semantic similarity
A measure of how alike two pieces of text or data are in meaning. In AI, it is often used in natural language processing to determine the closeness of concepts or contexts.
- CoUn: Empowering Machine Unlearning via Contrastive Learning
- Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention
- Feedback-Aware MCTS for Goal-Oriented Information Seeking
- InstructSAM: A Training-free Framework for Instruction-Oriented Remote Sensing Object Recognition
- Inv-Entropy: A Fully Probabilistic Framework for Uncertainty Quantification in Language Models
- Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale
- Learning Human-Object Interaction as Groups
- On the Emergence of Linear Analogies in Word Embeddings
- One-Step Offline Distillation of Diffusion-based Models via Koopman Modeling
- Semantic-KG: Using Knowledge Graphs to Construct Benchmarks for Measuring Semantic Similarity
- Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
- VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set