social Media Popularity CVPR 2025 DRUM: Learning Demonstration Retriever for Large MUlti-modal Models ACL 2025 Time-LlaMA: Adapting Large Language Models for Time Series Modeling via Dynamic Low-rank Adaptation ACL 2025 Low-Rank Continual Pyramid Vision Transformer: Incrementally Segment Whole-Body Organs in CT with Light-Weighted Adaptation MICCAI 2024 IAPT: Instance-Aware Prompt Tuning for Large Language Models ACL 2024 FanLoRA: Fantastic LoRAs and Where to Find Them in Large Language Model Fine-tuning EMNLP 2024 PARA: Parameter-Efficient Fine-tuning with Prompt-Aware Representation Adjustment EMNLP 2024 SCA: Selective Compression Attention for Efficiently Extending the Context Window of Large Language Models EMNLP 2024 MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning EMNLP 2024 ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback ICML 2024 DiffVC+: Improving Diffusion-based Voice Conversion for Speaker Anonymization INTERSPEECH 2024 ALoRA: Allocating Low-Rank Adaptation for Fine-tuning Large Language Models NAACL 2024 LECO: Improving Early Exiting via Learned Exits and Comparison-based Exiting Mechanism ACL 2023 On the Implicit Bias of Linear Equivariant Steerable Networks NIPS 2023 Sample Complexity of Probability Divergences under Group Symmetry ICML 2023 Learned Adapters Are Better Than Manually Designed Adapters ACL 2023 NAG-NER: a Unified Non-Autoregressive Generation Framework for Various NER Tasks ACL 2023 Unified Demonstration Retriever for In-Context Learning ACL 2023 SPT: Learning to Selectively Insert Prompts for Better Prompt Tuning EMNLP 2023 BADGE: Speeding Up BERT Inference after Deployment via Block-wise Bypasses and Divergence-based Early Exiting ACL 2023 SegPrompt: Using Segmentation Map as a Better Prompt to Finetune Deep Models for Kidney Stone Classification MIDL 2023 Continually Detection, Rapidly React: Unseen Rumors Detection Based on Continual Prompt-Tuning COLING 2022 Localized Adversarial Domain Generalization CVPR 2022 Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translation EMNLP 2022 Structure-preserving GANs ICML 2022 PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early Exiting NAACL 2022 Scaling-Translation-Equivariant Networks with Decomposed Convolutional Filters JMLR 2022 A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation ACL 2022 AutoRC: Improving BERT Based Relation Classification Models via Architecture Search ACL 2021 LeeBERT: Learned Early Exit for BERT with cross-level optimization ACL 2021 Global Attention Decoder for Chinese Spelling Error Correction ACL 2021 LeeBERT: Learned Early Exit for BERT with cross-level optimization IJCNLP 2021 AutoRC: Improving BERT Based Relation Classification Models via Architecture Search IJCNLP 2021 MVP-BERT: Multi-Vocab Pre-training for Chinese BERT IJCNLP 2021 Global Attention Decoder for Chinese Spelling Error Correction IJCNLP 2021 paht_nlp @ MEDIQA 2021: Multi-grained Query Focused Multi-Answer Summarization NAACL 2021 Discovering Better Model Architectures for Medical Query Understanding NAACL 2021 Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization ICCV 2021 GAML-BERT: Improving BERT Early Exiting by Gradient Aligned Mutual Learning EMNLP 2021 MVP-BERT: Multi-Vocab Pre-training for Chinese BERT ACL 2021 PANLP at MEDIQA 2019: Pre-trained Language Models, Transfer Learning and Knowledge Distillation ACL 2019 Pingan Smart Health and SJTU at COIN - Shared Task: utilizing Pre-trained Language Models and Common-sense Knowledge in Machine Reading Tasks EMNLP 2019 Deep Neural Nets with Interpolating Function as Output Activation NIPS 2018 LDMNet: Low Dimensional Manifold Regularized Neural Networks CVPR 2018