学者档案2022-2026
Yu Qiao
Shanghai Artificial Intelligence Laboratory
34论文数
12末位作者
88合作者人数
0一作
0独著
一作与末位作者按论文署名顺序统计,部分顶会采用姓氏字母顺序署名。
近期论文34
- Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO第 10 位,共 11 位作者ICML 2026
- An Intelligent Agentic System for Complex Image Restoration Problems第 4 位,共 5 位作者ICLR 2025
- Personalize Segment Anything Model with One Shot第 8 位,共 11 位作者ICLR 2024 · 333 次引用
- LLaMA-Adapter: Efficient Fine-tuning of Large Language Models with Zero-initialized Attention第 9 位,共 9 位作者ICLR 2024 · 174 次引用
- SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models第 17 位,共 19 位作者ICML 2024 · 149 次引用
- 4Diffusion: Multi-view Video Diffusion Model for 4D Generation第 6 位,共 7 位作者NeurIPS 2024 · 119 次引用
- Critic-Guided Decision Transformer for Offline Reinforcement Learning第 5 位,共 5 位作者AAAI 2024 · 35 次引用
- Does Video-Text Pretraining Help Open-Vocabulary Online Action Detection?第 7 位,共 8 位作者NeurIPS 2024 · 16 次引用
- Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning第 11 位,共 12 位作者NeurIPS 2024 · 10 次引用
- DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement第 3 位,共 4 位作者CVPR 2024 · 8 次引用
- ConditionVideo: Training-Free Condition-Guided Video Generation第 5 位,共 5 位作者AAAI 2024 · 7 次引用
- LLaMA-Excitor: General Instruction Tuning via Indirect Feature Interaction第 3 位,共 5 位作者CVPR 2024 · 5 次引用
- SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learning第 5 位,共 6 位作者ACL 2024 · 5 次引用
- Data Adaptive Traceback for Vision-Language Foundation Models in Image Classification第 5 位,共 5 位作者AAAI 2024 · 4 次引用
- Learning 1D Causal Visual Representation with De-focus Attention Networks第 9 位,共 11 位作者NeurIPS 2024 · 3 次引用
- Language-aware Visual Semantic Distillation for Video Question Answering第 3 位,共 5 位作者CVPR 2024 · 2 次引用
- MoPS: Modular Story Premise Synthesis for Open-Ended Automatic Story Generation第 2 位,共 3 位作者ACL 2024 · 2 次引用
- Inference-Time Language Model Alignment via Integrated Value Guidance第 5 位,共 5 位作者EMNLP Findings 2024 · 1 次引用
- Vision Transformer Adapter for Dense Predictions第 7 位,共 7 位作者ICLR 2023 · 204 次引用
- Long-Term Rhythmic Video Soundtracker第 5 位,共 5 位作者ICML 2023 · 24 次引用
- Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling第 6 位,共 6 位作者ICLR 2023 · 7 次引用
- Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translation第 6 位,共 7 位作者ACL Findings 2023 · 4 次引用
- BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision第 9 位,共 12 位作者CVPR 2023
- Bi3D: Bi-Domain Active Learning for Cross-Domain 3D Object Detection第 7 位,共 7 位作者CVPR 2023
- CO3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving第 7 位,共 9 位作者ICLR 2023
- Distilling Focal Knowledge from Imperfect Expert for 3D Object Detection第 6 位,共 8 位作者CVPR 2023
- InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions第 12 位,共 12 位作者CVPR 2023
- LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross- Modal Fusion第 10 位,共 11 位作者CVPR 2023
- Prompt, Generate, Then Cache: Cascade of Foundation Models Makes Strong Few-Shot Learners第 7 位,共 8 位作者CVPR 2023
- SCPNet: Semantic Scene Completion on Point Cloud第 8 位,共 8 位作者CVPR 2023
展示最近收录的 30 篇论文。
