17 citations · 19 across the 10 of their papers we have counts for
5 papers · 1 filter
To Reason but Not to Stop: Understanding and Recovering Pruned Large Reasoning Models
Minh-Anh Nguyen, Nguyen T. Ha Lan, Xiyan Fu +2
Weight pruning can degrade the accuracy of large reasoning models (LRMs), yet it remains unclear whether it damages reasoning itself. We find that much of this degradation stems fr…
DeltaTTG: Training Multi-Turn Agents with a Token-to-Go Progress Meter
Xuyan Ye, Xiyan Fu, Shengda Fan +3
Reinforcement learning with verifiable rewards (RLVR) for multi-turn agents relies on sparse terminal rewards that say little about individual steps. Within-group step comparisons…
Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output
Guozheng Li, Xiyan Fu, Yiwen Guo
Current reinforcement learning from human feedback (RLHF) methods primarily rely on scalar rewards from a trained reward model (RM). While effective, scalar rewards are often noisy…
When Languages Disagree: Self-Evolving Multilingual LLM Judges
Xiyan Fu, Wei Lu
Multilingual LLM-as-a-judge is widely used to evaluate model outputs across languages, but suffers from cross-lingual inconsistency (Fu and Liu, 2025). Existing methods typically t…
Reinforcement Learning for Compositional Generalization with Outcome-Level Optimization
Xiyan Fu, Wei Liu
Compositional generalization refers to correctly interpret novel combinations of known primitives, which remains a major challenge. Existing approaches often rely on supervised fin…