Get started
Author

Yejin Choi

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
2026 · Liu, Shih-Yang, Dong, Xin, et al. · arXiv (Cornell University) · 209
PDF
Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
2026 · Hatamizadeh, Ali, Choi, Yejin, et al. · arXiv (Cornell University) · 53
PDF
ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
2026 · Hong, Yining, Liu, Jiageng, et al. · arXiv (Cornell University) · 41
PDF
RAGEN-2: Reasoning Collapse in Agentic RL
2026 · Wang, Zihan, Gui, Chi, et al. · arXiv (Cornell University) · 26
PDF
Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text
2026 · Lu, Ximing, Acuna, David, et al. · arXiv (Cornell University) · 12
PDF
Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs
2026 · Hong, Yining, Huang, Huang, et al. · arXiv (Cornell University) · 9
PDF
MoCo: A One-Stop Shop for Model Collaboration Research
2026 · Feng, Shangbin, Bai, Yuyang, et al. · arXiv (Cornell University) · 8
PDF
Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch
2026 · Kim, Hyunwoo, Mireshghallah, Niloofar, et al. · arXiv (Cornell University) · 6
PDF
How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning
2026 · Kim, Bosung, Wang, Ruiyi, et al. · arXiv (Cornell University) · 5
PDF
DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation
2026 · Jung, Jaehun, Kim, Hyunwoo, et al. · arXiv (Cornell University) · 1
PDF
Works count: 10
Citation count: 370
H-index: 7
I10-index: 5
Year
Topic
Type