We provide more architecture and training details of the proposed HiT as well as additional experimental results to help better understand our paper. MQA is identical except that the different heads share a single set of keys and values. We report detailed results in Table 1 on ImageNet 128 128 . "pixel shuffle" indicates the pixel shuffle operation [ " indicates the blocking operation producing non-overlapping feature blocks, each of which has We use Tensorflow for implementation. We provide the detailed description about the generative process of the proposed HiT in Algorithm 1. See Algorithm 3 for more details about blocking and unblocking. X and Y are blocked feature maps where m is # of patches and n is patch sequence length. Args: X: a tensor used as query with shape [b, m, n, d] Y: a tensor used as key and value with shape [b, m, n, d] W_q: a tensor projecting query with shape [h, d, k] W_k: a tensor projecting key with shape [d, k] W_v: a tensor projecting value with shape [d, v] W_o: a tensor projecting output with shape [h, d, v] Returns: Z: a tensor with shape [b, m, n, d] """ Q = tf.einsum("bmnd,hdk->bhmnk",

We provide more architecture and training details of the proposed HiT as well as additional experimental results to help better understand our paper. MQA is identical except that the different heads share a single set of keys and values. We report detailed results in Table 1 on ImageNet 128 128 . "pixel shuffle" indicates the pixel shuffle operation [ " indicates the blocking operation producing non-overlapping feature blocks, each of which has We use Tensorflow for implementation. We provide the detailed description about the generative process of the proposed HiT in Algorithm 1. See Algorithm 3 for more details about blocking and unblocking. X and Y are blocked feature maps where m is # of patches and n is patch sequence length. Args: X: a tensor used as query with shape [b, m, n, d] Y: a tensor used as key and value with shape [b, m, n, d] W_q: a tensor projecting query with shape [h, d, k] W_k: a tensor projecting key with shape [d, k] W_v: a tensor projecting value with shape [d, v] W_o: a tensor projecting output with shape [h, d, v] Returns: Z: a tensor with shape [b, m, n, d] """ Q = tf.einsum("bmnd,hdk->bhmnk",

Figure 5: Graphical representation of the normalized performance of the best trained policy on D4RL averaged over 4 random seeds. Figure 15: Graphical representation of the normalized performance of the last trained policy on D4RL after online tuning averaged over 4 random seeds. Our codebase is released under Apache License 2.0. For most of the algorithms and datasets, we use default hyperparameters if available. Decision Transformer (DT) training is splitted into datasets pass epochs.

In CORL, we isolate methods implementation into separate single files, making performance-relevant details easier to recognize.

Offline reinforcement learning (RL) enables learning effective policies from fixed datasets without any environment interaction. Existing methods typically employ policy constraints to mitigate the distribution shift encountered during offline RL training. However, because the scale of the constraints varies across tasks and datasets of differing quality, existing methods must meticulously tune hyperparameters to match each dataset, which is time-consuming and often impractical. We propose Adaptive Scaling of Policy Constraints (ASPC), a second-order differentiable framework that dynamically balances RL and behavior cloning (BC) during training. We theoretically analyze its performance improvement guarantee. In experiments on 39 datasets across four D4RL domains, ASPC using a single hyperparameter configuration outperforms other adaptive constraint methods and state-of-the-art offline RL algorithms that require per-dataset tuning while incurring only minimal computational overhead. The code will be released at https://github.com/Colin-Jing/ASPC.

Online movie review websites are valuable for information and discussion about movies. However, the massive spoiler reviews detract from the movie-watching experience, making spoiler detection an important task. Previous methods simply focus on reviews' text content, ignoring the heterogeneity of information in the platform. For instance, the metadata and the corresponding user's information of a review could be helpful. Besides, the spoiler language of movie reviews tends to be genre-specific, thus posing a domain generalization challenge for existing methods. To this end, we propose MMoE, a multi-modal network that utilizes information from multiple modalities to facilitate robust spoiler detection and adopts Mixture-of-Experts to enhance domain generalization. MMoE first extracts graph, text, and meta feature from the user-movie network, the review's textual content, and the review's metadata respectively. To handle genre-specific spoilers, we then adopt Mixture-of-Experts architecture to process information in three modalities to promote robustness. Finally, we use an expert fusion layer to integrate the features from different perspectives and make predictions based on the fused embedding. Experiments demonstrate that MMoE achieves state-of-the-art performance on two widely-used spoiler detection datasets, surpassing previous SOTA methods by 2.56% and 8.41% in terms of accuracy and F1-score. Further experiments also demonstrate MMoE's superiority in robustness and generalization.