Small-step Semantics, Big-step Semantics, Reduction Rules, Language Specification
ACE-RL: Adaptive Constraint-Enhanced Reward for Long-form Generation Reinforcement Learning
arxiv.org·3d
When Is MCP Actually Worth It?
thenewstack.io·1d
Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking
arxiv.org·2d
Integrating Spatial and Semantic Embeddings for Stereo Sound Event Localization in Videos
arxiv.org·2d
Loading...Loading more...