arxiv:2409.00844
Blair Yang
loveblairsky
AI & ML interests
Alignment, red teaming
Recent Activity
new activity about 15 hours ago
PhalaCloud/GLM-5.2-W4AFP8:GLM-5.2-W4AFP8 on 8×H100: fp8_e4m3 KV cache produces corrupted output, while BF16 KV works correctly commentedon a paper 3 months ago
ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement upvoted a paper 3 months ago
ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-RefinementOrganizations
