arxiv:2512.15182
SARIM HASHMI
Sarim-Hash
AI & ML interests
None yet
Recent Activity
upvoted a paper 15 days ago
CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization upvoted an article about 2 months ago
Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment updated a model 3 months ago
Sarim-Hash/Qwen3-14B-sandbaggingOrganizations
