Jie Zhang
3 papers · Latest:
Software Engineering
How Does Chunking Affect Retrieval-Augmented Code Completion? A Controlled Empirical Study
A study on RAG code completion found function-based chunking underperforms, while Sliding Window and cAST are optimal, and context length is key.
2605.04763
Machine LearningTTVS: Boosting Self-Exploring Reinforcement Learning via Test-time Variational Synthesis
TTVS boosts self-exploring reinforcement learning by dynamically synthesizing diverse training data from unlabeled test queries, improving LRM adaptation.
2604.08468
Natural Language ProcessingValence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control
Researchers found a valence-arousal subspace in LLMs, enabling precise control over emotional output, refusal, and sycophancy across models.
2604.03147
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.