generalization capability
Generalization capability refers to an AI model's ability to perform well on unseen data that was not part of its training set, indicating the model's robustness and adaptability.
- 3DPE-Gaze:Unlocking the Potential of 3D Facial Priors for Generalized Gaze Estimation
- A Generalized Label Shift Perspective for Cross-Domain Gaze Estimation
- A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings
- Efficient Part-level 3D Object Generation via Dual Volume Packing
- GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation
- Interactive Anomaly Detection for Articulated Objects via Motion Anticipation
- Learning Robust Vision-Language Models from Natural Latent Spaces
- Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning
- Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning
- Rethinking Out-of-Distribution Detection and Generalization with Collective Behavior Dynamics
- RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domains
- Test3R: Learning to Reconstruct 3D at Test Time
- Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2