AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation

Sicheng Yang, Yukai Huang, Weitong Cai, Shitong Sun, You He, Jiankang Deng, Hang Zhang, Jifei Song, Zhensong Zhang

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs · 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 iterative dialogue-driven text clarifier to a small LLMQwen2.5-7B · CLAMBERvagueness judgement accuracy (%): 24.4 -> 53.0Improved
add iterative dialogue-driven text clarifier to a small LLMLlama-3.1-8B · CLAMBERvagueness judgement accuracy (%): 25.9 -> 52.9Improved
add text clarifier to a large LLMLlama-3.1-405B · CLAMBERvagueness judgement accuracy (%): 54.9 -> 60.1Improved
add vision clarifier (open-set detector plus geometric quality checks)GPT-4o · VRA-Ego visual ambiguitystrict recover rate (%): 40.6 -> 61.4Improved
add vision clarifierQwen2.5-VL · VRA-Ego visual ambiguitytarget identification accuracy (%): 86.6 -> 91.2Improved
add cross-modal 3D pointing ray-casting with context-aware cropGPT-4o · VRA-Ego referential ambiguitysemantic answer recover rate (%): 65.2 -> 69.0Improved
add cross-modal pointing clarifierQwen2.5-VL · VRA-Ego referential ambiguitysemantic answer recover rate (%): 57.8 -> 64.4Improved
swap default open-set detector for Florence-2 (ablation)Vision clarifier · VRA-Ego visual ambiguityaccuracy / recover rate: about 1% accuracy, 3% recover rate dropHurt
swap default detector for YOLOE or YOLO-World (ablation)Vision clarifier · VRA-Ego visual ambiguityaccuracy / recover rate: about 2% accuracy, 5% recover rate dropHurt
replace custom fingertip detector with MediaPipe (ablation)Cross-modal clarifier · VRA-Ego referential ambiguitypointing success accuracy: 15% decreaseHurt
use context-aware cropping instead of point-based segmentation or full image (ablation)Cross-modal clarifier · VRA-Ego referential ambiguitysemantic answer recover rateImproved

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