Qianru Sun

History to Future: Evolving Agent with Experience and Thought for Zero-shot Vision-and-Language Navigation CVPR 2026 3D Question Answering via only 2D Vision-Language Models ICML 2025 Frame-Voyager: Learning to Query Frames for Video Large Language Models ICLR 2025 Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning CVPR 2025 Reverse Modeling in Large Language Models NAACL 2025 Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization ICCV 2025 Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models NeurIPS 2024 Exploring Diffusion Time-steps for Unsupervised Representation Learning ICLR 2024 Few-shot Learner Parameterization by Diffusion Time-steps CVPR 2024 Learning De-Biased Representations for Remote-Sensing Imagery NeurIPS 2024 LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement EMNLP 2024 Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration NeurIPS 2024 Unified Generative and Discriminative Training for Multi-modal Large Language Models NeurIPS 2024 Unleashing Network Potentials for Semantic Scene Completion CVPR 2024 Wakening Past Concepts Without Past Data: Class-Incremental Learning From Online Placebos WACV 2024 Class-Incremental Exemplar Compression for Class-Incremental Learning CVPR 2023 Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection ICLR 2023 Extracting Class Activation Maps From Non-Discriminative Features As Well CVPR 2023 Freestyle Layout-to-Image Synthesis CVPR 2023 Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models NeurIPS 2023 Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition ICCV 2023 Make the U in UDA Matter: Invariant Consistency Learning for Unsupervised Domain Adaptation NeurIPS 2023 Online Hyperparameter Optimization for Class-Incremental Learning AAAI 2023 Semantic Scene Completion With Cleaner Self CVPR 2023 Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection CVPR 2023 Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-of-Distribution Generalization ECCV 2022 Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation CVPR 2022 Deconfounded Visual Grounding AAAI 2022 Equivariance and Invariance Inductive Bias for Learning from Insufficient Data ECCV 2022 Interventional Training for Out-Of-Distribution Natural Language Understanding EMNLP 2022 On Mitigating Hard Clusters for Face Clustering ECCV 2022 Translate-Train Embracing Translationese Artifacts ACL 2022 Adaptive Aggregation Networks for Class-Incremental Learning CVPR 2021 Causal Attention for Unbiased Visual Recognition ICCV 2021 COSY: COunterfactual SYntax for Cross-Lingual Understanding ACL 2021 Counterfactual Zero-Shot and Open-Set Visual Recognition CVPR 2021 RMM: Reinforced Memory Management for Class-Incremental Learning NeurIPS 2021 Self-Regulation for Semantic Segmentation ICCV 2021 Self-Supervised Learning Disentangled Group Representation as Feature NeurIPS 2021 Transporting Causal Mechanisms for Unsupervised Domain Adaptation ICCV 2021 An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning ECCV 2020 Causal Intervention for Weakly-Supervised Semantic Segmentation NeurIPS 2020 Feature Pyramid Transformer ECCV 2020 Interventional Few-Shot Learning NeurIPS 2020 Mnemonics Training: Multi-Class Incremental Learning Without Forgetting CVPR 2020 Teacher-Student Networks with Multiple Decoders for Solving Math Word Problem IJCAI 2020 Visual Commonsense R-CNN CVPR 2020 Learning to Self-Train for Semi-Supervised Few-Shot Classification NeurIPS 2019 Meta-Transfer Learning for Few-Shot Learning CVPR 2019 A Hybrid Model for Identity Obfuscation by Face Replacement ECCV 2018 Disentangled Person Image Generation CVPR 2018 Natural and Effective Obfuscation by Head Inpainting CVPR 2018 A Domain Based Approach to Social Relation Recognition CVPR 2017 Pose Guided Person Image Generation NeurIPS 2017