Researcher — paper.dinq.me

2026 顶会论文

一作ICLR 2026Poster· Applications / Language, Speech and Dialog

Dynamic Early Exit in Reasoning Models

Chenxu Yang · Qingyi Si · Yongjie Duan · Zheliang Zhu · Chenyu Zhu · Qiaowei Li · Minghui Chen · Zheng Lin · Weipinng Wang

推理多模态OpenReview

作者位次 #2/7ACL 2026Poster· Natural Language Processing

V ec I nfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization

Dingyu Yao · Chenxu Yang · Zhengyang Tong · Zheng Lin · WEI LIU · Jian Luan · Weiping Wang

摘要

The Key-Value (KV) cache introduces substantial memory overhead during large language model (LLM) inference. Although existing vector quantization (VQ) methods reduce KV cache usage and provide flexible representational capacity across bit-widths, they suffer severe performance degradation at ult...

效率与系统推理可解释性OpenReview 项目页

一作AAAI 2026Poster· Artificial Intelligence

Test-time Prompt Intervention

Chenxu Yang · Qingyi Si · Mz Dai · Dingyu Yao · Mingyu Zheng · Minghui Chen · Zheng Lin · Weiping Wang

OpenReview

一作AAAI 2026Poster· Artificial Intelligence

Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Models

Chenxu Yang · Qingyi Si · Lanrui Wang · Zheng Lin

理论与学习动力学OpenReview

Chenxu Yang

获取完整研究档案

联系方式

2026 顶会论文

Dynamic Early Exit in Reasoning Models

V ec I nfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization

Test-time Prompt Intervention

Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Models

常见合作者