Get started
Author

Di Liang

EEG signal recognition of flavor perception in rapeseed oil from different processing techniques
2026 · Lanhang Yao, Di Liang, et al. · Food Chemistry · 9
DPI: Exploiting Parameter Heterogeneity for Interference-Free Fine-Tuning
2026 · Xiaoyu Liu, Xiaoyu Guan, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 1
MMTableBench: A Multi-level Multimodal Benchmark for Reasoning and Layout Complexity in Table QA
2026 · Xianjie Wu, Xiaohang Xu, et al. · International World Wide Web Conference (WWW) · 1
Data Scaling Laws in Stereo Matching: From In-domain Fitting to Cross-domain Generalization
2026 · Zhao, Tong, Liang, Di, et al. · arXiv (Cornell University)
PDF
QREF: Improving DeepSearch Agents by Aligning Search with Reasoning via Query Refinement and Evidence Filtering
2026 · Chen, Yujia, Wang, Yuhui, et al. · arXiv (Cornell University)
PDF
UXBench Pro: Benchmarking Personalized User Experience in Multi-Turn Dialogue Interactions
2026 · Hong, Mengze, Lei, Zeyang, et al. · arXiv (Cornell University)
PDF
Identity-Assisted Association of Unordered DOA Estimates for Neural Speech Source Tracking
2026 · Yang, Bing, Liang, Di, et al. · arXiv (Cornell University)
PDF
Harmful Content Is Not Enough: Continuation Framing Moderates In-Context Emergent Misalignment
2026 · Liu, Peiyang, Wang, Xi, et al. · arXiv (Cornell University)
PDF
TRACE: Discovering Task-Specific Parameter via Adaptation-Aware Probing for Continual Fine-Tuning
2026 · Xiaosong Han, Ke Chen, et al. · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
Multi-Granularity Reasoning for Natural Language Inference
2026 · Chunling Xi, Di Liang · International Joint Conference on Neural Networks (IJCNN)
PDF
Beyond Semantic Similarity: Multi-Stage Calibration for In-Context Learning
2026 · Chunling Xi, Di Liang · International Joint Conference on Neural Networks (IJCNN)
Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning
2026 · Lin, Zekai, Xue, Chao, et al. · arXiv (Cornell University)
PDF
Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories
2026 · Liu, Peiyang, Chen, Zhirui, et al. · arXiv (Cornell University)
PDF
Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models
2026 · Xue, Chao, Wang, Yao, et al. · arXiv (Cornell University)
PDF
Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty
2026 · Xue, Chao, Wang, Yao, et al. · arXiv (Cornell University)
PDF
When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG
2026 · Li, Junchen, Xu, Liang, et al. · arXiv (Cornell University)
PDF
Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation
2026 · Hu, Zhanghao, Zhu, Qinglin, et al. · arXiv (Cornell University)
PDF
DPI: Exploiting Parameter Heterogeneity for Interference-Free Fine-Tuning
2026 · Liu, Xiaoyu, Guan, Xiaoyu, et al. · arXiv (Cornell University)
PDF
Rethinking LLM-Driven Heuristic Design: Generating Efficient and Specialized Solvers via Dynamics-Aware Optimization
2026 · Wang, Rongzheng, Huang, Yihong, et al. · arXiv (Cornell University)
PDF
Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories
2026 · Peiyang Liu, Zhirui Chen, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models
2026 · Chao Xue, Yao Wang, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning
2026 · Zekai Lin, Chao Xue, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty
2026 · Chao Xue, Yao Wang, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
PDF
Works count: 23
Citation count: 11
H-index: 1
I10-index:
Year
Topic
Type