Tag
Proposes a multi-objective reinforcement learning framework combining semantic embeddings with Pareto-DQN to balance engagement, diversity, and fairness in recommendations, mitigating filter bubbles.
TheoremGraph is a unified statement-level dependency graph that spans both informal mathematics (arXiv papers) and formal mathematics (Lean projects), using semantic embeddings to bridge the gap between them. The authors provide datasets, extractors, and APIs to support mathematical search and retrieval.
Proposes SENSE, a semantic embedding navigation method for retrieval-based speculative decoding that uses hidden states for semantic alignment and soft-gated evaluation, achieving up to 3.26x speedup on LLaMA and Qwen families while preserving generation quality.