AI Paper Atlas

Research map / Video / Video-language understanding

NeuS-QA: Grounding Long-Form Video Understanding in Temporal Logic and Neuro-Symbolic Reasoning

Sahil Shah, S P Sharan, Harsh Goel, Minkyu Choi, Mustafa Munir, Manvik Pasula, Radu Marculescu, Sandeep Chinchali

AAAI 2026 · Video › Video-language understanding · approach: Video question answering · 3 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 NeuS-QA segment retrieval to Qwen2.5-VLQwen2.5-VL-7B · LongVideoBench (reasoning subset)overall accuracy (%): 50.44 -> 60.09Improved
add NeuS-QA to GPT-4oGPT-4o · LongVideoBench (reasoning subset)overall accuracy (%): 49.56 -> 58.33Improved
add NeuS-QA to LLaVA-OneVisionLLaVA-OneVision-Qwen2-7B · LongVideoBench (reasoning subset)overall accuracy (%): 53.07 -> 58.77Improved
add NeuS-QA to AriaAria · LongVideoBench (reasoning subset)overall accuracy (%): 53.07 -> 58.77Improved
add NeuS-QA to Qwen2.5-VL on CinePileQwen2.5-VL-7B · CinePileaccuracy (%): 50.73 -> 53.66Improved
add NeuS-QA to GPT-4o on E3E questionsGPT-4o · LongVideoBench E3Eaccuracy (%): 58.11 -> 68.92Improved
add NeuS-QA to GPT-4o on T3E questionsGPT-4o · LongVideoBench T3Eaccuracy (%): 43.40 -> 49.06Mixed
replace temporal-logic automaton with VLM-only relevance judgement (ablation)NeuS-QA · LongVideoBench (GPT-4o answerer, ablation)accuracy (%): 40.09 -> 58.33Improved
use InternVL2-8B instead of Qwen2.5-VL to build the automaton (ablation)NeuS-QA · LongVideoBench (GPT-4o answerer, ablation)accuracy (%): 52.63 -> 58.33Improved
trim to relevant segments instead of dynamic scaling (ablation)NeuS-QA · LongVideoBench (GPT-4o answerer, ablation)accuracy (%): 53.51 -> 58.33Improved
trim to relevant segments instead of speed bias sampling (ablation)NeuS-QA · LongVideoBench (GPT-4o answerer, ablation)accuracy (%): 52.19 -> 58.33Improved
use NeuS-QA segments instead of ground-truth annotated segmentsNeuS-QA · LongVideoBenchaccuracy (%): 52 -> 59Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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