Tag
SeLMRoute introduces an LLM routing framework that separates candidate-independent semantic evidence extraction from performance learning, achieving 72.08% average accuracy on LLMRouterBench across 15 datasets and 20 candidate models, outperforming the strongest fixed candidate (69.23%) and enabling both performance-oriented and cost-aware routing decisions.
V-RAE proposes a video representation autoencoder that builds semantically organized latents from frozen vision representations to enhance video generation quality, convergence speed, and predictive modeling.
This paper introduces the concept and architecture of a Business World Model (BWM), a specialized world model for business environments that encodes states, dynamics, constraints, and objectives to support autonomous decision-making and goal-driven planning.
This paper proposes Scene Abstraction, a framework for constructing structured representations of the interpretive scenes that words evoke in context, using few-shot prompting of large language models. The authors introduce COCA-Scenes, a dataset of 520 usage instances, and provide empirical evidence that scenes are reliably identifiable and align better with human interpretation than alternatives.
This paper introduces Semantic Representation Attack (SRA), a novel LLM-agnostic method that optimizes for malicious semantic representations rather than exact text, achieving high attack success rates across multiple open-source models.