AI Paper Atlas

Research map / Video / Video-language understanding

A Very Big Video Reasoning Suite

Maijunxian Wang, Ruisi Wang, Juyi Lin, Ran Ji, Thaddäus Wiedemer, Qingying Gao, Dezhi Luo, Yaoyao Qian, Lianyu Huang, Zelong Hong, Jiahui Ge, Qianli Ma and 43 more

ICML 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 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
fine-tune Wan2.2-I2V-A14B with LoRA on VBVR-Dataset (500K samples)Wan2.2-I2V-A14B · VBVR-Bench overallscore: 0.371 -> 0.685Improved
scale training data from 0K to 400K samples (ablation)VBVR-Wan2.2 · VBVR-Bench in-domainscore: 0.412 -> 0.771Improved
increase training data beyond 400K samples (ablation)VBVR-Wan2.2 · VBVR-Bench in-domainscore: 0.771 -> 0.760No clear effect
scale training data from 0K to 500K samples (ablation)VBVR-Wan2.2 · VBVR-Bench out-of-domainscore: 0.329 -> 0.610Improved
increase training data from 200K to 500K samples (ablation)VBVR-Wan2.2 · VBVR-Bench overallscore: 0.689 -> 0.685No clear effect
apply the same VBVR fine-tuning to a different backbone (LTX-2.3) (ablation)LTX-2.3 · VBVR-Bench overallscore: 0.516 overallImproved
LoRA fine-tune on VBVR-DatasetWan2.2-I2V-A14B · VBench-I2V camera motion consistencyscore: 0.5444 -> 0.6592Improved
LoRA fine-tune on VBVR-DatasetWan2.2-I2V-A14B · VBench-I2V dynamic degreescore: 0.5285 -> 0.4106Hurt
LoRA fine-tune on VBVR-DatasetWan2.2-I2V-A14B · VBench-I2V total scorescore: 0.8816 -> 0.8835No clear effect

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