AI Paper Atlas

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

Flexible Concept Bottleneck Model

Xingbo Du, Qiantong Dou, Lei Fan, Rui Zhang

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Test-time adaptation of VLMs · 1 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 sparsemax instead of hard truncation to 30 concepts (ablation)FCBM, ViT-L/14 · CIFAR100 zero-shot with DeepSeek-V3 conceptsaccuracy (%): 23.61 -> 62.27Improved
add sparsemax instead of hard truncation to 30 concepts (ablation)FCBM, ResNet50 · CIFAR10 zero-shot with DeepSeek-V3 conceptsaccuracy (%): 54.00 -> 75.32Improved
add sparsemax instead of hard truncation to 30 concepts (ablation)FCBM, ViT-L/14 · ImageNet zero-shot with DeepSeek-V3 conceptsaccuracy (%): 15.07 -> 51.70Improved
add learnable temperature instead of default unlearnable temperature (ablation)FCBM, ViT-L/14 · CIFAR100 zero-shot with DeepSeek-V3 conceptsaccuracy (%): 38.54 -> 62.27Improved
add learnable temperature instead of default unlearnable temperature (ablation)FCBM, ResNet50 · CIFAR10 trained conceptsaccuracy (%): 81.27 -> 85.59Improved
add learnable temperature instead of default unlearnable temperature (ablation)FCBM, ResNet50 · CUB trained conceptsaccuracy (%): 29.45 -> 63.92Improved
add sparsemax instead of hard truncation (ablation)FCBM, ResNet50 · Places365 trained conceptsaccuracy (%): 49.85 -> 49.13Hurt
add sparsemax instead of hard truncation (ablation)FCBM, ViT-L/14 · CIFAR10 trained conceptsaccuracy (%): 97.27 -> 97.21No clear effect
replace the full concept pool with GPT-4o-generated concepts without fine-tuning (ablation)FCBM, ViT-L/14 · CIFAR10accuracy (%): 97.21 -> 94.19Hurt
replace the full concept pool with DeepSeek-V3 concepts without fine-tuning (ablation)FCBM, ResNet50 · CUBaccuracy (%): 63.92 -> 18.07Hurt
use FCBM hypernetwork-sparsemax instead of linear layer (LF-CBM)ViT-L/14 backbone · CIFAR100 (NEC about 30)accuracy (%): 81.98 -> 83.63Improved
use FCBM instead of LF-CBMResNet50 backbone · CUB (NEC about 30)accuracy (%): 56.91 -> 63.46Improved

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