Ji Pei — accepted AI-conference papers

2025

Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence

EMNLP 2025

Recent advances in reasoning models have demonstrated significant improvements in accuracy by employing detailed and comprehensive reasoning processes. However, generating these lengthy reasoning sequences is computationally expensive and time-consuming. To address this inefficiency, we leverage the

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning Steps

Yijiong Yu, Zhixiao Qi, Yongfeng Huang, Wei Wang, Weifeng.liu, Ran Chen +1

EMNLP 2025

Long-context language models (LCLMs), characterized by their extensive context window, are becoming popular. However, despite the fact that they are nearly perfect at standard long-context retrieval tasks, our evaluations demonstrate they fail in some basic cases. Later, we find they can be well add

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗