#Model Control
2 articles with this tag
AI Research
MMDiff: Auditing and Steering MLLMs
MMDiff, a new multimodal model-diffing framework, enables granular control and understanding of MLLMs by isolating and manipulating specific behavioral features.
about 3 hours ago
AI Research
Steering LRMs Beyond Output Degradation
A new probe-based method, FPCG, distinguishes prediction from detection features to enable precise large reasoning models steering with minimal output quality degradation.
2 months ago