Researcher — paper.dinq.me

2026 顶会论文

作者位次 #9/10ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders

Next-ToBE: Probabilistic Next Token-Bag Exploitation for Activating Anticipatory Capacity in LLMs

Yihe Liu · Huibin Wang · Xianming Hu · Pinyi Zhang · Jiahao Xiong · Chenglin Wang · Nuoyi Chen · Hongbo Zhao · Jie Zhang · Kai Zhang

OpenReview

作者位次 #6/7ACL 2026Poster· Natural Language Processing

Localized Low-Rank Adaptation within Clustered Parameter Subspaces

Jiahao Xiong · Yihe Liu · Xianming Hu · Hongbo Zhao · Nuoyi Chen · Jie Zhang · Kai Zhang

摘要

Low-Rank Adaptation (LoRA) for large language models (LLMs) has achieved significant success in various domains. So far, most algorithms in the LoRA-family rely on global low-rank factors spanning the entire update weight matrix ( \Delta \mathbf{W} ). Through careful analysis, however, we observe...

效率与系统评测与基准推理OpenReview 项目页

作者位次 #8/10ACL 2026Findings· Findings of ACL

Z oom RAG : Hierarchical Random-walk Zooming across Multi-scale Information Graphs for Fast and Accurate RAG

Xianming Hu · Jingyang Chen · Bin Tang · Yihe Liu · Yihong Huang · Hongbo Zhao · Nuoyi Chen · Jie Zhang · Ping Li · Kai Zhang

摘要

Retrieval-Augmented Generation is a powerful tool for NLP applications. Yet, it is challenging to encode large knowledge bases as compact offline structures while simultaneously achieving accurate, low-latency online retrieval. We propose ZoomRAG , a coarse-to-fine, hierarchical graph inference m...

检索与知识推理效率与系统OpenReview 项目页

Jie Zhang

获取完整研究档案

联系方式

2026 顶会论文

Next-ToBE: Probabilistic Next Token-Bag Exploitation for Activating Anticipatory Capacity in LLMs

Localized Low-Rank Adaptation within Clustered Parameter Subspaces

Z oom RAG : Hierarchical Random-walk Zooming across Multi-scale Information Graphs for Fast and Accurate RAG

常见合作者