arxiv:2605.18643
Kaiyan Zhang
iseesaw
AI & ML interests
Large Reasoning Models, Reinforcement Learning, Agent
Recent Activity
authored a paper 9 days ago
Post-Trained MoE Can Skip Half Experts via Self-Distillation upvoted a paper 11 days ago
Post-Trained MoE Can Skip Half Experts via Self-Distillation upvoted a paper 3 months ago
How Far Can Unsupervised RLVR Scale LLM Training?Organizations
arxiv:2509.15207
arxiv:2509.09674
arxiv:2509.08827
arxiv:2509.04419
arxiv:2508.10874
arxiv:2508.10308
arxiv:2504.16084
arxiv:2504.00891
arxiv:2503.18942
arxiv:2503.11224
arxiv:2502.06703
arxiv:2502.01456
arxiv:2501.18362
arxiv:2412.17739
arxiv:2412.14689
arxiv:2412.01981
arxiv:2410.11795
arxiv:2407.08940
arxiv:2407.08642
arxiv:2406.12295
arxiv:2406.05534
arxiv:2406.03949
arxiv:2405.17534
arxiv:2405.11870
arxiv:2403.03129
arxiv:2310.15477
arxiv:2305.13888
