Smartphones provide an attractive yet challenging platform for human activity recognition (HAR). They are ubiquitous, but also limit the input of HAR systems to a single IMU. These systems are also challenged by the inherent diversity of human activities and varying phone placement on the user’s body. This results in traditional smartphone HAR systems having limited personalization potential or imposing a high user burden. We propose ActivitySeeker, a personalized smartphone HAR system that combines self-supervised activity discovery and low-burden user interaction to collaboratively label IMU data and adapt HAR models to individual users on-device through transfer learning. We evaluated ActivitySeeker through simulated online learning and in-the-wild user experiments, where it discovered 95.5% of personal activity types and achieved high recognition accuracy (93.3%) while maintaining a positive user experience. Leveraging the synergy between user and smartphone, ActivitySeeker opens up new possibilities for HAR-based applications like fitness, health and personalized recommendation.

Recent advances in structure-based drug design (SBDD) have produced surprising results, with models often generating molecules that achieve better Vina docking scores than actual ligands. However, these results are frequently overly optimistic due to the limitations of docking score accuracy and the challenges of wet-lab validation. While generated molecules may demonstrate high QED (drug-likeness) and SA (synthetic accessibility) scores, they often lack true drug-like properties or synthesizability. To address these limitations, we propose a model-level evaluation framework that emphasizes practical metrics aligned with real-world applications. Inspired by recent findings on the utility of generated molecules in ligand-based virtual screening, our framework evaluates SBDD models by their ability to produce molecules that effectively retrieve active compounds from chemical libraries via similarity-based searches. This approach provides a direct indication of therapeutic potential, bridging the gap between theoretical performance and real-world utility. Our experiments reveal that while SBDD models may excel in theoretical metrics like Vina scores, they often fall short in these practical metrics. By introducing this new evaluation strategy, we aim to enhance the relevance and impact of SBDD models for pharmaceutical research and development.

Small molecules are vital to modern medicine, and accurately predicting their bioactivity against protein targets is crucial for therapeutic discovery and development. However, current machine learning models often rely on spurious features, leading to biased outcomes. Notably, a simple pocket-only baseline can achieve results comparable to, and sometimes better than, more complex models that incorporate both the protein pockets and the small molecules. Our analysis reveals that this phenomenon arises from insufficient training data and an improper evaluation process, which is typically conducted at the pocket level rather than the small molecule level. To address these issues, we redefine the bioactivity prediction task by introducing the SIU dataset-a million-scale Structural small molecule-protein Interaction dataset for Unbiased bioactivity prediction task, which is 50 times larger than the widely used PDBbind. The bioactivity labels in SIU are derived from wet experiments and organized by label types, ensuring greater accuracy and comparability. The complexes in SIU are constructed using a majority vote from three commonly used docking software programs, enhancing their reliability. Additionally, the structure of SIU allows for multiple small molecules to be associated with each protein pocket, enabling the redefinition of evaluation metrics like Pearson and Spearman correlations across different small molecules targeting the same protein pocket. Experimental results demonstrate that this new task provides a more challenging and meaningful benchmark for training and evaluating bioactivity prediction models, ultimately offering a more robust assessment of model performance.

Structure-guided molecular generation is pivotal in early-stage drug discovery, enabling the design of compounds tailored to specific protein targets. However, despite recent advances in 3D generative modeling, particularly in improving docking scores, these methods often produce rare and intrinsically irrational molecular structures that deviate from drug-like chemical space. To quantify this issue, we propose a novel metric, the Molecule Reasonable Ratio (MRR), which measures structural rationality and reveals a critical gap between existing models and real-world approved drugs. To address this, we introduce the Collaborative Intelligence Drug Design (CIDD) framework, the first approach to unify the 3D interaction modeling capabilities of generative models with the general knowledge and reasoning power of large language models (LLMs). By leveraging LLM-based Chain-of-Thought reasoning, CIDD generates molecules that not only bind effectively to protein pockets but also exhibit strong structural drug-likeness, rationality, and synthetic accessibility. On the CrossDocked2020 benchmark, CIDD consistently improves drug-likeness metrics, including QED, SA, and MRR, across different base generative models, while maintaining competitive binding affinity. Notably, it raises the combined success rate (balancing drug-likeness and binding) from 15.72% to 34.59%, more than doubling previous results. These findings demonstrate the value of integrating knowledge reasoning with geometric generation to advance AI-driven drug design.

Recently, a noticeable trend has emerged in developing pre-trained foundation models in the domains of CV and NLP. However, for molecular pre-training, there lacks a universal model capable of effectively applying to various categories of molecular tasks, since existing prevalent pre-training methods exhibit effectiveness for specific types of downstream tasks. Furthermore, the lack of profound understanding of existing pre-training methods, including 2D graph masking, 2D-3D contrastive learning, and 3D denoising, hampers the advancement of molecular foundation models. In this work, we provide a unified comprehension of existing pre-training methods through the lens of contrastive learning. Thus their distinctions lie in clustering different views of molecules, which is shown beneficial to specific downstream tasks. To achieve a complete and general-purpose molecular representation, we propose a novel pre-training framework, named UniCorn, that inherits the merits of the three methods, depicting molecular views in three different levels. SOTA performance across quantum, physicochemical, and biological tasks, along with comprehensive ablation study, validate the universality and effectiveness of UniCorn.

In the field of Structure-based Drug Design (SBDD), deep learning-based generative models have achieved outstanding performance in terms of docking score. However, further study shows that the existing molecular generative methods and docking scores both have lacked consideration in terms of specificity, which means that generated molecules bind to almost every protein pocket with high affinity. To address this, we introduce the Delta Score, a new metric for evaluating the specificity of molecular binding. To further incorporate this insight for generation, we develop an innovative energy-guided approach using contrastive learning, with active compounds as decoys, to direct generative models toward creating molecules with high specificity. Our empirical results show that this method not only enhances the delta score but also maintains or improves traditional docking scores, successfully bridging the gap between SBDD and real-world needs.

Curriculum learning is a training paradigm where machine learning models are trained in a meaningful order, inspired by the way humans learn curricula. Due to its capability to improve model generalization and convergence, curriculum learning has gained considerable attention and has been widely applied to various research domains. Nevertheless, as new curriculum learning methods continue to emerge, it remains an open issue to benchmark them fairly. Therefore, we develop CurBench, the first benchmark that supports systematic evaluations for curriculum learning. Specifically, it consists of 15 datasets spanning 3 research domains: computer vision, natural language processing, and graph machine learning, along with 3 settings: standard, noise, and imbalance. To facilitate a comprehensive comparison, we establish the evaluation from 2 dimensions: performance and complexity. CurBench also provides a unified toolkit that plugs automatic curricula into general machine learning processes, enabling the implementation of 15 core curriculum learning methods. On the basis of this benchmark, we conduct comparative experiments and make empirical analyses of existing methods. CurBench is open-source and publicly available at https://github.com/THUMNLab/CurBench.

This work focuses on an active topic in the HCI community, namely tutorial creation by demonstration. We present a novel tool named SmartRecorder that facilitates people, without video editing skills, creating video tutorials for smartphone interaction tasks. As automatic interaction trace extraction is a key component to tutorial generation, we seek to tackle the challenges of automatically extracting user interaction traces on smartphones from screencasts. Uniquely, with respect to prior research in this field, we combine computer vision techniques with IMU-based sensing algorithms, and the technical evaluation results show the importance of smartphone IMU data in improving system performance. With the extracted key information of each step, SmartRecorder generates instructional content initially and provides tutorial creators with a tutorial refinement editor designed based on a high recall (99.38%) of key steps to revise the initial instructional content. Finally, SmartRecorder generates video tutorials based on refined instructional content. The results of the user study demonstrate that SmartRecorder allows non-experts to create smartphone usage video tutorials with less time and higher satisfaction from recipients.

Due to the lack of trusted third parties as guarantees in peer-to-peer (P2P) networks, how to ensure trusted transactions between peers has become a research hotspot. However, the open and distributed characteristics of P2P networks have brought challenges to network security, and there are problems such as node fraud and unavailability of services in the network. To solve the problem of how to select trusted transaction peers in P2P groups, a new trust model, GT-Bidding, is proposed in this paper. This model follows the bidding process of human society. First, each service peer applies for a group of guarantee peers and carries out credit mortgages for this service. Second, based on the entropy and TOPSIS method (Technology for Order Preference by Similarity to an Ideal Solution) approaching the ideal solution, a set of ideal trading sequences is selected. Then, the transaction impact function is used to assign weights to the selected guarantee peers and service nodes, respectively; thus, the comprehensive trust of each service node can be calculated. Finally, the service peer is verified using feedback based on the specific confidence level, which encourages the reputation of the service and its guarantee peers to update. Experiments show that GT-Bidding improves the successful transaction rate and resists complex attacks.

The artificial potential field (APF) method is widely used for autonomous mobile robot path-planning due to its simplicity and mathematical elegance. However, most researches are focused on solving the path-planning problem in a stationary environment, where both targets and obstacles are stationary. This paper proposes a new APF method for path-planning of mobile robots in a dynamic environment where the target and obstacles are moving. First, the new force function and the relative threat coefficient function are defined. Then, a new APF path-planning algorithm based on the relative threat coefficient is presented. Finally, computer simulation and experiment are used to demonstrate the effectiveness of the dynamic path-planning scheme