Xu Yang

Adaptive-Learngene: Continual Expansion and Task-Aware Selection of Learngenes for Dynamic Environments AAAI 2026 Breaking Semantic Boundaries: Distribution-Guided Semantic Exploration for Creative Generation CVPR 2026 Efficient and Effective In-context Demonstration Selection with Coreset AAAI 2026 Extracting Multimodal Learngene in CLIP: Unveiling the Multimodal Generalizable Knowledge AAAI 2026 GraphIC: A Graph-Based In-Context Example Retrieval Model for Multi-Step Reasoning AAAI 2026 Learngene: Inheritable ‘Genes’ in Intelligent Agents (Abstract Reprint) AAAI 2026 TVHighlights: LLM-Guided Human-Free Collaborative Training for Video Highlight Detection in Movies and TV Dramas CVPR 2026 Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens CVPR 2025 Fast Large Language Model Collaborative Decoding via Speculation ICML 2025 Inheriting Generalized Learngene for Efficient Knowledge Transfer across Multiple Tasks AAAI 2025 Learngene Tells You How to Customize: Task-Aware Parameter Initialization at Flexible Scales ICML 2025 Mimic In-Context Learning for Multimodal Tasks CVPR 2025 Number it: Temporal Grounding Videos like Flipping Manga CVPR 2025 Redefining <Creative> in Dictionary: Towards an Enhanced Semantic Understanding of Creative Generation CVPR 2025 Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient AAAI 2025 Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark AAAI 2025 Building Variable-Sized Models via Learngene Pool AAAI 2024 Cluster-Learngene: Inheriting Adaptive Clusters for Vision Transformers NeurIPS 2024 Exploring Learngene via Stage-wise Weight Sharing for Initializing Variable-sized Models IJCAI 2024 How to Configure Good In-Context Sequence for Visual Question Answering CVPR 2024 Initializing Variable-sized Vision Transformers from Learngene with Learnable Transformation NeurIPS 2024 LIVE: Learnable In-Context Vector for Visual Question Answering NeurIPS 2024 Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models NeurIPS 2024 Linearly Decomposing and Recomposing Vision Transformers for Diverse-Scale Models NeurIPS 2024 Transformer as Linear Expansion of Learngene AAAI 2024 Vision Transformers as Probabilistic Expansion from Learngene ICML 2024 Exploring Diverse In-Context Configurations for Image Captioning NeurIPS 2023 Learning From Biased Soft Labels NeurIPS 2023 Learning Trajectory-Word Alignments for Video-Language Tasks ICCV 2023 Transforming Visual Scene Graphs to Image Captions ACL 2023 EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching CVPR 2022 Auto-Parsing Network for Image Captioning and Visual Question Answering ICCV 2021 Causal Attention for Vision-Language Tasks CVPR 2021 Finding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change Captioning ECCV 2020 Learning Progressive Joint Propagation for Human Motion Prediction ECCV 2020 Auto-Encoding Scene Graphs for Image Captioning CVPR 2019 Learning to Collocate Neural Modules for Image Captioning ICCV 2019 Unpaired Image Captioning via Scene Graph Alignments ICCV 2019 Shuffle-Then-Assemble: Learning Object-Agnostic Visual Relationship Features ECCV 2018 Sparsity Conditional Energy Label Distribution Learning for Age Estimation IJCAI 2016