4 citations · 4 across the 3 of their papers we have counts for
4 papers
From Observation to Intervention: Distilling Self-Generated In-Context Demonstrations via Executable Causal Intervention
Minming Ye, Min Liu, Haoang Chi +2
Self-generated In-Context Learning (ICL) enables LLMs to synthesize their own few-shot demonstrations, often outperforming manual prompts. However, existing methods filter demonstr…
Accelerating Rectified Flow Models via Trajectory-Aware Caching
Xiao Liu, Kai Liu, Naiyang Guan +5
Diffusion and rectified flow (RF) models generate high-fidelity images and videos, but their iterative velocity-field evaluations are computationally expensive. Existing caching me…
MVP: Meta Visual Prompt Tuning for Few-Shot Remote Sensing Image Scene Classification
Junjie Zhu, Yiying Li, Chunping Qiu +3
Vision Transformer (ViT) models have recently emerged as powerful and versatile models for various visual tasks. Recently, a work called PMF has achieved promising results in few-s…
LPN: Language-guided Prototypical Network for few-shot classification
Kaihui Cheng, Chule Yang, Xiao Liu +2
Few-shot classification aims to adapt to new tasks with limited labeled examples. To fully use the accessible data, recent methods explore suitable measures for the similarity betw…