| BRDF estimation | Computer Vision | 10 | 0 |
| Chinese Semantic Role Labeling | Language & Reasoning | 10 | 0 |
| Conditional Text-to-Image Synthesis Introducing extra conditions based on the text-to-image gene… | Multimodal & Vision-Language | 10 | 0 |
| Consistent Character Generation Given a text prompt describing a character, we need to disti… | Computer Vision | 10 | 0 |
| Continued fraction | Medical & Scientific | 10 | 0 |
| Correlated Time Series Forecasting | Time Series & Forecasting | 10 | 0 |
| Cross-Lingual Semantic Textual Similarity | Language & Reasoning | 10 | 0 |
| Cross-modal place recognition text-to-point-cloud place recognition | Multimodal & Vision-Language | 10 | 0 |
| Data Ablation Data Ablation is the study of change in data, and its effect… | Computer Vision | 10 | 0 |
| Diffusion Personalization Tuning Free This is a sub-class of diffusion personalization methods whe… | Computer Vision | 10 | 0 |
| Drone-view target localization (Drone -> Satellite) Given one drone-view image or video, th… | Computer Vision | 10 | 0 |
| Dynamic Node Classification node classification on temporal graphs | Graphs & Structured Data | 10 | 0 |
| EEG based sleep staging Sleep staging from only EEG signal | Medical & Scientific | 10 | 0 |
| Generalized Zero-Shot Object Detection | Computer Vision | 10 | 0 |
| GitHub issue resolution | Computer Vision | 10 | 0 |
| Human-Object Interaction Generation Generate image based on given human-object interaction input | Computer Vision | 10 | 0 |
| Image Classification with Label Noise | Computer Vision | 10 | 0 |
| Infant Brain Mri Segmentation | Medical & Scientific | 10 | 0 |
| Learning Network Representations | Time Series & Forecasting | 10 | 0 |
| Mathematical Induction Tests the language model's capability to understand inductio… | Language & Reasoning | 10 | 0 |
| Modality completion | Computer Vision | 10 | 0 |
| Multi-Domain Recommender Systems | Recommendation & Retrieval | 10 | 0 |
| Multi-Label Image Retrieval | Computer Vision | 10 | 0 |
| Multi-modal Named Entity Recognition Multi-modal named entity recognition aims at improving the a… | Language & Reasoning | 10 | 0 |
| One-shot Unsupervised Domain Adaptation | Computer Vision | 10 | 0 |
| Online surgical phase recognition Online surgical phase recognition: the first 40 videos to tr… | Medical & Scientific | 10 | 0 |
| Only Connect Walls Dataset Task 1 (Grouping) Split data into groups, taking into account knowledge in the… | Language & Reasoning | 10 | 0 |
| open vocabulary 3d instance segmentation | Computer Vision | 10 | 0 |
| Outdoor Positioning Outdoor Positioning (e.g. GPS) | Computer Vision | 10 | 0 |
| Overlapped 15-1 | Language & Reasoning | 10 | 0 |
| Overlapped 15-5 | Language & Reasoning | 10 | 0 |
| Phone-level pronunciation scoring | Audio & Speech | 10 | 0 |
| Physical Commonsense Reasoning | Language & Reasoning | 10 | 0 |
| Polyp Segmentation The goal of the project is to develop a computer-aided detec… | Computer Vision | 10 | 0 |
| Predict Future Video Frames | Computer Vision | 10 | 0 |
| Pupil Tracking | Computer Vision | 10 | 0 |
| RGB-T Salient Object Detection RGB-T Salient Object Detection (SOD) focuses on identifying … | Computer Vision | 10 | 0 |
| Self-supervised Video Retrieval | Computer Vision | 10 | 0 |
| Semantic Shift Detection Detect the semantic change of a word between two corpora | Computer Vision | 10 | 0 |
| Silent Speech Recognition Interpret speech without acoustic signals | Audio & Speech | 10 | 0 |
| Singer Identification | Audio & Speech | 10 | 0 |
| Single Image Desnowing | Computer Vision | 10 | 0 |
| Skeleton Based Action Segmentation | Computer Vision | 10 | 0 |
| Slice Discovery | Foundations & Efficiency | 10 | 0 |
| Split-CIFAR-10 | Computer Vision | 10 | 0 |
| Stroke Classification | Medical & Scientific | 10 | 0 |
| Text-to-Face Generation | Computer Vision | 10 | 0 |
| Uncertainty Visualization Visualize uncertainty in restoration models. | Computer Vision | 10 | 0 |
| Unsupervised MNIST | Foundations & Efficiency | 10 | 0 |
| Unsupervised Spatial Clustering | Computer Vision | 10 | 0 |
