5 papers
TreeSpark: Learning to Draft the Trees You Verify for Speculative Decoding
Jihao Zhao, Qianyu Jiang, Shuaishuai Zu +6
Parallel drafters such as DFlash and DSpark reduce proposal latency, but early mismatches limit how much of each block can be accepted. Retaining alternatives introduces parent sta…
Writer-R1: Dynamic Rubric Mining for Reinforcement Learning of Open-Ended Writing
Jihao Zhao, Shuaishuai Zu, Zhiyuan Ji +2
Training models for open-ended writing requires diverse prompts and sufficiently precise specifications of response quality. Constructing such specifications at scale entails recov…
QChunker: Learning Question-Aware Text Chunking for Domain RAG via Multi-Agent Debate
Jihao Zhao, Daixuan Li, Pengfei Li +3
The effectiveness upper bound of retrieval-augmented generation (RAG) is fundamentally constrained by the semantic integrity and information granularity of text chunks in its knowl…
RouterKT: Mixture-of-Experts for Knowledge Tracing
Han Liao, Shuaishuai Zu
Knowledge Tracing (KT) is a fundamental task in Intelligent Tutoring Systems (ITS), which aims to model the dynamic knowledge states of students based on their interaction historie…
Fair Knowledge Tracing in Second Language Acquisition
Weitao Tang, Guanliang Chen, Shuaishuai Zu +1
In second-language acquisition, predictive modeling aids educators in implementing diverse teaching strategies, attracting significant research attention. However, while model accu…