Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Yangyi Fang
Observed name:
Fang, Yangyi
Institution:
Tsinghua University
Observed institution:
Tsinghua University
OpenAlex ID:
A5126450348
How Much, Then Where: Credit-Conserving Action-to-Token Allocation for Multi-Turn Agent Reinforcement Learning
2026
·
Ma, Lichao
, Sun, Yang
, et al.
·
arXiv (Cornell University)
PDF
Placing Puzzle Pieces Where They Matter: A Question Augmentation Framework for Reinforcement Learning
2026
·
Fang, Yangyi
, Lin, Jiaye
, et al.
·
arXiv (Cornell University)
PDF
From $\log π$ to $π$: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight
2026
·
Fu, Xiaoliang
, Lin, Jiaye
, et al.
·
arXiv (Cornell University)
PDF
Multi-granularity Intent Modeling with Adversarial Robustness for Sequential Recommendation
2026
·
Yangyi Fang
, Haolin Shi
·
Proceedings of the AAAI Conference on Artificial Intelligence
How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization
2026
·
Fang, Yangyi
, Lin, Jiaye
, et al.
·
arXiv (Cornell University)
PDF
Proximity-Based Multi-Turn Optimization: Practical Credit Assignment for LLM Agent Training
2026
·
Fang, Yangyi
, Lin, Jiaye
, et al.
·
arXiv (Cornell University)
PDF
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
2026
·
Fu, Xiaoliang
, Lin, Jiaye
, et al.
·
arXiv (Cornell University)
PDF
From log 𝜋 to 𝜋: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight
2026
·
Xiaoliang Fu
, Jiaye Lin
, et al.
·
Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Placing Puzzle Pieces Where They Matter: A Question Augmentation Framework for Reinforcement Learning
2026
·
Yangyi Fang
, Haolin Shi
·
Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
2026
·
Xiaoliang Fu
, Jiaye Lin
, et al.
·
Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Show more works
View as search
Works count:
10
Citation count:
H-index:
I10-index:
Year
Topic
Type