Get started
Author

Yanlin Lai

PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception
2026 · Wei, Yana, Peng, Hongbo, et al. · arXiv (Cornell University)
PDF
MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy
2026 · Shaoxiong Zhan, Yanlin Lai, et al. · Proceedings of the AAAI Conference on Artificial Intelligence
PDF
3ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language Models
2026 · Zhan, Shaoxiong, Lai, Yanlin, et al. · arXiv (Cornell University)
PDF
PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering
2026 · Wang, Xiangfeng, Guo, Hangyu, et al. · arXiv (Cornell University)
PDF
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
2026 · Huang, Ailin, Li, Ang, et al. · arXiv (Cornell University)
PDF
R-Align: Enhancing Generative Reward Models through Rationale-Centric Meta-Judging
2026 · Lai, Yanlin, Huang, Mitt, et al. · arXiv (Cornell University)
PDF
STEP3-VL-10B Technical Report
2026 · Huang, Ailin, Yao, Chengyuan, et al. · arXiv (Cornell University)
PDF
PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering
2026 · Xiangfeng Wang, Hangyu Guo, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Works count: 9
Citation count:
H-index:
I10-index:
Year
Topic
Type