3 papers
cs.AI2026
BitNest: Bit-Nested Speculative Decoding for Memory-Efficient LLM Inference Acceleration
Chence Yang, Ningxi Cheng, Arash Akbari +9
Speculative decoding accelerates autoregressive generation by using a lightweight draft to propose multiple tokens for parallel verification. However, existing methods often requir…
cs.CY2026
A Framework for Human-AI Q-Matrix Refinement: A NeuralCDM Evaluation
Ying Zhang, Ningxi Cheng, Yizhu Gao +5
Q-matrices are a cornerstone of theory-driven assessment and learning analytics, making item demands and students' underlying knowledge components and misconceptions explicit and a…
cs.LG2026
Q-realign: Piggybacking Realignment on Quantization for Safe and Efficient LLM Deployment
Qitao Tan, Xiaoying Song, Ningxi Cheng +6
Public large language models (LLMs) are typically safety-aligned during pretraining, yet task-specific fine-tuning required for deployment often erodes this alignment and introduce…