| Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP | Dec 1, 2024 | Natural Language Understandingzero-shot-classification | CodeCode Available | 0 |
| AdaCBM: An Adaptive Concept Bottleneck Model for Explainable and Accurate Diagnosis | Aug 4, 2024 | ClassificationDiagnostic | CodeCode Available | 0 |
| Understanding Visual Concepts Across Models | Jun 11, 2024 | Image Generationobject-detection | CodeCode Available | 0 |
| Describe me an Aucklet: Generating Grounded Perceptual Category Descriptions | Mar 7, 2023 | nlg evaluationRepresentation Learning | CodeCode Available | 0 |
| DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation | Jul 14, 2025 | DecoderGPU | CodeCode Available | 0 |
| I can listen but cannot read: An evaluation of two-tower multimodal systems for instrument recognition | Jul 25, 2024 | Instrument RecognitionRetrieval | CodeCode Available | 0 |
| Data-Free Generalized Zero-Shot Learning | Jan 28, 2024 | Generalized Zero-Shot Learningzero-shot-classification | CodeCode Available | 0 |
| Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks | Oct 5, 2023 | Contrastive LearningData Poisoning | CodeCode Available | 0 |
| Uniformity First: Uniformity-aware Test-time Adaptation of Vision-language Models against Image Corruption | May 19, 2025 | Knowledge DistillationTest-time Adaptation | CodeCode Available | 0 |
| WYTIWYR: A User Intent-Aware Framework with Multi-modal Inputs for Visualization Retrieval | Apr 14, 2023 | Retrievalzero-shot-classification | CodeCode Available | 0 |
