Modern detection transformers (DETRs) use a set of object queries to predict a list of
bounding boxes, sort them by their classification confidence scores, and select the top …

This paper identifies significant redundancy in the query-key interactions within self-attention
mechanisms of diffusion transformer models, particularly during the early stages of …

Offline-to-online reinforcement learning (RL) is a training paradigm that combines pre-
training on a pre-collected dataset with fine-tuning in an online environment. However, the …

The divergence of the Q-value estimation has been a prominent issue offline reinforcement
learning (offline RL), where the agent has no access to real dynamics. Traditional beliefs …

In applying reinforcement learning (RL) to high-stakes domains, quantitative and qualitative
evaluation using observational data can help practitioners understand the generalization …

Offline reinforcement learning (RL) expects to get an optimal policy by utilizing offline data.
During policy learning, one typical method often constrains the target policy by offline data to …

In offline reinforcement learning, the challenge of out-of-distribution (OOD) is pronounced.
To address this, existing methods often constrain the learned policy through policy …

With the ability to learn from static datasets, Offline Reinforcement Learning (RL) emerges as
a compelling avenue for real-world applications. However, state-of-the-art offline RL …

In healthcare, clinicians constantly make decisions about when and how to treat each
patient. These decisions are based on medical training and clinical experience, but they …

Terrain preference learning from trajectory queries allows complex reward structures to be
obtained for robot navigation without the need for manual specification. However, traditional …