Peng Gao
11 papers · 4 citations
Most-cited papers
- Uniformer: Unifying Convolution And Self-attention For Visual Recognition2022 · 541 citations
- Omniquant: Omnidirectionally Calibrated Quantization For Large Language Models2023 · 385 citations
- Fast Convergence Of DETR With Spatially Modulated Co-attention2021 · 335 citations
- Tip-adapter: Training-free Adaption Of CLIP For Few-shot Classification2022 · 310 citations
- SPHINX: The Joint Mixing Of Weights, Tasks, And Visual Embeddings For Multi-modal Large Language Models2023 · 288 citations
- Frozen CLIP Models Are Efficient Video Learners2022 · 168 citations
- Adaptive Markup Language Generation For Contextually-grounded Visual Document Understanding2025 · 1 citations
- Spatial Preference Rewarding For Mllms Spatial Understanding2025
Topics