Yang Yue
Source-listed: Ph.D. student (direct-entry doctoral student) · Tsinghua University
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?Saved credit: First author · 2025Explore people connected to this work →
- The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language ModelsSaved credit: Contributor · 2026Explore people connected to this work →
- DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Manipulator ControlSaved credit: First author · 2024Explore people connected to this work →
- Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RLSaved credit: First author · 2023Explore people connected to this work →
- Decoupled Prioritized Resampling for Offline RLSaved credit: Contributor · 2023Explore people connected to this work →