AI Paper Atlas

Research map / Video / Video-language understanding

SPIKE-RL: Video-LLMs meet Bayesian Surprise

Sahithya Ravi, Aditya Chinchure, Raymond T. Ng, Leonid Sigal, Vered Shwartz

ICLR 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
add GRPO belief optimization (SPIKE-RL) (ablation)SPIKE · Oops! surprise localizationAcc@0.25s: 60.0 -> 62.9Improved
add GRPO belief optimization (SPIKE-RL) (ablation)SPIKE · FunQA surprise localizationIoU: 65.7 -> 68.2Improved
add GRPO belief optimization (SPIKE-RL) (ablation)SPIKE · Mr. Bean surprise localizationIoU: 54.8 -> 61.1Improved
add GRPO belief optimization (SPIKE-RL) (ablation)SPIKE · belief diversity1-cos similarity: 33.5% -> 40.3%Improved
add GRPO belief optimization (SPIKE-RL) (ablation)SPIKE · Oops! human correlationSpearman correlation: 0.84 -> 0.87Improved
replace uniform sampling with SPIKE surprise-weighted samplingQwen2.5-VL-7B · BlackSwanaccuracy: 67.2 -> 68.8Improved
replace uniform sampling with SPIKE-RL samplingQwen2.5-VL-7B · ExFunTubeLLM-Match: 68.7 -> 75.7Improved
replace uniform sampling with SPIKE-RL samplingQwen2.5-VL-7B · VideoMME-Saccuracy: 59.8 -> 62.5Improved
replace uniform sampling with SPIKE-RL samplingQwen2.5-VL-7B · NextQAaccuracy: 68.6 -> 70.3Improved
replace uniform sampling with SPIKE-RL samplingQwen2.5-VL-32B · VideoMME-Saccuracy: 69.9 -> 73.5Improved
replace uniform sampling with SPIKE-RL samplingQwen2.5-VL-32B · FunQA (Task 2)LLM-Match: 72.7 -> 75.8Improved
use RGB histogram shot-boundary sampling instead of uniformQwen2.5-VL-7B · BlackSwanaccuracy: 67.2 -> 49.6Hurt

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