arxiv:2603.20105
xiaotong
xtongji
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Robots Need More than VLA and World Models authored a paper 3 months ago
Multi-Task GRPO: Reliable LLM Reasoning Across Tasks authored a paper 3 months ago
Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K SamplersOrganizations
None yet
models 0
None public yet
datasets 0
None public yet