Deep generative models have unlocked another profound realm of human creativity. By capturing and generalizing patterns within data, we have entered the epoch of all-encompassing Artificial Intelligence for General Creativity (AIGC). Notably, diffusion models, recognized as one of the paramount generative models, materialize human ideation into tangible instances across diverse domains, encompassing imagery, text, speech, biology, and healthcare. To provide advanced and comprehensive insights into diffusion, this survey comprehensively elucidates its developmental trajectory and future directions from three distinct angles: the fundamental formulation of diffusion, algorithmic enhancements, and the manifold applications of diffusion. Each layer is meticulously explored to offer a profound comprehension of its evolution. Structured and summarized approaches are presented here.

Trajectory prediction has been a crucial task in building a reliable autonomous driving system by anticipating possible dangers. One key issue is to generate consistent trajectory predictions without colliding. To overcome the challenge, we propose an efficient masked autoencoder for trajectory prediction (Traj-MAE) that better represents the complicated behaviors of agents in the driving environment. Specifically, our Traj-MAE employs diverse masking strategies to pre-train the trajectory encoder and map encoder, allowing for the capture of social and temporal information among agents while leveraging the effect of environment from multiple granularities. To address the catastrophic forgetting problem that arises when pre-training the network with multiple masking strategies, we introduce a continual pre-training framework, which can help Traj-MAE learn valuable and diverse information from various strategies efficiently. Our experimental results in both multi-agent and single-agent settings demonstrate that Traj-MAE achieves competitive results with state-of-the-art methods and significantly outperforms our baseline model. Project page: https://jiazewang.com/projects/trajmae.html.

The current throughput of conventional organic chemical synthesis is usually a few experiments for each operator per day. We develop a robotic system for ultra-high-throughput chemical synthesis, online characterization, and large-scale condition screening of photocatalytic reactions, based on the liquid-core waveguide, microfluidic liquid-handling, and artificial intelligence techniques. The system is capable of performing automated reactant mixture preparation, changing, introduction, ultra-fast photocatalytic reactions in seconds, online spectroscopic detection of the reaction product, and screening of different reaction conditions. We apply the system in large-scale screening of 12,000 reaction conditions of a photocatalytic [2 + 2] cycloaddition reaction including multiple continuous and discrete variables, reaching an ultra-high throughput up to 10,000 reaction conditions per day. Based on the data, AI-assisted cross-substrate/photocatalyst prediction is conducted.

Session-based recommendation (SBR) systems aim to utilize the user’s short-term behavior sequence to predict the next item without the detailed user profile.Most recent works try to model the user preference by treating the sessions as between-item transition graphs and utilize various graph neural networks (GNNs) to encode the representations of pair-wise relations among items and their neighbors. Some of the existing GNN-based models mainly focus on aggregating information from the view of spatial graph structure, which ignores the temporal relations within neighbors of an item during message passing and the information loss results in a sub-optimal problem. Other works embrace this challenge by incorporating additional temporal information but lack sufficient interaction between the spatial and temporal patterns. To address this issue, inspired by the uniformity and alignment properties of contrastive learning techniques, we propose a novel framework called Session-based Recommendation with Spatio-temporal Contrastive Learning-enhanced GNNs (RESTC). The idea is to supplement the GNN-based main supervised recommendation task with the temporal representation via an auxiliary cross-view contrastive learning mechanism. Furthermore, a novel global collaborative filtering graph embedding is leveraged to enhance the spatial view in the main task.Extensive experiments demonstrate the significant performance of RESTC compared with the state-of-the-art baselines. We release our source code athttps://github.com/SUSTechBruce/RESTC-Source-code.