Jian Liang

What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time ACL 2026 Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models? CVPR 2025 LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models CVPR 2025 Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning ICML 2025 Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning ICML 2025 Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains ICML 2025 Catch Your Emotion: Sharpening Emotion Perception in Multimodal Large Language Models ICML 2025 From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection ICML 2025 LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application AAAI 2025 Exploring Vacant Classes in Label-Skewed Federated Learning AAAI 2025 Protecting Model Adaptation from Trojans in the Unlabeled Data AAAI 2025 LoRA-Pro: Are Low-Rank Adapters Properly Optimized? ICLR 2025 Cooperative Pseudo Labeling for Unsupervised Federated Classification ICCV 2025 TAT: Task-Adaptive Transformer for All-in-One Medical Image Restoration MICCAI 2025 Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language Models ICML 2025 R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning CVPR 2025 STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay ECCV 2024 Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks ICLR 2024 Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models ICML 2024 Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization ICML 2024 Pseudo-Calibration: Improving Predictive Uncertainty Estimation in Unsupervised Domain Adaptation ICML 2024 Subjective Topic meets LLMs: Unleashing Comprehensive, Reflective and Creative Thinking through the Negation of Negation EMNLP 2024 Weight Diffusion for Future: Learn to Generalize in Non-Stationary Environments NIPS 2024 Exploring Structured Semantic Priors Underlying Diffusion Score for Test-time Adaptation NIPS 2024 Towards Reliable Model Selection for Unsupervised Domain Adaptation: An Empirical Study and A Certified Baseline NIPS 2024 Backdoor Defense via Test-Time Detecting and Repairing CVPR 2024 HORIZON: High-Resolution Semantically Controlled Panorama Synthesis AAAI 2024 CLAP: Collaborative Adaptation for Patchwork Learning ICLR 2024 A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation ICLR 2024 TALL: Thumbnail Layout for Deepfake Video Detection ICCV 2023 Mixed Samples as Probes for Unsupervised Model Selection in Domain Adaptation NIPS 2023 Improving Generalization With Domain Convex Game CVPR 2023 Mind the Label Shift of Augmentation-Based Graph OOD Generalization CVPR 2023 Informative Data Mining for One-Shot Cross-Domain Semantic Segmentation ICCV 2023 Free Lunch for Domain Adversarial Training: Environment Label Smoothing ICLR 2023 Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning ICLR 2023 Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks NIPS 2022 Contrastive Graph Structure Learning via Information Bottleneck for Recommendation NIPS 2022 Causality Inspired Representation Learning for Domain Generalization CVPR 2022 Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning CVPR 2022 DINE: Domain Adaptation From Single and Multiple Black-Box Predictors CVPR 2022 Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification ECCV 2022 NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion ECCV 2022 NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis NIPS 2022 Synergy-of-Experts: Collaborate to Improve Adversarial Robustness NIPS 2022 Domain Adaptation With Auxiliary Target Domain-Oriented Classifier CVPR 2021 Semantic Concentration for Domain Adaptation ICCV 2021 Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning NIPS 2021 Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial Examples ICLR 2021 Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning NIPS 2021 Pareto Domain Adaptation NIPS 2021 No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data NIPS 2021 Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation AAAI 2021 A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation ECCV 2020 Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation ICML 2020 Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets ACL 2019 Distant Supervised Centroid Shift: A Simple and Efficient Approach to Visual Domain Adaptation CVPR 2019 Additive Adversarial Learning for Unbiased Authentication CVPR 2019 Deep Spatial Feature Reconstruction for Partial Person Re-Identification: Alignment-Free Approach CVPR 2018 Group-Invariant Cross-Modal Subspace Learning IJCAI 2016