Kaijie Chen

MemMark introduces a state-evolution attribution watermark that embeds owner-controlled signals into latent memory-write decisions, enabling robust provenance tracking for agent memory even when all traditional logs and metadata are lost.

The paper proposes using GUI agents, both as objective evaluators and subjective playtesters, to significantly improve the generation of playable games from prompts, demonstrating a 66.8% rubric pass-rate with a novel iterative framework.

The paper reframes Parameter-Efficient Fine-Tuning (PEFT) from a mere cost-saving alternative to a robust architecture for creating persistent, personalized models that layer specific behaviors onto large shared foundation models.