Fangyu Li

Fangyu Li, Shenbao Yu, Feng Zeng et al.

There has been a growing interest in benchmarking sequential recommendation models and reproducing/improving existing models. For example, Rendle et al. improved matrix factorization models by tuning their parameters and hyperparameters. Petrov and Macdonald developed a more efficient and effective implementation of BERT4Rec, which resolved inconsistencies in performance comparison between BERT4Rec and SASRec in previous works. In particular, BERT4Rec and SASRec share a similar network structure, with the main difference lying in their training objective/loss function. Therefore, we analyzed the advantages and disadvantages of commonly used loss functions in sequential recommendation and proposed an improved loss function that leverages their strengths. We conduct extensive experiments on two influential open-source libraries, and the results demonstrate that our improved loss function significantly enhances the performance of GRU4Rec, SASRec, SR-GNN, and S3Rec models, improving their benchmarks significantly. Furthermore, the improved SASRec benchmark outperforms BERT4Rec on the ML-1M and Beauty datasets and achieves similar results to BERT4Rec on the ML-20M and Steam datasets. We also reproduce the results of the BERT4Rec model on the Beauty dataset. Finally, we provide a comprehensive explanation of the effectiveness of our improved loss function through experiments. Our code is publicly available at https://github.com/Li-fAngyU/sequential_rec.

Junyi Liu, Yifu Tang, Haimeng Zhao et al.

Cybersecurity breaches are the common anomalies for distributed cyber-physical systems (CPS). However, the cyber security breach classification is still a difficult problem, even using cutting-edge artificial intelligence (AI) approaches. In this paper, we study the multi-class classification problem in cyber security for attack detection. A challenging multi-node data-censoring case is considered. In such a case, data within each data center/node cannot be shared while the local data is incomplete. Particularly, local nodes contain only a part of the multiple classes. In order to train a global multi-class classifier without sharing the raw data across all nodes, the main result of our study is designing a multi-node multi-class classification ensemble approach. By gathering the estimated parameters of the binary classifiers and data densities from each local node, the missing information for each local node is completed to build the global multi-class classifier. Numerical experiments are given to validate the effectiveness of the proposed approach under the multi-node data-censoring case. Under such a case, we even show the out-performance of the proposed approach over the full-data approach.

Jiaqi Tan, Fangyu Li, Yang Liu

Instruction driven image editing with standard CLIP text encoders often fails in complex scenes with many objects. We present QL-Adapter, a framework for multiple object editing that tackles two challenges: enforcing object counts and spatial layouts, and accommodating diverse categories. QL-Adapter consists of two core modules: the Image-Layout Fusion Module (ILFM) and the Cross-Modal Augmentation Module (CMAM). ILFM fuses layout priors with ViT patch tokens from the CLIP image encoder to strengthen spatial structure understanding. CMAM injects image features into the text branch to enrich textual embeddings and improve instruction following. We further build QL-Dataset, a benchmark that spans broad category, layout, and count variations, and define the task of quantity and layout consistent image editing (QL-Edit). Extensive experiments show that QL-Adapter achieves state of the art performance on QL-Edit and significantly outperforms existing models.

Jiaqi Tan, Xu Zheng, Fangyu Li et al.

Multimodal semantic segmentation enhances model robustness by exploiting cross-modal complementarities. However, existing methods often suffer from imbalanced modal dependencies, where overall performance degrades significantly once a dominant modality deteriorates in real-world scenarios. Thus, modality balance has become acritical challenge for practical multimodal segmentation. To address this issue, we propose EQUISeg, a multimodal segmentation framework that balances modality contributions through equal encoding of modalities. Built upon a four-stage Cross-modal Transformer Block(CMTB), EQUISeg enables efficient multimodal fusion and hierarchical selection. Furthermore, we design a Self-guided Module(SGM) that mitigates modality imbalance by introducing a mutual guidance mechanism, enabling each modality to adaptively adjust its contribution and enhance robustness under degraded conditions. Extensive experiments on multiple datasets demonstrate that EQUISeg achieves significant performance gains and effectively alleviates the adverse effects of modality imbalance in segmentation tasks.

Adam W. Harley, Shrinidhi K. Lakshmikanth, Fangyu Li et al.

Predictive coding theories suggest that the brain learns by predicting observations at various levels of abstraction. One of the most basic prediction tasks is view prediction: how would a given scene look from an alternative viewpoint? Humans excel at this task. Our ability to imagine and fill in missing information is tightly coupled with perception: we feel as if we see the world in 3 dimensions, while in fact, information from only the front surface of the world hits our retinas. This paper explores the role of view prediction in the development of 3D visual recognition. We propose neural 3D mapping networks, which take as input 2.5D (color and depth) video streams captured by a moving camera, and lift them to stable 3D feature maps of the scene, by disentangling the scene content from the motion of the camera. The model also projects its 3D feature maps to novel viewpoints, to predict and match against target views. We propose contrastive prediction losses to replace the standard color regression loss, and show that this leads to better performance on complex photorealistic data. We show that the proposed model learns visual representations useful for (1) semi-supervised learning of 3D object detectors, and (2) unsupervised learning of 3D moving object detectors, by estimating the motion of the inferred 3D feature maps in videos of dynamic scenes. To the best of our knowledge, this is the first work that empirically shows view prediction to be a scalable self-supervised task beneficial to 3D object detection.

Minhui Zou, Yang Shi, Chengliang Wang et al.

With the popularity of deep learning (DL), artificial intelligence (AI) has been applied in many areas of human life. Neural network or artificial neural network (NN), the main technique behind DL, has been extensively studied to facilitate computer vision and natural language recognition. However, the more we rely on information technology, the more vulnerable we are. That is, malicious NNs could bring huge threat in the so-called coming AI era. In this paper, for the first time in the literature, we propose a novel approach to design and insert powerful neural-level trojans or PoTrojan in pre-trained NN models. Most of the time, PoTrojans remain inactive, not affecting the normal functions of their host NN models. PoTrojans could only be triggered in very rare conditions. Once activated, however, the PoTrojans could cause the host NN models to malfunction, either falsely predicting or classifying, which is a significant threat to human society of the AI era. We would explain the principles of PoTrojans and the easiness of designing and inserting them in pre-trained deep learning models. PoTrojans doesn't modify the existing architecture or parameters of the pre-trained models, without re-training. Hence, the proposed method is very efficient.