Shiqi Wang

DeepRAHT: Learning Predictive RAHT for Point Cloud Attribute Compression AAAI 2026 TIGER: Text-Informed Generalized Enzyme-Reaction Retrieval ACL 2026 When Privacy Meets Recovery: The Overlooked Half of Surrogate-Driven Privacy Preservation for MLLM Editing AAAI 2026 Planning-Aware Code Infilling via Horizon-Length Prediction EMNLP 2025 Making Old Film Great Again: Degradation-aware State Space Model for Old Film Restoration CVPR 2025 Q-PART: Quasi-Periodic Adaptive Regression with Test-time Training for Pediatric Left Ventricular Ejection Fraction Regression CVPR 2025 An Information-Theoretic Regularizer for Lossy Neural Image Compression ICCV 2025 Joint Semantic and Rendering Enhancements in 3D Gaussian Modeling with Anisotropic Local Encoding ICCV 2025 PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification ICML 2025 AI-generated Image Quality Assessment in Visual Communication AAAI 2025 Unified Coding for Both Human Perception and Generalized Machine Analytics with CLIP Supervision AAAI 2025 Speed Master: Quick or Slow Play to Attack Speaker Recognition AAAI 2025 MR-FIQA: Face Image Quality Assessment with Multi-Reference Representations from Synthetic Data Generation ICCV 2025 Test-time Adaptation for Image Compression with Distribution Regularization ICLR 2025 MicroEdit: Neuron-level Knowledge Disentanglement and Localization in Lifelong Model Editing EMNLP 2025 daDPO: Distribution-Aware DPO for Distilling Conversational Abilities ACL 2025 Generating Commonsense Reasoning Questions with Controllable Complexity through Multi-step Structural Composition COLING 2025 Reward Difference Optimization For Sample Reweighting In Offline RLHF EMNLP 2024 Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare NIPS 2024 LeDex: Training LLMs to Better Self-Debug and Explain Code NIPS 2024 DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor NIPS 2024 Mitigating the Impact of False Negative in Dense Retrieval with Contrastive Confidence Regularization AAAI 2024 Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models ACL 2024 Token Alignment via Character Matching for Subword Completion ACL 2024 CLIB-FIQA: Face Image Quality Assessment with Confidence Calibration CVPR 2024 PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling CVPR 2024 Towards Open-ended Visual Quality Comparison ECCV 2024 Unrolled Decomposed Unpaired Learning for Controllable Low-Light Video Enhancement ECCV 2024 Multimodal Clickbait Detection by De-confounding Biases Using Causal Representation Inference EMNLP 2024 CodeFort: Robust Training for Code Generation Models EMNLP 2024 Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization ICLR 2024 ScreenAgent: A Vision Language Model-driven Computer Control Agent IJCAI 2024 ReTA: Recursively Thinking Ahead to Improve the Strategic Reasoning of Large Language Models NAACL 2024 Are Diffusion Models Vulnerable to Membership Inference Attacks? ICML 2023 Generating Deep Questions with Commonsense Reasoning Ability from the Text by Disentangled Adversarial Inference ACL 2023 Troubleshooting Ethnic Quality Bias with Curriculum Domain Adaptation for Face Image Quality Assessment ICCV 2023 ReCode: Robustness Evaluation of Code Generation Models ACL 2023 Multi-lingual Evaluation of Code Generation Models ICLR 2023 ScanDMM: A Deep Markov Model of Scanpath Prediction for 360deg Images CVPR 2023 Optimization-Inspired Cross-Attention Transformer for Compressive Sensing CVPR 2023 A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU Networks ICML 2022 Rethinking Attention-Model Explainability through Faithfulness Violation Test ICML 2022 Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder ICML 2022 General Cutting Planes for Bound-Propagation-Based Neural Network Verification NIPS 2022 Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers ICLR 2021 Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification NIPS 2021 Adaptive Verifiable Training Using Pairwise Class Similarity AAAI 2021 HYDRA: Pruning Adversarially Robust Neural Networks NIPS 2020 Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization NIPS 2020 Towards Scale-Free Rain Streak Removal via Self-Supervised Fractal Band Learning AAAI 2020 ARMA Nets: Expanding Receptive Field for Dense Prediction NIPS 2020 From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement CVPR 2020 Self-Learning Video Rain Streak Removal: When Cyclic Consistency Meets Temporal Correspondence CVPR 2020 Self-Critical N-Step Training for Image Captioning CVPR 2019 Learning to Explore Intrinsic Saliency for Stereoscopic Video CVPR 2019 VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the Wild CVPR 2019 Domain Generalization With Adversarial Feature Learning CVPR 2018 Efficient Formal Safety Analysis of Neural Networks NIPS 2018