multi-task learning
Multi-task learning involves training a single model on multiple related tasks simultaneously. This approach leverages shared representations across tasks, which can improve the model's ability to learn and generalize by reducing overfitting and promoting knowledge transfer.
- CSI-Bench: A Large-Scale In-the-Wild Dataset for Multi-task WiFi Sensing
- Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning
- Continual Optimization with Symmetry Teleportation for Multi-Task Learning
- Diffusion Transformers as Open-World Spatiotemporal Foundation Models
- DynaPhArM: Adaptive and Physics-Constrained Modeling for Target-Drug Complexes with Drug-Specific Adaptations
- Exploring Tradeoffs through Mode Connectivity for Multi-Task Learning
- Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes
- FlowFeat: Pixel-Dense Embedding of Motion Profiles
- MTL-KD: Multi-Task Learning Via Knowledge Distillation for Generalizable Neural Vehicle Routing Solver
- Meta-World+: An Improved, Standardized, RL Benchmark
- NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective
- PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts
- SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing
- SynCL: A Synergistic Training Strategy with Instance-Aware Contrastive Learning for End-to-End Multi-Camera 3D Tracking