Yu Song
5 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper proposes using large language models (LLMs) to generate and compositionally verify software implementations directly from natural language specifications, showing promising preliminary results.
The paper introduces MIRAGE, a framework that systematically discovers semantic attacks on online HD map construction by finding plausible environmental variations that bypass standard adversarial defenses, demonstrating attacks that remove or inject critical road boundaries.
The paper introduces AgentSchool, an advanced LLM-powered multi-agent simulator that models learning as state transitions to provide a robust, ethically viable testbed for educational research and pedagogical reform.
Taiji is a novel LLM-as-Enhancer framework that optimizes recommender systems by addressing the challenges of generating high-quality reasoning data and balancing semantic and ID-based rewards.
This paper proposes Tail-Aware Adaptive-k (TAA-k), a training-free framework for adaptive context selection in retrieval-augmented generation systems using Extreme Value Theory.
Papers
Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generation
Ziyu Song, Jiaming Fang, Kuangyu Li, Tuo Xia +1 more
This paper proposes Tail-Aware Adaptive-k (TAA-k), a training-free framework for adaptive context selection in retrieval-augmented generation systems using Extreme Value Theory.