| Group Activity Recognition using Unreliable Tracked Pose | Jan 6, 2024 | Activity RecognitionAll | —Unverified | 0 |
| Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM | Jan 4, 2024 | All | —Unverified | 0 |
| k-Winners-Take-All Ensemble Neural Network | Jan 4, 2024 | AllMixture-of-Experts | CodeCode Available | 0 |
| Distraction is All You Need: Memory-Efficient Image Immunization against Diffusion-Based Image Editing | Jan 1, 2024 | AllDenoising | —Unverified | 0 |
| Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers | Jan 1, 2024 | AllBackdoor Attack | CodeCode Available | 1 |
| AM-RADIO: Agglomerative Vision Foundation Model Reduce All Domains Into One | Jan 1, 2024 | AllBenchmarking | —Unverified | 0 |
| Jack of All Tasks Master of Many: Designing General-Purpose Coarse-to-Fine Vision-Language Model | Jan 1, 2024 | AllAttribute | —Unverified | 0 |
| One-dimensional Adapter to Rule Them All: Concepts Diffusion Models and Erasing Applications | Jan 1, 2024 | AllImage Generation | —Unverified | 0 |
| Multimodal Prompt Perceiver: Empower Adaptiveness Generalizability and Fidelity for All-in-One Image Restoration | Jan 1, 2024 | AllDecoder | —Unverified | 0 |
| ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks | Jan 1, 2024 | All | —Unverified | 0 |