Enhong Chen

5 papers University of Science and Technology of China

• Accurate KV Cache Eviction via Anchor Direction Projection for Efficient LLM Inference
• Improving Time Series Forecasting via Instance-aware Post-hoc Revision
• LogicTree: Improving Complex Reasoning of LLMs via Instantiated Multi-step Synthetic Logical Data
• P-Law: Predicting Quantitative Scaling Law with Entropy Guidance in Large Recommendation Models
• RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering