Get started
Author

Yi R. Fung

Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking
2024 · Fung, Yi, Zhao, Ruining, et al. · arXiv (Cornell University) · 3
PDF
CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents
2026 · Jiayu Liu, Cheng Qian, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 2
PDF
CiteGuard: Faithful Citation Attribution for LLMs via Retrieval-Augmented Validation
2026 · Yee Man Choi, Xuehang Guo, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 1
PDF
Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents
2026 · Huang, Yuchen, Li, Sijia, et al. · arXiv (Cornell University)
PDF
Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning
2026 · Fang, Yiyang, Fu, Pei, et al. · arXiv (Cornell University)
PDF
CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes
2026 · Huang, Yuchen, Li, Xiang, et al. · arXiv (Cornell University)
PDF
RedAct: Redacting Agent Capability Traces for Procedural Skill Protection
2026 · Xu, Shuwen, He, Zhitao, et al. · arXiv (Cornell University)
PDF
On the Geometry of On-Policy Distillation
2026 · Shen, Zhennan, Li, Yanshu, et al. · arXiv (Cornell University)
PDF
AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints
2026 · Liu, Jiayu, Qian, Cheng, et al. · arXiv (Cornell University)
PDF
Reinforcement Learning from Denoising Feedback
2026 · He, Qi, Chen, Huan, et al. · arXiv (Cornell University)
PDF
Scalable Token-Level Hallucination Detection in Large Language Models
2026 · Min, Rui, Pang, Tianyu, et al. · arXiv (Cornell University)
PDF
Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents
2026 · Huang, Shijue, Guo, Hangyu, et al. · arXiv (Cornell University)
PDF
On Stable Long-Form Generation: Benchmarking and Mitigating Length Volatility
2026 · He, Zhitao, Yang, Haolin, et al. · arXiv (Cornell University)
PDF
Code2Math: Can Your Code Agent Evolve Math Problems Through Exploration?
2026 · Guo, Dadi, Xie, Yuejin, et al. · arXiv (Cornell University)
PDF
AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios
2026 · Su, Zhaochen, Gao, Jincheng, et al. · arXiv (Cornell University)
PDF
Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority
2026 · Zhanming Shen, Zeyu Qin, et al.
PDF
Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority
2026 · Shen, Zhanming, Qin, Zeyu, et al. · arXiv (Cornell University)
PDF
RebuttalAgent: Strategic Persuasion in Academic Rebuttal via Theory of Mind
2026 · He, Zhitao, Lyu, Zongwei, et al. · arXiv (Cornell University)
PDF
GeoBrowse: A Geolocation Benchmark for Agentic Tool Use with Expert-Annotated Reasoning Traces
2026 · Xinyu Geng, Yanjing Xiao, et al. · Lecture notes in computer science
PDF
Learning Diverse Responses with Prefix-Conditioned Supervised Fine-Tuning
2026 · Zhiyuan Fan, Guanqiao Chen, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment
2026 · Xinyu Geng, Xuanhua He, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios
2025 · Luo, Haotian, Zhang, Huaisong, et al. · arXiv (Cornell University)
PDF
GPT-RagAD: Two-layer Retrieval-Augmented Multilingual Diagnosis System
2025 · Liu, Xinyi, Sun, Dachun, et al. · Rare & Special e-Zone (The Hong Kong University of Science and Technology)
PDF
Human-centric trustworthy foundation model reasoning
2024 · Fung, Yi · Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)
Works count: 29
Citation count: 8
H-index: 2
I10-index:
Year
Topic
Type