AI Paper Atlas

Research map / Video / Video-language understanding

Incentivizing Vision Language Models to Search for Long Video Question Answering

Harsh Goel, S P Sharan, Sahil Shah, Minkyu Choi, Joungbin An, Kristen Grauman, Sandeep Chinchali

ECCV 2026 · Video › Video-language understanding · approach: Video question answering · 2 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 VETL temporal-logic reward to exact-match reward (ablation)VSeek (GRPO, Qwen3-VL-4B-Thinking) · MLVUPass@1: 66.7 -> 67.9Improved
add VETL reward to exact-match reward (ablation)VSeek · Video-MMEPass@1: 59.3 -> 61.4Improved
add VETL reward to exact-match reward (ablation)VSeek · LongVideoBenchPass@1: 60.5 -> 60.9Improved
add VETL reward to exact-match reward (ablation)VSeek · LVBench and CGBench-mini (OOD)Pass@1: 40.0 -> 38.8; 33.2 -> 32.3Hurt
post-train with search and RL (VSeek-VETL) vs direct base inferenceQwen3-VL-4B-Thinking · LongVideoBenchPass@1: 51.7 -> 60.9Improved
use temporal-logic decomposition instead of direct decomposition for rewards (ablation)VSeek-VETL · MLVUPass@1: 66.3 -> 67.9Improved
use temporal-logic decomposition instead of direct decomposition (ablation)VSeek-VETL · Video-MMEPass@1: 59.3 -> 61.4Improved
use VETL specification instead of direct decomposition (judge score) (ablation)VSeek reward pipeline · GPT-5.2 judge mean score (0-6)score: 3.8 -> 5.3Improved
add VETL reward to RLOO training (ablation)VSeek with RLOO · LongVideoBenchPass@1: 58.0 -> 60.4Improved
add VETL reward to GSPO training (ablation)VSeek with GSPO · MLVUPass@1: 67.7 -> 62.7Hurt
add VETL reward to GSPO training (ablation)VSeek with GSPO · Video-MMEPass@1: 62.9 -> 58.1Hurt
add VETL reward on Instruct base model (ablation)VSeek-Ins · MLVUPass@1: 60.3 -> 66.1Improved

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