Yangyi Chen

Computer Science · Physical Sciences

7h-index130citations16works3.32yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

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

Research Topics

Topic Modeling(10), Natural Language Processing Techniques(7), Adversarial Robustness in Machine Learning(5), Multimodal Machine Learning Applications(3), Speech Recognition and Synthesis(2)

Publications16 total

Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
arXiv (Cornell University)·2025Open Access
SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering
arXiv (Cornell University)·2025· 1 citedOpen Access
Executable Code Actions Elicit Better LLM Agents
arXiv (Cornell University)·2024· 9 citedOpen Access
Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge
arXiv (Cornell University)·2023Open Access
DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback
arXiv (Cornell University)·2023· 1 citedOpen Access
CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
arXiv (Cornell University)·2023· 8 citedOpen Access
MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
arXiv (Cornell University)·2023· 15 citedOpen Access
Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models
arXiv (Cornell University)·2023· 1 citedOpen Access
Making Pre-trained Language Models both Task-solvers and Self-calibrators
arXiv (Cornell University)·2023Open Access
Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations
arXiv (Cornell University)·2023· 7 citedOpen Access
Making Pre-trained Language Models both Task-solvers and Self-calibrators
2023Open Access
A Close Look into the Calibration of Pre-trained Language Models
2023· 10 citedOpen Access
A Close Look into the Calibration of Pre-trained Language Models
arXiv (Cornell University)·2022· 3 citedOpen Access
A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks
arXiv (Cornell University)·2022· 24 citedOpen Access
Exploring the Universal Vulnerability of Prompt-based Learning Paradigm
Findings of the Association for Computational Linguistics: NAACL 2022·2022· 40 citedOpen Access
Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework
arXiv (Cornell University)·2021· 11 citedOpen Access

Frequent Co-authors

Heng Ji(9), Xingyao Wang(7), Lifan Yuan(6), Ganqu Cui(5), Zhiyuan Liu(5), Lifan Yuan(3), Hongcheng Gao(2), Maosong Sun(2), Heng Ji(2), Karan Sikka(2), Michael Cogswell(2), Ajay Divakaran(2), Lei Xu(1), Bingxiang He(1), Zihan Wang(1), Jiateng Liu(1), Hao Peng(1), Yichi Zhang(1), Wei Wei(1), Yizhe Zhang(1)