AI Paper Atlas

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

DVLA-RL: Dual-Level Vision–Language Alignment with Reinforcement Learning Gating for Few-Shot Learning

Wenhao Li, Xianjing Meng, Qiangchang Wang, Zhongyi Han, Zhibin Wu, Yilong Yin

ICLR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 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 attribute-level semantics and RL-gated attention to the baseline (ablation)baseline · miniImageNet 1-shotaccuracy: 68.67 -> 75.73Improved
add description-level semantics to Attr + Top-k + RLA (ablation)DVLA-RL · miniImageNet 1-shotaccuracy: 76.56 -> 81.69Improved
add progressive Top-k attribute selection (ablation)DVLA-RL Attr + RLA · miniImageNet 1-shotaccuracy: 75.73 -> 76.56Improved
add progressive Top-k attribute selection (ablation)DVLA-RL Attr + RLA · miniImageNet 5-shotaccuracy: 85.76 -> 85.25Hurt
add progressive Top-k attribute selection (ablation)DVLA-RL Attr + RLA · CUB 1-shotaccuracy: 88.63 -> 89.33Improved
add description-level semantics to attribute-level model (ablation)DVLA-RL Attr + Top-k + RLA · CUB 5-shotaccuracy: 90.91 -> 95.06Improved
replace summation gating with RL gate (ablation)DVLA-RL · miniImageNet 1-shotaccuracy: 79.63 -> 81.69Improved
replace MLP gating with RL gate (ablation)DVLA-RL · miniImageNet 1-shotaccuracy: 80.05 -> 81.69Improved
replace ECER fusion with RLA module (ablation)DVLA-RL · miniImageNet 1-shotaccuracy: 79.35 -> 81.69Improved
use DSC semantics instead of class-name semantics (ablation)DVLA-RL · miniImageNet 1-shotaccuracy: 78.96 -> 81.69Improved
increase Beta concentration kappa from 5 to 20 (ablation)DVLA-RL · miniImageNet 1-shotaccuracy: 81.69 -> 81.58No clear effect
increase RL weight lambda from 0.1 to 1.0 (ablation)DVLA-RL · miniImageNet 1-shotaccuracy: 81.69 -> 81.08Hurt

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