Shiyu Chang

A Reinforcement Learning Framework for Robust and Secure LLM Watermarking EACL 2026 VSP: Diagnosing the Dual Challenges of Perception and Reasoning in Spatial Planning Tasks for MLLMs ICCV 2025 Augment before You Try: Knowledge-Enhanced Table Question Answering via Table Expansion EMNLP 2025 Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing IJCNLP 2025 Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning ICLR 2025 Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing AACL 2025 Instruction-Following Pruning for Large Language Models ICML 2025 A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation NAACL 2025 Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference NIPS 2024 Revisiting Who’s Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective EMNLP 2024 Correcting Diffusion Generation through Resampling CVPR 2024 Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once ICML 2024 Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling ICML 2024 Speech Self-Supervised Learning Using Diffusion Model Synthetic Data ICML 2024 Advancing the Robustness of Large Language Models through Self-Denoised Smoothing NAACL 2024 GeSS: Benchmarking Geometric Deep Learning under Scientific Applications with Distribution Shifts NIPS 2024 PromptBoosting: Black-Box Text Classification with Ten Forward Passes ICML 2023 Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models ICML 2023 TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization ICLR 2023 Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning NIPS 2023 Robust Mixture-of-Expert Training for Convolutional Neural Networks ICCV 2023 Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis ICCV 2023 Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models CVPR 2023 Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection COLING 2022 Fairness Reprogramming NIPS 2022 An Adversarial Framework for Generating Unseen Images by Activation Maximization AAAI 2022 Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding ACL 2022 Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free CVPR 2022 Optimizer Amalgamation ICLR 2022 Adversarial Support Alignment ICLR 2022 How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective ICLR 2022 Learning Stable Classifiers by Transferring Unstable Features ICML 2022 Data-Efficient Double-Win Lottery Tickets from Robust Pre-training ICML 2022 Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness ICML 2022 ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers ICML 2022 Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization ICML 2022 Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition INTERSPEECH 2022 WavPrompt: Towards Few-Shot Spoken Language Understanding with Frozen Language Models INTERSPEECH 2022 DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings NAACL 2022 Zero-Shot Cross-Lingual Phonetic Recognition with External Language Embedding INTERSPEECH 2021 The Lottery Tickets Hypothesis for Supervised and Self-Supervised Pre-Training in Computer Vision Models CVPR 2021 TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up NIPS 2021 PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition NIPS 2021 Self-Progressing Robust Training AAAI 2021 Robust Overfitting may be mitigated by properly learned smoothening ICLR 2021 Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning ICLR 2021 Generating Adversarial Computer Programs using Optimized Obfuscations ICLR 2021 Complementary Evidence Identification in Open-Domain Question Answering EACL 2021 Understanding Interlocking Dynamics of Cooperative Rationalization NIPS 2021 Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers ICML 2021 Global Prosody Style Transfer Without Text Transcriptions ICML 2021 Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning EMNLP 2020 Few-shot Text Classification with Distributional Signatures ICLR 2020 Training Stronger Baselines for Learning to Optimize NIPS 2020 Proper Network Interpretability Helps Adversarial Robustness in Classification ICML 2020 Invariant Rationalization ICML 2020 Unsupervised Speech Decomposition via Triple Information Bottleneck ICML 2020 The Lottery Ticket Hypothesis for Pre-trained BERT Networks NIPS 2020 Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning CVPR 2020 Out-of-Domain Detection for Low-Resource Text Classification Tasks IJCNLP 2019 Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control EMNLP 2019 Context-Aware Conversation Thread Detection in Multi-Party Chat EMNLP 2019 Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering EMNLP 2019 TWEETQA: A Social Media Focused Question Answering Dataset ACL 2019 AutoGAN: Neural Architecture Search for Generative Adversarial Networks ICCV 2019 Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets ACL 2019 Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader ACL 2019 Self-Supervised Learning for Contextualized Extractive Summarization ACL 2019 Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers NIPS 2019 Extracting Multiple-Relations in One-Pass with Pre-Trained Transformers ACL 2019 AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss ICML 2019 A Game Theoretic Approach to Class-wise Selective Rationalization NIPS 2019 Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing NAACL 2019 Sentence Embedding Alignment for Lifelong Relation Extraction NAACL 2019 Hybrid Reinforcement Learning with Expert State Sequences AAAI 2019 Out-of-Domain Detection for Low-Resource Text Classification Tasks EMNLP 2019 Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control IJCNLP 2019 Context-Aware Conversation Thread Detection in Multi-Party Chat IJCNLP 2019 Additive Adversarial Learning for Unbiased Authentication CVPR 2019 Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering ICLR 2018 Scheduled Policy Optimization for Natural Language Communication with Intelligent Agents IJCAI 2018 A Co-Matching Model for Multi-choice Reading Comprehension ACL 2018 Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization NIPS 2018 Improving Reinforcement Learning Based Image Captioning with Natural Language Prior EMNLP 2018 Deriving Machine Attention from Human Rationales EMNLP 2018 Diverse Few-Shot Text Classification with Multiple Metrics NAACL 2018 Image Super-Resolution via Dual-State Recurrent Networks CVPR 2018 One-Shot Relational Learning for Knowledge Graphs EMNLP 2018 Speech Enhancement Using Bayesian Wavenet INTERSPEECH 2017 Dilated Recurrent Neural Networks NIPS 2017 Jointly Attentive Spatial-Temporal Pooling Networks for Video-Based Person Re-Identification ICCV 2017 Robust Video Super-Resolution With Learned Temporal Dynamics ICCV 2017 D3: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images CVPR 2016 Studying Very Low Resolution Recognition Using Deep Networks CVPR 2016 A Joint Optimization Framework of Sparse Coding and Discriminative Clustering IJCAI 2015 A Space Alignment Method for Cold-Start TV Show Recommendations IJCAI 2015 Learning Locally-Adaptive Decision Functions for Person Verification CVPR 2013