Yifan Zhang

DriveFlow: Rectified Flow Adaptation for Robust 3D Object Detection in Autonomous Driving AAAI 2026 PersonaVLM: Long-Term Personalized Multimodal LLMs CVPR 2026 Scaling Law for Multimodal Large Language Model Supervised Fine-Tuning ACL 2026 Towards Human-Like Robot Handwriting via Contour-Aware Generation CVPR 2026 AI-Driven Virtual Teacher for Enhanced Educational Efficiency: Leveraging Large Pretrain Models for Autonomous Error Analysis and Correction AAAI 2025 Beyond Isolated Words: Diffusion Brush for Handwritten Text-Line Generation ICCV 2025 DAMA: Data- and Model-aware Alignment of Multi-modal LLMs ICML 2025 DriveGEN: Generalized and Robust 3D Detection in Driving via Controllable Text-to-Image Diffusion Generation CVPR 2025 Learning to Extrapolate and Adjust: Two-Stage Meta-Learning for Concept Drift in Online Time Series Forecasting IJCAI 2025 MEGA: Memory-Efficient 4D Gaussian Splatting for Dynamic Scenes ICCV 2025 MM-RLHF: The Next Step Forward in Multimodal LLM Alignment ICML 2025 MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans? ICLR 2025 Poison-splat: Computation Cost Attack on 3D Gaussian Splatting ICLR 2025 TopNet: Transformer-Efficient Occupancy Prediction Network for Octree-Structured Point Cloud Geometry Compression CVPR 2025 Implicit Concept Removal of Diffusion Models ECCV 2024 MonoTTA: Fully Test-Time Adaptation for Monocular 3D Object Detection ECCV 2024 One-Shot Diffusion Mimicker for Handwritten Text Generation ECCV 2024 Position: What Can Large Language Models Tell Us about Time Series Analysis ICML 2024 AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation ICML 2023 Dataset Quantization ICCV 2023 Disentangling Writer and Character Styles for Handwriting Generation CVPR 2023 Expanding Small-Scale Datasets with Guided Imagination NeurIPS 2023 Free Lunch for Domain Adversarial Training: Environment Label Smoothing ICLR 2023 OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling NeurIPS 2023 Towards Stable Test-time Adaptation in Dynamic Wild World ICLR 2023 Efficient Test-Time Model Adaptation without Forgetting ICML 2022 How Well Does Self-Supervised Pre-Training Perform with Streaming Data? ICLR 2022 Not All Points Are Equal: Learning Highly Efficient Point-Based Detectors for 3D LiDAR Point Clouds CVPR 2022 Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation ECCV 2022 Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition NeurIPS 2022 AdaXpert: Adapting Neural Architecture for Growing Data ICML 2021 No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data NeurIPS 2021 Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation IJCAI 2021 Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning NeurIPS 2021 Relation-Aware Transformer for Portfolio Policy Learning IJCAI 2020 Multi-marginal Wasserstein GAN NeurIPS 2019 Leveraging Multiple Domains for Sentiment Classification COLING 2016