nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 Text Generation • 67B • Updated 4 days ago • 1.12M • 228
view article Article Activation Steering With Mean Response Probes : A Case Study In Suppressing Sycophancy In Language Models During TTC Nov 27, 2025 • 2
SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents Paper • 2509.06283 • Published Sep 8, 2025 • 17