知识花园 (Knowledge Garden)

The Knowledge Mining team $\sqsubseteq$ The Websoft research group

User Tools

Site Tools

Trace:
en:team:publications

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
en:team:publications [2026/07/30 17:31] – [2026 年] whuen:team:publications [2026/09/23 10:54] (current) – whu
Line 2: Line 2:
  
 **Marks**: $^\star$//Corresponding author//; $^\dagger$//Equal contributor//; $^\S$//External collaborator// **Marks**: $^\star$//Corresponding author//; $^\dagger$//Equal contributor//; $^\S$//External collaborator//
 +
 +==== 2027 年 ====
 +
 +  - Ziqi Wang, Jingzhe Zhang, Shuo Shen, Wei Hu$^\star$.\\ Fast label-filtering approximate nearest neighbor search via progressive label set stratification.\\ In: //SIGMOD//, 2027.
  
 ==== 2026 年 ==== ==== 2026 年 ====
Line 7: Line 11:
   - Ziqi Wang, Jingzhe Zhang, Wei Hu$^\star$.\\ WoW: A window-to-window incremental index for range-filtering approximate nearest neighbor search.\\ In: //SIGMOD//, 3(6):378, 2026. [[https://arxiv.org/abs/2508.18617|arXiv]] [[https://github.com/nju-websoft/WoW|GitHub]]   - Ziqi Wang, Jingzhe Zhang, Wei Hu$^\star$.\\ WoW: A window-to-window incremental index for range-filtering approximate nearest neighbor search.\\ In: //SIGMOD//, 3(6):378, 2026. [[https://arxiv.org/abs/2508.18617|arXiv]] [[https://github.com/nju-websoft/WoW|GitHub]]
   - Yuhan Wu, Huan Zhang, Wei Cheng, Chen Shen, Jingyue Yang, Wei Hu$^\star$.\\ Bootstrapping code translation with weighted multilanguage exploration.\\ In: //ACL//, 36247--36259, 2026. [[https://arxiv.org/abs/2601.03512|arXiv]] [[https://github.com/nju-websoft/BootTrans|GitHub]]   - Yuhan Wu, Huan Zhang, Wei Cheng, Chen Shen, Jingyue Yang, Wei Hu$^\star$.\\ Bootstrapping code translation with weighted multilanguage exploration.\\ In: //ACL//, 36247--36259, 2026. [[https://arxiv.org/abs/2601.03512|arXiv]] [[https://github.com/nju-websoft/BootTrans|GitHub]]
-  - Wei Cheng, Chen Shen, Huan Zhang, Yuhan Wu, Jingyue Yang, Wei Hu$^\star$.\\ BCaLLM: Call graph-guided Python breaking change detection with large language models.\\ In: //ISSTA//, 2026.+  - Wei Cheng, Chen Shen, Huan Zhang, Yuhan Wu, Jingyue Yang, Wei Hu.\\ BCaLLM: Call graph-guided Python breaking change detection with large language models.\\ In: //ISSTA//, 3:104, 2026. [[https://github.com/nju-websoft/BCaLLM|GitHub]]
   - Xiangyu Liu, Haodi Lei, Yi Liu, Yang Liu, Wei Hu$^\star$.\\ ProtSAE: Disentangling and interpreting protein language models via semantically-guided sparse autoencoders.\\ In: //AAAI//, 773--781, 2026. [[https://arxiv.org/abs/2509.05309|arXiv]] [[https://github.com/nju-websoft/ProtSAE|GitHub]]   - Xiangyu Liu, Haodi Lei, Yi Liu, Yang Liu, Wei Hu$^\star$.\\ ProtSAE: Disentangling and interpreting protein language models via semantically-guided sparse autoencoders.\\ In: //AAAI//, 773--781, 2026. [[https://arxiv.org/abs/2509.05309|arXiv]] [[https://github.com/nju-websoft/ProtSAE|GitHub]]
   - Yi Liu, Xiangyu Liu, Zequn Sun, Wei Hu$^\star$.\\ Answering the unanswerable is to err knowingly: Analyzing and mitigating abstention failures in large reasoning models.\\ In: //AAAI//, 32231--32239, 2026. [[https://arxiv.org/abs/2508.18760|arXiv]] [[https://github.com/nju-websoft/AbstentionReasoning|GitHub]]   - Yi Liu, Xiangyu Liu, Zequn Sun, Wei Hu$^\star$.\\ Answering the unanswerable is to err knowingly: Analyzing and mitigating abstention failures in large reasoning models.\\ In: //AAAI//, 32231--32239, 2026. [[https://arxiv.org/abs/2508.18760|arXiv]] [[https://github.com/nju-websoft/AbstentionReasoning|GitHub]]
   - Yuhan Wu, Huan Zhang, Wei Cheng, Chen Shen, Jingyue Yang, Wei Hu$^\star$.\\ Improving code translation with syntax-guided and semantic-aware preference optimization.\\ In: //IJCAI//, 2026. [[https://arxiv.org/abs/2605.13229|arXiv]] [[https://github.com/nju-websoft/CTO|GitHub]]   - Yuhan Wu, Huan Zhang, Wei Cheng, Chen Shen, Jingyue Yang, Wei Hu$^\star$.\\ Improving code translation with syntax-guided and semantic-aware preference optimization.\\ In: //IJCAI//, 2026. [[https://arxiv.org/abs/2605.13229|arXiv]] [[https://github.com/nju-websoft/CTO|GitHub]]
   - Zequn Sun, Xiaohui Zhang, Yaqin Jin$^\S$, Wei Hu$^\star$.\\ Mitigating exploration sluggishness in iterative knowledge graph augmentation.\\ In: //ISWC//, 2026.   - Zequn Sun, Xiaohui Zhang, Yaqin Jin$^\S$, Wei Hu$^\star$.\\ Mitigating exploration sluggishness in iterative knowledge graph augmentation.\\ In: //ISWC//, 2026.
 +  - Rongzhi Zhu$^\dagger$, Xiangyu Liu$^\dagger$, Yi Liu, Shuo Zhang$^\S$, Ruirui Zhang$^\S$, Rui Wu$^\S$, Tao Jiang$^\S$, Zequn Sun$^\star$, Wenhao Xu$^\S$, Wei Hu.\\ Dense process supervision for search agents via fact utility estimation.\\ In: //EMNLP//, 2026.
 +  - Haoyang Chen, Yi Liu, Jianzhi Shao$^\S$, Xiaozhou Xu$^\S$, Zhe Sun$^\S$, Wei Hu$^\star$.\\ Polished but unresolved: Identifying late-stage pressure states in long-horizon tool-use agents.\\ In: //EMNLP//, 2026.
 +  - Yang Liu$^\dagger$, Chenxu Wang$^{\dagger,\S}$, Jianzhi Shao$^\S$, Jun Ji, Xiaozhou Xu$^\S$, Zhe Sun$^\S$, Wei Hu$^\star$.\\ Beyond query-item matching: Personalized behavioral relevance modeling for e-commerce search via rubric-guided reinforcement learning.\\ In: //EMNLP (Industry Track)//, 2026.
   - Huan Zhang, Wei Cheng, Wei Hu$^\star$.\\ Self-improving code generation via semantic entropy and behavioral consensus.\\ In: //ICPC//, 49--60, 2026. [[https://arxiv.org/abs/2603.29292|arXiv]] [[https://github.com/nju-websoft/ConSelf|GitHub]]   - Huan Zhang, Wei Cheng, Wei Hu$^\star$.\\ Self-improving code generation via semantic entropy and behavioral consensus.\\ In: //ICPC//, 49--60, 2026. [[https://arxiv.org/abs/2603.29292|arXiv]] [[https://github.com/nju-websoft/ConSelf|GitHub]]
-  - Haoyang Chen, Yi Liu, Chenyang Li, Wei Hu$^\star$.\\ Decomposing complexity: A difficulty-aware multi-agent framework for open-domain knowledge graph construction.\\ In: //DASFAA//, 324--339, 2026.+  - Haoyang Chen, Yi Liu, Chenyang Li$^\S$, Wei Hu$^\star$.\\ Decomposing complexity: A difficulty-aware multi-agent framework for open-domain knowledge graph construction.\\ In: //DASFAA//, 324--339, 2026.
   - Haoyang Chen, Yi Liu, Jianzhi Shao$^\S$, Tao Zhang$^\S$, Chengfu Huo$^\S$, Wei Hu$^\star$.\\ How do answer tokens read reasoning traces? Self-reading patterns in thinking LLMs for quantitative reasoning.\\ In: //Findings of ACL//, 30150--30166, 2026. [[https://arxiv.org/abs/2604.19149|arXiv]]   - Haoyang Chen, Yi Liu, Jianzhi Shao$^\S$, Tao Zhang$^\S$, Chengfu Huo$^\S$, Wei Hu$^\star$.\\ How do answer tokens read reasoning traces? Self-reading patterns in thinking LLMs for quantitative reasoning.\\ In: //Findings of ACL//, 30150--30166, 2026. [[https://arxiv.org/abs/2604.19149|arXiv]]
   - Wei Cheng, Yongchang Cao$^\S$, Chen Shen, Binhua Li$^\S$, Jue Chen$^\S$, Yongbin Li$^{\S,\star}$, Wei Hu$^\star$.\\ To diff or not to diff? Structure-aware and adaptive output formats for efficient LLM-based code editing.\\ In: //Findings of ACL//, 29677--29694, 2026. [[https://arxiv.org/abs/2604.27296|arXiv]] [[https://github.com/nju-websoft/AdaEdit|GitHub]]   - Wei Cheng, Yongchang Cao$^\S$, Chen Shen, Binhua Li$^\S$, Jue Chen$^\S$, Yongbin Li$^{\S,\star}$, Wei Hu$^\star$.\\ To diff or not to diff? Structure-aware and adaptive output formats for efficient LLM-based code editing.\\ In: //Findings of ACL//, 29677--29694, 2026. [[https://arxiv.org/abs/2604.27296|arXiv]] [[https://github.com/nju-websoft/AdaEdit|GitHub]]
 +  - Rongzhi Zhu, Yi Liu, Jiancheng Wang$^{\S,\star}$, Xiangyu Liu, Zequn Sun$^\star$, Yiwei Wang$^\S$, Yu Deng$^\S$, Zijian Zhou$^\S$, Wei Hu.\\ When can large reasoning models save thinking? Mechanistic analysis of behavioral divergence in reasoning.\\ In: //EMNLP Findings//, 2026.
 +  - Rongzhi Zhu, Xiang Huang$^\S$, Yuchuan Wu$^\S$, Rui Wang$^\S$, Zequn Sun$^\star$, Tao Ren$^\S$, Weiyao Luo$^\S$, Bingxue Qiu$^\S$, Jieping Ye$^\S$, Yongbin Li$^{\S,\star}$, Wei Hu.\\ EIBench: A Simulator-Based Benchmark and Turn-Credit RL for Emotion Management.\\ In: //EMNLP Findings//, 2026.
 +  - Huicheng Huang, Xiaohui Zhang, Yuanning Cui$^\S$, Zequn Sun$^\star$, Wei Hu.\\ AdaMemPIP: Adaptive memory pipeline orchestration for LLM agents.\\ In: //EMNLP Findings//, 2026.
 +  - Chengyuan Yang, Zequn Sun$^\star$, Wei Wei, Wei Hu.\\ Beyond static summarization: Proactive memory extraction for LLM agents.\\ In: //EMNLP Findings//, 2026.
 +  - Yang Liu, Zequn Sun, Yuanning Cui$^\S$, Wei Hu$^\star$.\\ Knowledge graph completion with iterative self-reflection of retrieval-augmented language models.\\ In: //ADMA//, 2026.
 +  - Yuan Feng, Xiaobin Tian, Wei Hu$^\star$.\\ LLM-guided explanation generation for knowledge graph embedding-based node classification.\\ In: //ADMA//, 2026.
   - Jianhao Chen, Zishuo Xun$^\S$, Bocheng Zhou$^\S$, Han Qi$^\S$, Hangfan Zhang$^\S$, Qiaosheng Zhang$^\S$, Yang Chen$^\S$, Wei Hu, Yuzhong Qu$^\star$, Shuyue Hu$^{\S,\star}$.\\ Do we truly need so many samples? Multi-LLM repeated sampling efficiently scales test-time compute.\\ In: //AAAI//, 20083--20091, 2026.   - Jianhao Chen, Zishuo Xun$^\S$, Bocheng Zhou$^\S$, Han Qi$^\S$, Hangfan Zhang$^\S$, Qiaosheng Zhang$^\S$, Yang Chen$^\S$, Wei Hu, Yuzhong Qu$^\star$, Shuyue Hu$^{\S,\star}$.\\ Do we truly need so many samples? Multi-LLM repeated sampling efficiently scales test-time compute.\\ In: //AAAI//, 20083--20091, 2026.
   - Yuheng Bao, Wenhao Zhou, Xuan Wu, Wei Hu, Dingkun Xu, Mingjia Qian, Yuzhong Qu$^\star$.\\ SQA: SPARQL query annotating with question-answer pairs.\\ In: //ESWC//, 42--62, 2026.   - Yuheng Bao, Wenhao Zhou, Xuan Wu, Wei Hu, Dingkun Xu, Mingjia Qian, Yuzhong Qu$^\star$.\\ SQA: SPARQL query annotating with question-answer pairs.\\ In: //ESWC//, 42--62, 2026.
   - Yuanning Cui$^\S$, Zequn Sun, Wei Hu, Zhangjie Fu$^{\S,\star}$.\\ KGFR: A foundation retriever for generalized knowledge graph question answering.\\ IEEE Transactions on Knowledge and Data Engineering, 2026. [[https://doi.org/10.1109/TKDE.2026.3712877|IEEE]]   - Yuanning Cui$^\S$, Zequn Sun, Wei Hu, Zhangjie Fu$^{\S,\star}$.\\ KGFR: A foundation retriever for generalized knowledge graph question answering.\\ IEEE Transactions on Knowledge and Data Engineering, 2026. [[https://doi.org/10.1109/TKDE.2026.3712877|IEEE]]
   - Yuanning Cui$^\S$, Zequn Sun, Wei Hu, Kexuan Xin$^\S$, Zhangjie Fu$^{\S,\star}$.\\ Breaking the reasoning horizon in entity alignment foundation models.\\ In: //IJCAI//, 2026.   - Yuanning Cui$^\S$, Zequn Sun, Wei Hu, Kexuan Xin$^\S$, Zhangjie Fu$^{\S,\star}$.\\ Breaking the reasoning horizon in entity alignment foundation models.\\ In: //IJCAI//, 2026.
 +
 ==== 2025 ==== ==== 2025 ====
  
en/team/publications.1785403885.txt.gz · Last modified: 2026/07/30 17:31 by whu