Lexiang Tang
According to our database1,
Lexiang Tang
authored at least 3 papers
in 2025.
Collaborative distances:
Collaborative distances:
Timeline
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
On csauthors.net:
Bibliography
2025
Leash: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model.
CoRR, December, 2025
Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation.
CoRR, June, 2025
Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions.
CoRR, June, 2025