AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

DigimonGPT: An Evolvable Agent with Hierarchical Human-like Memory for Video Question Answering

Borui Li, Xingcai Zhang, Tianen Liu, Shuai Wang, Yun Cheng, Shuai Wang

AAAI 2026 · Vision-language and multimodal › Visual question answering · approach: Multimodal question answering datasets · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add semantic memory to episodic memory (ablation)DigimonGPT · NExT-QA (All)accuracy: 55.06 -> 60.67Improved
add semantic memory to episodic memory (ablation)DigimonGPT · NExT-QA (Descriptive)accuracy: 50.00 -> 43.75Hurt
add procedural memory to episodic memory (ablation)DigimonGPT · NExT-QA (All)accuracy: 55.06 -> 58.43Improved
add semantic memory on top of episodic and procedural memory (ablation)DigimonGPT · NExT-QA (All)accuracy: 58.43 -> 67.42Improved
add procedural memory on top of episodic and semantic memory (ablation)DigimonGPT · NExT-QA (All)accuracy: 60.67 -> 67.42Improved
add memory replay versus no replay (ablation)DigimonGPT · NExT-QA (All)accuracy: 55.06 -> 67.42Improved
use dynamic complexity-aware replay instead of fixed Ms=3, Mp=2 (ablation)DigimonGPT · NExT-QA (All)accuracy: 65.17 -> 67.42Improved
replay 5 memories of each type instead of dynamic amount (ablation)DigimonGPT · NExT-QA (All)accuracy: 67.42 -> 57.30Hurt
replay only 1 memory of each type instead of dynamic amount (ablation)DigimonGPT · NExT-QA (Descriptive)accuracy: 68.75 -> 43.75Mixed
increase beta from 0.2 to 0.3 (ablation)DigimonGPT · NExT-QA (All)accuracy: 67.42 -> 62.92Hurt
increase alpha from 0.03 to 0.05 (ablation)DigimonGPT · NExT-QA (All)accuracy: 67.42 -> 66.29Hurt
use normalized hyperparameters alpha=0.11, beta=0.89 (ablation)DigimonGPT · NExT-QA (All)accuracy: 67.42 -> 58.43Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy