ZhangXiaoyun
DadaCloud01
AI & ML interests
None yet
Recent Activity
authored a paper about 12 hours ago
Rediscovering Entropy Regularization: Adaptive Coefficient Unlocks Its
Potential for LLM Reinforcement Learning authored a paper about 12 hours ago
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters authored a paper about 12 hours ago
Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling StrategyOrganizations
