text embeddings
Text embeddings are vector representations of text that capture semantic meanings, enabling models to understand and process natural language in tasks such as sentiment analysis and translation.
- AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant Adversarial Patches
- Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models
- Harnessing the Universal Geometry of Embeddings
- LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders
- MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation
- Multimodal Causal Reasoning for UAV Object Detection
- RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Chest X-ray with Zero-Shot Multi-Task Capability
- Rare Text Semantics Were Always There in Your Diffusion Transformer
- Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models
- Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models