6 accepted papers
Class-Incremental Learning (CIL) enables models to continuously learn new classes while mitigating catastrophic forgetting. Recently, Pre-Trained Models (PTMs) have greatly enhanced CIL performance, even when fine-tuning is limited to the first task. This advantage is particularly beneficial for CIL…
Logit-based knowledge distillation (KD) is commonly used to mitigate catastrophic forgetting in class-incremental learning (CIL) caused by data distribution shifts. However, the strict match of logit values between student and teacher models conflicts with the cross-entropy (CE) loss objective of le…
Continual learning (CL) empowers pre-trained vision-language (VL) models to efficiently adapt to a sequence of downstream tasks. However, these models often encounter challenges in retaining previously acquired skills due to parameter shifts and limited access to historical data. In response, recent…
Deep reinforcement learning has achieved encouraging performance in many realms. However, one of its primary challenges is the sparsity of extrinsic rewards, which is still far from solved. Complementary learning system theory suggests that effective human learning relies on two complementary learni…
In the real world, robot task plans may easily become invalid due to unexpected state dynamics, preventing the robot from accessing the complete task-relevant information. The possible occurrence of information incompleteness during robot plan execution expects the robot to sense the environment and
Robots operating in open environments expect to have robust plans to achieve tasks successfully under environment uncertainties. However, both partial observability and dynamics of environment states have significantly decreased the robustness of task achievement, making robot task planning much mor…