Steering Autoregressive Music Generation with Recursive Feature Machines
"模型控制" 相关文章
The sum of its parts: composing AI control protocols
The sum of its parts: composing AI control protocols
Energy-Driven Steering: Reducing False Refusals in Large Language Models
Analyzing Finetuning Representation Shift for Multimodal LLMs Steering
Anthropic AI Introduces Persona Vectors to Monitor and Control Personality Shifts in LLMs
Anthropic最新论文，在训练中给人工智能一种邪恶的“疫苗”，可能会让它变得更好
大模型上下文工程之Prefill Response（预填响应）技巧
FBSDiff: Plug-and-Play Frequency Band Substitution of Diffusion Features for Highly Controllable Text-Driven Image Translation
Internal Value Alignment in Large Language Models through Controlled Value Vector Activation
大模型可解释性在工业界的应用实战丨周五直播·大模型可解释性读书会
Surrogate Model for Heat Transfer Prediction in Impinging Jet Arrays using Dynamic Inlet/Outlet and Flow Rate Control
Open Challenges in Representation Engineering
具爭議的加州AI法案能否通過將在9月底見真章
