AI Paper Atlas

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

RLAP-CLIP: Continual Multimodal Learning with Prototype Adaptation and Difficulty-Aware Routing

Ruikun Luo, Jiarui Wang, Yuan Gao, Jing Yang, Jieming Yang, Song Wu, Hai Jin, Xiaoyu Xia

ICLR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs

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 visual prompts to text-only prompting (ablation)PROOF base · Eight datasets averageaverage accuracy (%): 78.97 -> 79.64 (+0.67)Improved
add difficulty-aware MoE routing (ablation)RLAP-CLIP with VP · Eight datasets averageaverage accuracy (%): 79.64 -> 80.79 (+1.15)Improved
add RLPO prototype optimization (ablation)RLAP-CLIP with VP+MoE · Eight datasets averageaverage accuracy (%): 80.79 -> 81.98 (+1.19)Improved
add cross-modal attention fusion (CMF) (ablation)RLAP-CLIP with VP+MoE+RLPO · Eight datasets averageaverage accuracy (%): 81.98 -> 82.87 (+0.89)Improved
add visual prompts on Food-101 versus Aircraft (ablation)PROOF base · Food-101 and Aircraftaverage accuracy (%): Aircraft +1.24, Food-101 +0.16Mixed
add dual-modal prompting versus no prompting (ablation)CLIP prompting · CUB-200separation ratio: 1.90 -> 3.11Improved
use dual-modal rather than text-only prompting (ablation)CLIP prompting · CUB-200separation ratio: 2.74 -> 3.11Improved
replace simple averaging with learned RLPO weights (ablation)prototype construction · Aircraftaccuracy (%): 56.32 -> 67.85Improved
replace simple averaging with RLPO weights (ablation)prototype construction · ObjectNetaccuracy (%): 41.27% simple averagingImproved
add quality-weighted averaging and then RLPO on CUB-200 (ablation)prototype construction · CUB-200accuracy (%): 79.86 -> 83.42Improved
increase lambda_RLPO from 0.2 to 1.0 (ablation)RLAP-CLIP · UCF-101accuracy (%): 97.68 -> 92.15Hurt
increase difficulty weight beta to 1.0 (ablation)RLAP-CLIP · CUB-200 and Aircraftaccuracy (%): CUB-200 -4.44 points, Aircraft -4.58 pointsHurt

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