AI Paper Atlas

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

Transferable Model-agnostic Vision-Language Model Adaptation for Efficient Weak-to-Strong Generalization

Jihwan Park, Taehoon Song, Sanghyeok Lee, Miso Choi, Hyunwoo J. Kim

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Test-time adaptation of VLMs · 0 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
use TransMiter adaptation transfer instead of target zero-shotCLIP target VLMs · 11 datasets base-to-baseaccuracy: RN50->ViT-B/16: 65.33 -> 77.16Improved
use TransMiter instead of EFTadaptation transfer · 11 datasets base-to-baseaccuracy / GFLOPs: e.g. 81.04 -> 82.05; 35.16 -> 0.01 GFLOPsImproved
use TransMiter instead of Prompt Transferadaptation transfer · ViT-B/16 -> ViT-L/14 PromptSRCaccuracy: 73.41 -> 82.51Improved
use a stronger source model (ViT-B/16 instead of RN50) (ablation)TransMiter with ViT-L/14 target · 11 datasets base-to-baseaccuracy: 80.39 -> 82.05Improved
use PromptSRC instead of CoOp for source fine-tuning (ablation)TransMiter · ViT-B/16 -> ViT-L/14accuracy: 82.05 -> 82.51Improved
use TransMiter instead of baselines on novel classestarget ViT-L/14 · base-to-novel averagenovel accuracy: 80.85 (zero-shot) -> 81.07Mixed
add auxiliary class expansion to the prediction adapter (ablation)TransMiter target · base-to-novel HMHM: 80.09 -> 81.24Improved
add basis change to the prediction adapter (ablation)TransMiter target · base-to-novel HMHM: 80.09 -> 80.80Improved
combine auxiliary classes and basis change (ablation)TransMiter target · base-to-baseaccuracy: 76.25 -> 82.51Improved
fine-tune TransMiter with labeled data (TransMiter+)supervised fine-tuning strategies · base-to-novel HM, ViT-L/14HM: PromptSRC 84.28 -> 84.69; MaPLe 82.35 -> 84.37Improved
use TransMiter+ with HPT/LwEIB strategyHPT, LwEIB · base-to-novel HMHM: HPT 84.95 -> 85.02; LwEIB 84.75 -> 84.96No clear effect
use TransMiter instead of Prompt Transfer for transfer costadaptation transfer · StanfordCars efficiencytransfer time (s): 480 -> 24Improved

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