llm-sci-exam-anrut

AI & ML interests

None defined yet.

Recent Activity

udbhavbamba  authored a paper 5 days ago

Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models

udbhavbamba  authored a paper about 1 month ago

S2D: Selective Spectral Decay for Quantization-Friendly Conditioning of Neural Activations

udbhavbamba  authored a paper about 1 month ago

XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation

View all activity

Team members 4