Large-scale pre-trained diffusion models are becoming increasingly popular in solving the Real-World Image Super-Resolution (Real-ISR) problem because of their rich generative priors. The recent development of diffusion transformer (DiT) has witnessed overwhelming performance over the traditional UNet-based architecture in image generation, which also raises the question: Can we adopt the advanced DiT-based diffusion model for Real-ISR? To this end, we propose our DiT4SR, one of the pioneering works to tame the large-scale DiT model for Real-ISR. Instead of directly injecting embeddings extracted from low-resolution (LR) images like ControlNet, we integrate the LR embeddings into the original attention mechanism of DiT, allowing for the bidirectional flow of information between the LR latent and the generated latent. The sufficient interaction of these two streams allows the LR stream to evolve with the diffusion process, producing progressively refined guidance that better aligns with the generated latent at each diffusion step. Additionally, the LR guidance is injected into the generated latent via a cross-stream convolution layer, compensating for DiT's limited ability to capture local information. These simple but effective designs endow the DiT model with superior performance in Real-ISR, which is demonstrated by extensive experiments. Project Page: https://adam-duan.github.io/projects/dit4sr/.

Learning a universal policy across different robot morphologies can significantly improve learning efficiency and enable zero-shot generalization to unseen morphologies. However, learning a highly performant universal policy requires sophisticated architectures like transformers (TF) that have larger memory and computational cost than simpler multi-layer perceptrons (MLP). To achieve both good performance like TF and high efficiency like MLP at inference time, we propose HyperDistill, which consists of: (1) A morphology-conditioned hypernetwork (HN) that generates robot-wise MLP policies, and (2) A policy distillation approach that is essential for successful training. We show that on UNIMAL, a benchmark with hundreds of diverse morphologies, HyperDistill performs as well as a universal TF teacher policy on both training and unseen test robots, but reduces model size by 6-14 times, and computational cost by 67-160 times in different environments. Our analysis attributes the efficiency advantage of HyperDistill at inference time to knowledge decoupling, i.e., the ability to decouple inter-task and intra-task knowledge, a general principle that could also be applied to improve inference efficiency in other domains. The code is publicly available at https://github.com/MasterXiong/Universal-Morphology-Control.

Crowd image is arguably one of the most laborious data to annotate. In this paper, we aim to reduce the massive demand for densely labeled crowd data, and propose a novel weakly-supervised setting, in which we leverage the binary ranking of two images with high-contrast crowd counts as training guidance. To enable training under this new setting, we convert the crowd count regression problem to a ranking potential prediction problem. In particular, we tailor a Siamese Ranking Network that predicts the potential scores of two images indicating the ordering of the counts. Hence, the ultimate goal is to assign appropriate potentials for all the crowd images to ensure their orderings obey the ranking labels. On the other hand, potentials reveal the relative crowd sizes but cannot yield an exact crowd count. We resolve this problem by introducing "anchors" during the inference stage. Concretely, anchors are a few images with count labels used for referencing the corresponding counts from potential scores by a simple linear mapping function. We conduct extensive experiments to study various combinations of supervision, and we show that our method outperforms existing weakly-supervised methods by a large margin without additional labeling effort. The code is available at https://github.com/pandaszzzzz/CCRanking.

State-of-charge (SoC) balancing in distributed energy storage systems (DESS) is crucial but challenging. Traditional deep reinforcement learning approaches struggle with real-world multiagent cooperation for SoC balance in these decentralized systems. To address these significant hurdles, this article pioneers an innovative fully-decentralized multiagent reinforcement learning (FDMARL) strategy, specifically tailored for DESS. First, the SoC balancing problem is formulated into a finite decentralized Markov decision process with action constraints derived from the microgrid context. Then, the average consensus algorithm is introduced for expanding the agent's observation and obtaining global information through a communication network. To improve multiagent system cooperation, a novel demand balance algorithm is proposed to refine agent actions for precise demand distribution. By the above modules, the FDMARL reveals outstanding performance in a fully-decentralized system without any expert experience or modeling. Finally, numerous simulations were carried out on pymgrid, (i.e., a Python-based open-source microgrid platform), which shows that: The FDMARL exceeds traditional reinforcement learning in decentralized cooperation, effectively manages large-scale systems with random states and demand/PV series, and maintains robustness with ESU failure or integration.

Learning a universal policy across different robot morphologies can significantly improve learning efficiency and generalization in continuous control. However, it poses a challenging multi-task reinforcement learning problem, as the optimal policy may be quite different across robots and critically depend on the morphology. Existing methods utilize graph neural networks or transformers to handle heterogeneous state and action spaces across different morphologies, but pay little attention to the dependency of a robot’s control policy on its morphology context. In this paper, we propose a hierarchical architecture to better model this dependency via contextual modulation, which includes two key submodules: (1) Instead of enforcing hard parameter sharing across robots, we use hypernetworks to generate morphology-dependent control parameters; (2) We propose a fixed attention mechanism that solely depends on the morphology to modulate the interactions between different limbs in a robot. Experimental results show that our method not only improves learning performance on a diverse set of training robots, but also generalizes better to unseen morphologies in a zero-shot fashion. The code is publicly available at https://github.com/MasterXiong/ModuMorph.

Deep reinforcement learning (RL) is notoriously impractical to deploy due to sample inefficiency. Meta-RL directly addresses this sample inefficiency by learning to perform few-shot learning when a distribution of related tasks is available for meta-training. While many specialized meta-RL methods have been proposed, recent work suggests that end-to-end learning in conjunction with an off-the-shelf sequential model, such as a recurrent network, is a surprisingly strong baseline. However, such claims have been controversial due to limited supporting evidence, particularly in the face of prior work establishing precisely the opposite. In this paper, we conduct an empirical investigation. While we likewise find that a recurrent network can achieve strong performance, we demonstrate that the use of hypernetworks is crucial to maximizing their potential. Surprisingly, when combined with hypernetworks, the recurrent baselines that are far simpler than existing specialized methods actually achieve the strongest performance of all methods evaluated. We provide code at https://github.com/jacooba/hyper.

Modern large-scale online service providers typically deploy microservices into containers to achieve flexible service management. One critical problem in such container-based microservice architectures is to control the arrival rate of requests in the containers to avoid containers from being overloaded. In this article, we present our experience of rate limit for the containers in Alibaba, one of the largest e-commerce services in the world. Given the highly diverse characteristics of containers in Alibaba, we point out that the existing rate limit mechanisms cannot meet our demand. Thus, we design Noah, a dynamic rate limiter that can automatically adapt to the specific characteristic of each container without human efforts. The key idea of Noah is to use deep reinforcement learning (DRL) that automatically infers the most suitable configuration for each container. To fully embrace the advantages of DRL in our context, Noah addresses two technical challenges. First, Noah uses a lightweight system monitoring mechanism to collect container status. In this way, it minimizes the monitoring overhead while ensuring a timely reaction to system load changes. Second, Noah injects synthetic extreme data when training its models. Thus, its model gains knowledge on unseen special events and hence remains highly available in extreme scenarios. To guarantee model convergence with the injected training data, Noah adopts task-specific curriculum learning to train the model from normal data to extreme data gradually. Noah has been deployed in the production of Alibaba for two years, serving more than 50000 containers and around 300 types of microservice applications. Experimental results show that Noah can well adapt to three common scenarios in the production environment. It effectively achieves better system availability and shorter request response time compared with four state-of-the-art rate limiters.

Human leukocyte antigen (HLA) complex molecules play an essential role in immune interactions by presenting peptides on the cell surface to T cells. With significant deep learning progress, a series of neural network-based models have been proposed and demonstrated with their excellent performances for peptide-HLA class I binding prediction. However, there is still a lack of effective binding prediction models for HLA class II protein binding with peptides due to its inherent challenges. We present a novel sequence-based pan-specific neural network structure, DeepSeaPanII, for peptide-HLA class II binding prediction in this work. Our model is an end-to-end neural network model without the need for pre-or post-processing on input samples compared with existing pan-specific models. Besides state-of-the-art performance in binding affinity prediction, DeepSeqPanII can also extract biological insight on the binding mechanism over the peptide by its attention mechanism-based binding core prediction capability. The leave-one-allele-out cross-validation and benchmark evaluation results show that our proposed network model achieved state-of-the-art performance in HLA-II peptide binding. The source code and trained models are freely available at https://github.com/pcpLiu/DeepSeqPanII.

Graph neural networks (GNNs) have been attracting increasing popularity due to their simplicity and effectiveness in a variety of fields. However, a large number of labeled data is generally required to train these networks, which could be very expensive to obtain in some domains. In this paper, we study active learning for GNNs, i.e., how to efficiently label the nodes on a graph to reduce the annotation cost of training GNNs. We formulate the problem as a sequential decision process on graphs and train a GNN-based policy network with reinforcement learning to learn the optimal query strategy. By jointly training on several source graphs with full labels, we learn a transferable active learning policy which can directly generalize to unlabeled target graphs. Experimental results on multiple datasets from different domains prove the effectiveness of the learned policy in promoting active learning performance in both settings of transferring between graphs in the same domain and across different domains.