From the 1 of 5 linked papers with an AI index.
5 papers
AspectCLIP: Optimizing CLIP Representation Space via Aspect-Guided Consistency Regularization
Yiyang Yao, Shanglin Liu, Jianming Lv +4
The paper introduces AspectCLIP, a method that groups image-text pairs by shared textual aspects and applies consistency regularization within these groups to avoid forcing unrelat…
SEAM: Smooth Execution of Action-Chunked Motion for Vision-Language-Action Policies
Dijia Zhan, Xuemiao Xu, Jinyi Li +1
Vision-Language-Action (VLA) policies that execute fixed-length action chunks can exhibit multimodal bifurcation: a cross-chunk inconsistency in which adjacent chunks generated fro…
NavOne: One-Step Global Planning for Vision-Language Navigation on Top-Down Maps
Dijia Zhan, Jinyi Li, Chenxi Zheng +4
Existing Vision-Language Navigation (VLN) methods typically adopt an egocentric, step-by-step paradigm, which struggles with error accumulation and limits efficiency. While recent…
Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification
Tuo Xiang, Xuemiao Xu, Bangzhen Liu +3
The rapid growth of 3D digital content necessitates expandable recognition systems for open-world scenarios. However, existing 3D class-incremental learning methods struggle under…
An Empirical Study on Prompt Compression for Large Language Models
Zheng Zhang, Jinyi Li, Yihuai Lan +2
Prompt engineering enables Large Language Models (LLMs) to perform a variety of tasks. However, lengthy prompts significantly increase computational complexity and economic costs.…