Ning Wang

Andrey Ignatov, Radu Timofte, Cheng-Ming Chiang et al.

Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS training dataset containing video sequences for a 4X video upscaling task. The runtime and power efficiency of all models was evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit capable of accelerating floating-point and quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt / 30 FPS] power consumption. A detailed description of all models developed in the challenge is provided in this paper.

Ning Wang, Jiahao Xie, Jihao Wu et al.

Despite the remarkable progress of image captioning, existing captioners typically lack the controllable capability to generate desired image captions, e.g., describing the image in a rough or detailed manner, in a factual or emotional view, etc. In this paper, we show that a unified model is qualified to perform well in diverse domains and freely switch among multiple styles. Such a controllable capability is achieved by embedding the prompt learning into the image captioning framework. To be specific, we design a set of prompts to fine-tune the pre-trained image captioner. These prompts allow the model to absorb stylized data from different domains for joint training, without performance degradation in each domain. Furthermore, we optimize the prompts with learnable vectors in the continuous word embedding space, avoiding the heuristic prompt engineering and meanwhile exhibiting superior performance. In the inference stage, our model is able to generate desired stylized captions by choosing the corresponding prompts. Extensive experiments verify the controllable capability of the proposed method. Notably, we achieve outstanding performance on two diverse image captioning benchmarks including COCO Karpathy split and TextCaps using a unified model.

Ning Wang, Han Liu, Diego Klabjan

We develop an abstractive summarization framework independent of labeled data for multiple heterogeneous documents. Unlike existing multi-document summarization methods, our framework processes documents telling different stories instead of documents on the same topic. We also enhance an existing sentence fusion method with a uni-directional language model to prioritize fused sentences with higher sentence probability with the goal of increasing readability. Lastly, we construct a total of twelve dataset variations based on CNN/Daily Mail and the NewsRoom datasets, where each document group contains a large and diverse collection of documents to evaluate the performance of our model in comparison with other baseline systems. Our experiments demonstrate that our framework outperforms current state-of-the-art methods in this more generic setting.

Wenjing Zhang, Xuejiao Lei, Zhaoxiang Liu et al.

Recently, the DeepSeek series of models, leveraging their exceptional reasoning capabilities and open-source strategy, is reshaping the global AI landscape. Despite these advantages, they exhibit significant safety deficiencies. Research conducted by Robust Intelligence, a subsidiary of Cisco, in collaboration with the University of Pennsylvania, revealed that DeepSeek-R1 has a 100\% attack success rate when processing harmful prompts. Additionally, multiple safety companies and research institutions have confirmed critical safety vulnerabilities in this model. As models demonstrating robust performance in Chinese and English, DeepSeek models require equally crucial safety assessments in both language contexts. However, current research has predominantly focused on safety evaluations in English environments, leaving a gap in comprehensive assessments of their safety performance in Chinese contexts. In response to this gap, this study introduces CHiSafetyBench, a Chinese-specific safety evaluation benchmark. This benchmark systematically evaluates the safety of DeepSeek-R1 and DeepSeek-V3 in Chinese contexts, revealing their performance across safety categories. The experimental results quantify the deficiencies of these two models in Chinese contexts, providing key insights for subsequent improvements. It should be noted that, despite our efforts to establish a comprehensive, objective, and authoritative evaluation benchmark, the selection of test samples, characteristics of data distribution, and the setting of evaluation criteria may inevitably introduce certain biases into the evaluation results. We will continuously optimize the evaluation benchmark and periodically update this report to provide more comprehensive and accurate assessment outcomes. Please refer to the latest version of the paper for the most recent evaluation results and conclusions.

Nuoye Xiong, Anqi Dong, Ning Wang et al.

Recent advances in deep learning have led to increasingly complex models with deeper layers and more parameters, reducing interpretability and making their decisions harder to understand. While many methods explain black-box reasoning, most lack effective interventions or only operate at sample-level without modifying the model itself. To address this, we propose the Concept Bottleneck Model for Enhancing Human-Neural Network Mutual Understanding (CBM-HNMU). CBM-HNMU leverages the Concept Bottleneck Model (CBM) as an interpretable framework to approximate black-box reasoning and communicate conceptual understanding. Detrimental concepts are automatically identified and refined (removed/replaced) based on global gradient contributions. The modified CBM then distills corrected knowledge back into the black-box model, enhancing both interpretability and accuracy. We evaluate CBM-HNMU on various CNN and transformer-based models across Flower-102, CIFAR-10, CIFAR-100, FGVC-Aircraft, and CUB-200, achieving a maximum accuracy improvement of 2.64% and a maximum increase in average accuracy across 1.03%. Source code is available at: https://github.com/XiGuaBo/CBM-HNMU.

Yishuang Tian, Ning Wang, Liang Zhang

The current deep neural network algorithm still stays in the end-to-end training supervision method like Image-Label pairs, which makes traditional algorithm is difficult to explain the reason for the results, and the prediction logic is difficult to understand and analyze. The current algorithm does not use the existing human knowledge information, which makes the model not in line with the human cognition model and makes the model not suitable for human use. In order to solve the above problems, the present invention provides a deep neural network training method based on the human knowledge, which uses the human cognition model to construct the deep neural network training model, and uses the existing human knowledge information to construct the deep neural network training model. This paper proposes a multi-level hierarchical deep learning algorithm, which is composed of multi-level hierarchical deep neural network architecture and multi-level hierarchical deep learning framework. The experimental results show that the proposed algorithm can effectively explain the hidden information of the neural network. The goal of our study is to improve the interpretability of deep neural networks (DNNs) by providing an analysis of the impact of knowledge injection on the classification task. We constructed a knowledge injection dataset with matching knowledge data and image classification data. The knowledge injection dataset is the benchmark dataset for the experiments in the paper. Our model expresses the improvement in interpretability and classification task performance of hidden layers at different scales.

Ning Wang, Jiajun Deng, Mingbo Jia

We present that visual grounding and image captioning, which perform as two mutually inverse processes, can be bridged together for collaborative training by careful designs. By consolidating this idea, we introduce CyCo, a cyclic-consistent learning framework to ameliorate the independent training pipelines of visual grounding and image captioning. The proposed framework (1) allows the semi-weakly supervised training of visual grounding; (2) improves the performance of fully supervised visual grounding; (3) yields a general captioning model that can describe arbitrary image regions. Extensive experiments show that our fully supervised grounding model achieves state-of-the-art performance, and the semi-weakly supervised one also exhibits competitive performance compared to the fully supervised counterparts. Our image captioning model has the capability to freely describe image regions and meanwhile shows impressive performance on prevalent captioning benchmarks.

Jie Li, Haifeng Liu, Chuanghua Gui et al.

We present the design and implementation of a visual search system for real time image retrieval on JD.com, the world's third largest and China's largest e-commerce site. We demonstrate that our system can support real time visual search with hundreds of billions of product images at sub-second timescales and handle frequent image updates through distributed hierarchical architecture and efficient indexing methods. We hope that sharing our practice with our real production system will inspire the middleware community's interest and appreciation for building practical large scale systems for emerging applications, such as ecommerce visual search.

Yutai Hou, Zhihan Zhou, Yijia Liu et al.

While few-shot classification has been widely explored with similarity based methods, few-shot sequence labeling poses a unique challenge as it also calls for modeling the label dependencies. To consider both the item similarity and label dependency, we propose to leverage the conditional random fields (CRFs) in few-shot sequence labeling. It calculates emission score with similarity based methods and obtains transition score with a specially designed transfer mechanism. When applying CRF in the few-shot scenarios, the discrepancy of label sets among different domains makes it hard to use the label dependency learned in prior domains. To tackle this, we introduce the dependency transfer mechanism that transfers abstract label transition patterns. In addition, the similarity methods rely on the high quality sample representation, which is challenging for sequence labeling, because sense of a word is different when measuring its similarity to words in different sentences. To remedy this, we take advantage of recent contextual embedding technique, and further propose a pair-wise embedder. It provides additional certainty for word sense by embedding query and support sentence pairwisely. Experimental results on slot tagging and named entity recognition show that our model significantly outperforms the strongest few-shot learning baseline by 11.76 (21.2%) and 12.18 (97.7%) F1 scores respectively in the one-shot setting.

Ning Wang, Yang Gao, Hao Chen et al.

The success of deep neural networks relies on significant architecture engineering. Recently neural architecture search (NAS) has emerged as a promise to greatly reduce manual effort in network design by automatically searching for optimal architectures, although typically such algorithms need an excessive amount of computational resources, e.g., a few thousand GPU-days. To date, on challenging vision tasks such as object detection, NAS, especially fast versions of NAS, is less studied. Here we propose to search for the decoder structure of object detectors with search efficiency being taken into consideration. To be more specific, we aim to efficiently search for the feature pyramid network (FPN) as well as the prediction head of a simple anchor-free object detector, namely FCOS, using a tailored reinforcement learning paradigm. With carefully designed search space, search algorithms and strategies for evaluating network quality, we are able to efficiently search a top-performing detection architecture within 4 days using 8 V100 GPUs. The discovered architecture surpasses state-of-the-art object detection models (such as Faster R-CNN, RetinaNet and FCOS) by 1.5 to 3.5 points in AP on the COCO dataset, with comparable computation complexity and memory footprint, demonstrating the efficacy of the proposed NAS for object detection.