Get started
Author

Yanjun Zhao

Observed name: Zhao, Yanjun
OpenAlex ID: A5125748265
PolicyMem: Geometric Policy Memory for LLM Governance
2026 · Bei, Yuanchen, Chen, Zhengzhang, et al. · arXiv (Cornell University)
PDF
From Inference to Adaptation: A Unified Optimal Transport View of Vision Language Model
2026 · Yu, Qi, Zeng, Zhichen, et al. · arXiv (Cornell University)
PDF
TAG-DLM: Diffusion Language Models for Text-Attributed Graph Learning
2026 · Chen, Lingjie, Bei, Yuanchen, et al. · arXiv (Cornell University)
PDF
Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents
2026 · Association for Computational Linguistics 2026, Bei, Yuanchen, et al. · Underline Science Inc.
PAPERMIND: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs
2026 · Association for Computational Linguistics 2026, Bei, Yuanchen, et al. · Underline Science Inc.
Code as Agent Harness
2026 · Ning, Xuying, Tieu, Katherine, et al. · arXiv (Cornell University)
PDF
Ramen: Robust Test-Time Adaptation of Vision-Language Models with Active Sample Selection
2026 · Bao, Wenxuan, Zhao, Yanjun, et al. · arXiv (Cornell University)
PDF
PaperMind: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs
2026 · Zhao, Yanjun, Wei, Tianxin, et al. · arXiv (Cornell University)
PDF
TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Models
2026 · Chen, Lingjie, Qiu, Ruizhong, et al. · arXiv (Cornell University)
PDF
Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents
2026 · Bei, Yuanchen, Wei, Tianxin, et al. · arXiv (Cornell University)
PDF
SABER: Switchable and Balanced Training for Efficient LLM Reasoning
2026 · Association for Artificial Intelligence 2026, He, Shien, et al. · Underline Science Inc.
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
2026 · Yanjun Zhao, Ruizhong Qiu, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents
2026 · Tianxin Wei, Zhan Shi, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Works count: 13
Citation count:
H-index:
I10-index:
Year
Topic
Type