most citedP3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices

1 citations · 1 across the 2 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment

Hongjue Zhao, Haosen Sun, Jiangtao Kong +8

Activation steering, or representation engineering, offers a lightweight approach to align large language models (LLMs) by manipulating their internal activations at inference time…