Ying Wei

Detecting What Queries Seek: Steering LLM Safety with FFN Output Activation Monitoring ACL 2026 SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning ICLR 2025 CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models ICLR 2025 What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning EMNLP 2025 Improving Alignment in LVLMs with Debiased Self-Judgment EMNLP 2025 Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation ICML 2025 CREAM: Consistency Regularized Self-Rewarding Language Models ICLR 2025 Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning ICLR 2025 Reaction Graph: Towards Reaction-Level Modeling for Chemical Reactions with 3D Structures ICML 2025 Automatic Expert Discovery in LLM Upcycling via Sparse Interpolated Mixture-of-Experts ACL 2025 Learning Visual Generative Priors without Text CVPR 2025 Anyprefer: An Agentic Framework for Preference Data Synthesis ICLR 2025 Mixture of Adversarial LoRAs: Boosting Robust Generalization in Meta-Tuning NIPS 2024 Learning Where to Edit Vision Transformers NIPS 2024 Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations via Pareto Optimization ICML 2024 Federated Continual Learning via Prompt-based Dual Knowledge Transfer ICML 2024 Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts ICML 2024 RetroOOD: Understanding Out-of-Distribution Generalization in Retrosynthesis Prediction AAAI 2024 One Meta-tuned Transformer is What You Need for Few-shot Learning ICML 2024 Gradual Domain Adaptation via Gradient Flow ICLR 2024 Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction ICLR 2024 Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing EMNLP 2024 Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation ACL 2024 Understanding and Patching Compositional Reasoning in LLMs ACL 2024 MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric CVPR 2024 Active Retrosynthetic Planning Aware of Route Quality ICLR 2024 Time-Varying LoRA: Towards Effective Cross-Domain Fine-Tuning of Diffusion Models NIPS 2024 DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs NIPS 2024 ScdNER: Span-Based Consistency-Aware Document-Level Named Entity Recognition EMNLP 2023 Does Continual Learning Meet Compositionality? New Benchmarks and An Evaluation Framework NIPS 2023 Secure Out-of-Distribution Task Generalization with Energy-Based Models NIPS 2023 Learning Chemical Rules of Retrosynthesis with Pre-training AAAI 2023 Learning to Substitute Spans towards Improving Compositional Generalization ACL 2023 Wasserstein Distributional Learning via Majorization-Minimization AISTATS 2023 Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective CVPR 2023 CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detection CVPR 2023 Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompts EMNLP 2023 Concept-wise Fine-tuning Matters in Preventing Negative Transfer ICCV 2023 Audio-Visual Fusion using Multiscale Temporal Convolutional Attention for Time-Domain Speech Separation INTERSPEECH 2023 Disentangling Task Relations for Few-shot Text Classification via Self-Supervised Hierarchical Task Clustering EMNLP 2022 Frustratingly Easy Transferability Estimation ICML 2022 The Role of Deconfounding in Meta-learning ICML 2022 Adversarial Task Up-sampling for Meta-learning NIPS 2022 GRASP: Navigating Retrosynthetic Planning with Goal-driven Policy NIPS 2022 Improving Task-Specific Generalization in Few-Shot Learning via Adaptive Vicinal Risk Minimization NIPS 2022 MetaTS: Meta Teacher-Student Network for Multilingual Sequence Labeling with Minimal Supervision EMNLP 2021 Functionally Regionalized Knowledge Transfer for Low-resource Drug Discovery NIPS 2021 Meta-learning Hyperparameter Performance Prediction with Neural Processes ICML 2021 Improving Generalization in Meta-learning via Task Augmentation ICML 2021 Meta-learning with an Adaptive Task Scheduler NIPS 2021 Learn to Cross-lingual Transfer with Meta Graph Learning Across Heterogeneous Languages EMNLP 2020 Graph Few-Shot Learning via Knowledge Transfer AAAI 2020 Self-Supervised Graph Transformer on Large-Scale Molecular Data NIPS 2020 Adversarial Sparse Transformer for Time Series Forecasting NIPS 2020 Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning IJCNLP 2019 Exploiting Coarse-to-Fine Task Transfer for Aspect-Level Sentiment Classification AAAI 2019 Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning EMNLP 2019 Hierarchically Structured Meta-learning ICML 2019 Learning to Multitask NIPS 2018 Transfer Learning via Learning to Transfer ICML 2018 Deep Neural Networks for High Dimension, Low Sample Size Data IJCAI 2017 End-to-End Adversarial Memory Network for Cross-domain Sentiment Classification IJCAI 2017