J C
dark-pen
AI & ML interests
None yet
Recent Activity
upvoted a paper about 7 hours ago
Reasoning Models Struggle to Control their Chains of Thought upvoted a paper about 7 hours ago
BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning liked
a model about 7 hours ago
trishtan/voxtral-sentinel-4b