AI.info
Haobo Wang
Explore Haobo Wang on AI.info.
- Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty
- Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation Shaping
- Table as a Modality for Large Language Models
- An Invariant Latent Space Perspective on Language Model Inversion