SOURCE-LINKED INTELLIGENCE

Good Memory Has ECC: Evaluating the Memory of Vision-Language Models Beyond Accuracy

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Memory is widely viewed as an important unsolved problem for LLMs and VLMs, and current benchmarks typically evaluate it by testing accuracy over long text or video. However, accuracy alone misses properties that matter for real long-horizon tasks. We introduce ECCBench, a benchmark and evaluation protocol that measures memory beyond a system's capacity--its raw accuracy at a specific budget--via three axes we call ECC: efficiency--the computation, in FLOPs, needed to answer from memory; compression--whether compressible inputs are remembered more accurately or efficiently; and calibration--wh

Read original source ↗ Open in workspace

recordType

paper

region

Global