AI Paper Atlas

Research map / Video / Video-language understanding

WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs

Jack Hong, Shilin Yan, Jiayin Cai, Xiaolong Jiang, Yao Hu, Weidi Xie

ICLR 2026 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 139 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 original audio to video (ablation)Gemini 1.5 Pro · WorldSenseaccuracy (%): 34.4 -> 48.0Improved
add subtitles to video (ablation)Gemini 1.5 Pro · WorldSenseaccuracy (%): 34.4 -> 39.3Improved
add original audio to video (ablation)Qwen2.5-Omni · WorldSenseaccuracy (%): 39.2 -> 45.2Improved
add subtitles to video (ablation)Qwen2.5-Omni · WorldSenseaccuracy (%): 39.2 -> 39.2No clear effect
add subtitles to video (ablation)Unified-IO-2 L · WorldSenseaccuracy (%): 26.6 -> 14.8Hurt
add original audio to video (ablation)Unified-IO-2 L · WorldSenseaccuracy (%): 26.6 -> 23.3Hurt
add original audio instead of subtitles (ablation)VideoLLaMA2 · WorldSenseaccuracy (%): 26.1 vs 25.4Mixed
add subtitles to video-only MLLM (ablation)Qwen2-VL · WorldSenseaccuracy (%): 32.4 -> 41.2Improved
add subtitles to video-only MLLM (ablation)GPT 4o · WorldSenseaccuracy (%): 42.6 -> 50.1Improved
add subtitles to video-only MLLM (ablation)Video-LLaVA · WorldSenseaccuracy (%): 20.3 -> 16.0Hurt
add video frames to audio-only input (ablation)Gemini 1.5 Pro · WorldSenseaccuracy (%): 34.6 -> 48.0Improved
use audio-visual MLLM instead of video-only MLLMopen-source models · WorldSenseaccuracy (%)Hurt

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