Tag
This paper studies quantization of recursive reasoning models where weight-tied blocks are reused, finding that per-tensor 4-bit quantization causes catastrophic drift but per-block scaling (e.g., MXInt4) restores accuracy, with deeper architectures being more sensitive.
ASGuard is a mechanistically-informed defense framework that mitigates jailbreaking attacks on LLMs by identifying vulnerable attention heads through circuit analysis and applying targeted activation scaling and fine-tuning to improve refusal behavior robustness while preserving model capabilities.