AI Paper Atlas

Research map / Video / Video generation

AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction

Junhao Cheng, Yuying Ge, Yixiao Ge, Jing Liao, Ying Shan

ICCV 2025 · Video › Video generation · approach: World-model video generation · 6 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
use first frame instead of random frame for visual feature f_v (ablation)AnimeGamer encoder · Ablation on tokenizer/de-tokenizer (Qiqi film, w/o MLLM)ACC-F: 0.4744 -> 0.7293Improved
use MLP instead of single Linear layer in E_a (ablation)AnimeGamer encoder · Ablation on tokenizer/de-tokenizer (Qiqi film, w/o MLLM)ACC-F: 0.3649 -> 0.7293Improved
combine f_v and f_md by concatenation instead of element-wise addition (ablation)AnimeGamer encoder · Ablation on tokenizer/de-tokenizer (Qiqi film, w/o MLLM)CLIP-I: 0.7684 -> 0.8672Improved
combine f_v and f_md by concatenation instead of cross-attention (ablation)AnimeGamer encoder · Ablation on tokenizer/de-tokenizer (Qiqi film, w/o MLLM)ACC-F: 0.3284 -> 0.7293Improved
add warm-up training phase for E_a (ablation)AnimeGamer encoder · Ablation on tokenizer/de-tokenizer (Qiqi film, w/o MLLM)ACC-F: 0.7028 -> 0.7293Improved
add motion scope f_ms to the decoder D_a (ablation)AnimeGamer decoder · Ablation on tokenizer/de-tokenizer (Qiqi film, w/o MLLM)ACC-F: 0.1824 -> 0.7293Improved
add motion scope f_ms to the decoder D_a (ablation)AnimeGamer decoder · Ablation on tokenizer/de-tokenizer (Qiqi film, w/o MLLM)MAE-F: 1.2189 -> 0.4029Improved
add cosine similarity loss for MLLM training (ablation)AnimeGamer · Ablation on next game state prediction/decoder adaptation (Qiqi film, with MLLM)ACC-F: 0.6722 -> 0.6649No clear effect
add cosine similarity loss for MLLM training (ablation)AnimeGamer · Ablation on next game state prediction/decoder adaptation (Qiqi film, with MLLM)CLIP-I: 0.7856 -> 0.7628Hurt
add decoder adaptation training phase (ablation)AnimeGamer · Ablation on next game state prediction/decoder adaptation (Qiqi film, with MLLM)CLIP-I: 0.6831 -> 0.7856Improved
add decoder adaptation training phase (ablation)AnimeGamer · Ablation on next game state prediction/decoder adaptation (Qiqi film, with MLLM)ACC-F: 0.3649 -> 0.6722Improved
use action-aware multimodal MLLM game state prediction instead of fine-tuned CogVideoX (GC)AnimeGamer vs GC · Anime life simulation benchmark (automatic)ACC-F: 0.4249 -> 0.6744Improved

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