Yixia Li

25 papers A* 2Journal 17Unranked 6
YearRankTypeTitle / Venue / Authors
2026 J jnl
Anchored Policy Optimization: Mitigating Exploration Collapse Via Support-Constrained Rectification.
CoRR
Tianyi Wang, Long Li, Hongcan Guo, Yibiao Chen, Yixia Li, Yong Wang, Yun Chen, Guanhua Chen
2026 J jnl
From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics.
CoRR
Bowen Cao, Dongdong Zhang, Yixia Li, Junpeng Liu, Shijue Huang, Chufan Shi, Hongyuan Lu, Yaokang Wu, Guanhua Chen, Wai Lam, Furu Wei
2026 J jnl
No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning.
CoRR
Zhicong Li, Lingjie Jiang, Yulan Hu, Xingchen Zeng, Yixia Li, Xiangwen Zhang, Guanhua Chen, Zheng Pan, Xin Li, Yong Liu
2026 J jnl
Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents.
CoRR
Zeping Li, Hongru Wang, Yiwen Zhao, Guanhua Chen, Yixia Li, Keyang Chen, Yixin Cao, Guangnan Ye, Hongfeng Chai, Zhenfei Yin
2026 J jnl
Towards Fair and Comprehensive Evaluation of Routers in Collaborative LLM Systems.
CoRR
Wanxing Wu, He Zhu, Yixia Li, Lei Yang, Jiehui Zhao, Hongru Wang, Jian Yang, Benyou Wang, Bingyi Jing, Guanhua Chen
2025 J jnl
Cantonese natural language processing in the transformers era: a survey and current challenges.
Lang. Resour. Evaluation
Rong Xiang, Emmanuele Chersoni, Yixia Li, Jing Li, Chu-Ren Huang, Yushan Pan, Yushi Li
2025 J jnl
Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning.
CoRR
Zhiwen Ruan, Yixia Li, He Zhu, Yun Chen, Peng Li, Yang Liu, Guanhua Chen
2025 — conf
FANNO: Augmenting High-Quality Instruction Data with Open-Sourced LLMs Only.
ACL (Findings)
He Zhu, Yifan Ding, Yicheng Tao, Zhiwen Ruan, Yixia Li, Wenjia Zhang, Yun Chen, Guanhua Chen
2025 J jnl
From Word to World: Can Large Language Models be Implicit Text-based World Models?
CoRR
Yixia Li, Hongru Wang, Jiahao Qiu, Zhenfei Yin, Dongdong Zhang, Cheng Qian, Zeping Li, Pony Ma, Guanhua Chen, Heng Ji, Mengdi Wang
2025 A* conf
G2: Guided Generation for Enhanced Output Diversity in LLMs.
EMNLP
Zhiwen Ruan, Yixia Li, Yefeng Liu, Yun Chen, Weihua Luo, Peng Li, Yang Liu, Guanhua Chen
2025 J jnl
G2: Guided Generation for Enhanced Output Diversity in LLMs.
CoRR
Zhiwen Ruan, Yixia Li, Yefeng Liu, Yun Chen, Weihua Luo, Peng Li, Yang Liu, Guanhua Chen
2025 — conf
ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs.
ACL (1)
Yan Yang, Yixia Li, Hongru Wang, Xuetao Wei, James Jianqiao Yu, Yun Chen, Guanhua Chen
2025 J jnl
ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs.
CoRR
Yan Yang, Yixia Li, Hongru Wang, Xuetao Wei, Jianqiao Yu, Yun Chen, Guanhua Chen
2025 — conf
LayAlign: Enhancing Multilingual Reasoning in Large Language Models via Layer-Wise Adaptive Fusion and Alignment Strategy.
NAACL (Findings)
Zhiwen Ruan, Yixia Li, He Zhu, Longyue Wang, Weihua Luo, Kaifu Zhang, Yun Chen, Guanhua Chen
2025 J jnl
LayAlign: Enhancing Multilingual Reasoning in Large Language Models via Layer-Wise Adaptive Fusion and Alignment Strategy.
CoRR
Zhiwen Ruan, Yixia Li, He Zhu, Longyue Wang, Weihua Luo, Kaifu Zhang, Yun Chen, Guanhua Chen
2025 — conf
MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning.
NAACL (Long Papers)
Hanqing Wang, Yixia Li, Shuo Wang, Guanhua Chen, Yun Chen
2025 J jnl
UniPoll: A Unified Social Media Poll Generation Framework via Multiobjective Optimization.
IEEE Trans. Neural Networks Learn. Syst.
Yixia Li, Rong Xiang, Yanlin Song, Jing Li
2025 J jnl
VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models.
CoRR
Lingjie Jiang, Shaohan Huang, Xun Wu, Yixia Li, Dongdong Zhang, Furu Wei
2024 J jnl
MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning.
CoRR
Hanqing Wang, Zeguan Xiao, Yixia Li, Shuo Wang, Guanhua Chen, Yun Chen
2024 — conf
PACIT: Unlocking the Power of Examples for Better In-Context Instruction Tuning.
ACL (Findings)
Tianci Xue, Ziqi Wang, Yixia Li, Yun Chen, Guanhua Chen
2024 A* conf
SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation.
NeurIPS
Yixia Li, Boya Xiong, Guanhua Chen, Yun Chen
2024 J jnl
SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation.
CoRR
Yixia Li, Boya Xiong, Guanhua Chen, Yun Chen
2023 J jnl
TADIS: Steering Models for Deep-Thinking about Demonstration Examples.
CoRR
Tianci Xue, Ziqi Wang, Yixia Li, Yun Chen, Guanhua Chen
2023 J jnl
UniPoll: A Unified Social Media Poll Generation Framework via Multi-Objective Optimization.
CoRR
Yixia Li, Rong Xiang, Yanlin Song, Jing Li
2019 — conf
Electric Power Grid Invulnerability Under Intentional Edge-Based Attacks.
DependSys
Yixia Li, Shudong Li, Yanshan Chen, Peiyan He, Xiaobo Wu, Weihong Han