| Manipulating and Mitigating Generative Model Biases without Retraining | Apr 3, 2024 | Backdoor AttackLanguage Modelling | —Unverified | 0 |
| Vocabulary Attack to Hijack Large Language Model Applications | Apr 3, 2024 | Language ModelingLanguage Modelling | —Unverified | 0 |
| GLEMOS: Benchmark for Instantaneous Graph Learning Model Selection | Apr 2, 2024 | Graph LearningLink Prediction | CodeCode Available | 0 |
| Asymptotics of Language Model Alignment | Apr 2, 2024 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Test-Time Model Adaptation with Only Forward Passes | Apr 2, 2024 | modelTest-time Adaptation | CodeCode Available | 2 |
| Using Interpretation Methods for Model Enhancement | Apr 2, 2024 | model | CodeCode Available | 0 |
| Learning-based model augmentation with LFRs | Apr 2, 2024 | Computational Efficiencymodel | CodeCode Available | 0 |
| Language Model Guided Interpretable Video Action Reasoning | Apr 2, 2024 | Action RecognitionDecision Making | CodeCode Available | 0 |
| Effective internal language model training and fusion for factorized transducer model | Apr 2, 2024 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Red-Teaming Segment Anything Model | Apr 2, 2024 | Image Segmentationmodel | CodeCode Available | 0 |
