Wenxiang Jiao

Computer Science · Physical Sciences

16h-index1.3kcitations97works6.62yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(41), Natural Language Processing Techniques(40), Multimodal Machine Learning Applications(12), Photonic and Optical Devices(8), Text Readability and Simplification(8)

Publications96 total

LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls
arXiv (Cornell University)·2025Open Access
Fints: Efficient Inference-Time Personalization for LLMs with Fine-Grained Instance-Tailored Steering
arXiv (Cornell University)·2025Open Access
DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains
arXiv (Cornell University)·2025Open Access
Benchmarking Chinese Commonsense Reasoning with a Multi-hop Reasoning Perspective
arXiv (Cornell University)·2025Open Access
Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards
arXiv (Cornell University)·2025Open Access
REA-RL: Reflection-Aware Online Reinforcement Learning for Efficient Large Reasoning Models
arXiv (Cornell University)·2025Open Access
Learning to Ask: When LLM Agents Meet Unclear Instruction
2025Open Access
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
2025Open Access
Chain-of-Jailbreak Attack for Image Generation Models via Step by Step Editing
2025· 1 citedOpen Access
DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization
2025Open Access
Findings of the WMT 2024 Shared Task on Discourse-Level Literary Translation
arXiv (Cornell University)·2024Open Access
DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization
arXiv (Cornell University)·2024Open Access
On the Shortcut Learning in Multilingual Neural Machine Translation
arXiv (Cornell University)·2024Open Access
On the shortcut learning in multilingual neural machine translation
Neurocomputing·2024· 2 cited
NewTerm: Benchmarking Real-Time New Terms for Large Language Models with Annual Updates
arXiv (Cornell University)·2024Open Access
Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step
arXiv (Cornell University)·2024Open Access
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
arXiv (Cornell University)·2024Open Access
Improving Gloss-free Sign Language Translation by Reducing Representation Density
arXiv (Cornell University)·2024Open Access
Quantifying trapping stability of optical tweezers with an external flow
Photonics Research·2024· 3 cited
How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments
arXiv (Cornell University)·2024· 8 citedOpen Access
page 1 of 5Next →

Frequent Co-authors

Zhaopeng Tu(27), Michael R. Lyu(22), Jen-tse Huang(14), Shuming Shi(12), Wenxuan Wang(10), Xing Wang(10), Irwin King(10), Xuping Zhang(8), Guanghui Wang(8), Wenxuan Wang(5), Min Jiang(5), Youliang Yuan(5), Man Ho Lam(5), Eric John Li(5), Zhiwei He(4), Yujiu Yang(4), Mi Li(4), Yuejiang Song(4), Shilin He(4), Zhoufeng Ying(4)