Technology
TFLEX: Temporal Feature-Logic Embedding Framework for Complex Reasoning over Temporal Knowledge Graph
Reasoning over TKGs has two challenges: 1.
Successor-Predecessor Intrinsic Exploration Changmin Y u 1,2 Neil Burgess
Exploration is essential in reinforcement learning, particularly in environments where external rewards are sparse. Here we focus on exploration with intrinsic rewards, where the agent transiently augments the external rewards with self-generated intrinsic rewards.
Multi-Scale Representation Learning for Protein Fitness Prediction
Given the limited availability of functional annotations from wet-lab experiments, previous methods have primarily relied on self-supervised models trained on vast, unlabeled protein sequence or structure datasets.
Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery
CPG enables the model to fully capture the intra-category diversity by representing each category with multiple prototypes.
A Appendix
Usage Application The model is intended for open-vocabulary object detection.Known Caveats
Scaling Open-Vocabulary Object Detection
Major challenges in scaling self-training are the choice of label space, pseudo-annotation filtering, and training efficiency.
Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis
The remarkable success of transformers in sequence modeling tasks, spanning various applications in natural language processing and computer vision, is attributed to the critical role of self-attention.