29 citations
5 papers
When Does Learning to Stop Help? A Cost-Aware Study of Early Exits in Reasoning Models
Zhe Dong, Fang Qin, Manish Shah
Reasoning models spend test-time compute unevenly across instances, and a growing family of early-exit rules -- confidence thresholds, entropy monitors, answer-stability checks, an…
Know Before You Fetch: Calibrated Retrieval-Budget Allocation for Retrieval-Augmented Generation
Zhe Dong, Fang Qin, Manish Shah +1
Retrieval-augmented generation (RAG) typically retrieves a fixed number of passages for every query. This is wasteful when the reader already knows the answer, and it can be harmfu…
Diagnosing and Mitigating Retrieval Bottlenecks in LLM-Based Cold-Start Recommendation
Zhe Dong, Fang Qin, Manish Shah +1
Large language models (LLMs) are increasingly used as rerankers in recommender systems, with the expectation that semantic understanding will help in cold-start and long-tail regim…
Utilizing the LightGBM Algorithm for Operator User Credit Assessment Research
Shaojie Li, Xinqi Dong, Danqing Ma +3
Mobile Internet user credit assessment is an important way for communication operators to establish decisions and formulate measures, and it is also a guarantee for operators to ob…
Fostc3net:A Lightweight YOLOv5 Based On the Network Structure Optimization
Danqing Ma, Shaojie Li, Bo Dang +2
Transmission line detection technology is crucial for automatic monitoring and ensuring the safety of electrical facilities. The YOLOv5 series is currently one of the most advanced…