Offline meta-reinforcement learning (OMRL) utilizes pre-collected offline datasets to enhance the agent's generalization ability on unseen tasks.

To ensure large language models (LLMs) are used safely, one must reduce their propensity to hallucinate or to generate unacceptable answers. A simple and often used strategy is to first let the LLM generate multiple hypotheses and then employ a reranker to choose the best one.

Consequently, we investigate how attribution gradients lead to uncertain explanation outcomes and introduce two forms of abnormalities for OOD detection: the zero-deflation abnormality and the channel-wise average abnormality.

TGNN[24]introduce3D-RESby extending the bounding box annotations of ScanRefer [5] to masks by incorporating the instance masks from ScanNet and proposed a two-stage pipeline. Further, 3D-STMN [65] proposed an end-to-end method that matches the text and superpoints to get the 3D segmentation of the target object directly.