PACE quantizes recurrent language-model states to four bits
On hybrid models from 4B to 35B parameters, mixed four- and eight-bit heads approach eight-bit DAMP at about two-thirds of its memory.
Stories per day · 30 days
1 RSS
2 stories, newest first · one card per story
Stories tagged #pace
PACE: Provenance-Aware Capability Enforcement for Tool-Using LLM Agents
PACE checks provenance and authority before LLM agent tool calls and posts the lowest attack success on most benchmarks.