Lu Wang

Zezhong Wang, Fangkai Yang, Lu Wang et al.

The jailbreak attack can bypass the safety measures of a Large Language Model (LLM), generating harmful content. This misuse of LLM has led to negative societal consequences. Currently, there are two main approaches to address jailbreak attacks: safety training and safeguards. Safety training focuses on further training LLM to enhance its safety. On the other hand, safeguards involve implementing external models or filters to prevent harmful outputs. However, safety training has constraints in its ability to adapt to new attack types and often leads to a drop in model performance. Safeguards have proven to be of limited help. To tackle these issues, we propose a novel approach called Self-Guard, which combines the strengths of both safety methods. Self-Guard includes two stages. In the first stage, we enhance the model's ability to assess harmful content, and in the second stage, we instruct the model to consistently perform harmful content detection on its own responses. The experiment has demonstrated that Self-Guard is robust against jailbreak attacks. In the bad case analysis, we find that LLM occasionally provides harmless responses to harmful queries. Additionally, we evaluated the general capabilities of the LLM before and after safety training, providing evidence that Self-Guard does not result in the LLM's performance degradation. In sensitivity tests, Self-Guard not only avoids inducing over-sensitivity in LLM but also can even mitigate this issue.

Yao Zhu, Yuefeng Chen, Wei Wang et al.

Learning generalized representations from limited training samples is crucial for applying deep neural networks in low-resource scenarios. Recently, methods based on Contrastive Language-Image Pre-training (CLIP) have exhibited promising performance in few-shot adaptation tasks. To avoid catastrophic forgetting and overfitting caused by few-shot fine-tuning, existing works usually freeze the parameters of CLIP pre-trained on large-scale datasets, overlooking the possibility that some parameters might not be suitable for downstream tasks. To this end, we revisit CLIP's visual encoder with a specific focus on its distinctive attention pooling layer, which performs a spatial weighted-sum of the dense feature maps. Given that dense feature maps contain meaningful semantic information, and different semantics hold varying importance for diverse downstream tasks (such as prioritizing semantics like ears and eyes in pet classification tasks rather than side mirrors), using the same weighted-sum operation for dense features across different few-shot tasks might not be appropriate. Hence, we propose fine-tuning the parameters of the attention pooling layer during the training process to encourage the model to focus on task-specific semantics. In the inference process, we perform residual blending between the features pooled by the fine-tuned and the original attention pooling layers to incorporate both the few-shot knowledge and the pre-trained CLIP's prior knowledge. We term this method as Semantic-Aware FinE-tuning (SAFE). SAFE is effective in enhancing the conventional few-shot CLIP and is compatible with the existing adapter approach (termed SAFE-A).

Wei Deng, Siyi Zhou, Jingchen Shu et al.

Recently, large language model (LLM) based text-to-speech (TTS) systems have gradually become the mainstream in the industry due to their high naturalness and powerful zero-shot voice cloning capabilities.Here, we introduce the IndexTTS system, which is mainly based on the XTTS and Tortoise model. We add some novel improvements. Specifically, in Chinese scenarios, we adopt a hybrid modeling method that combines characters and pinyin, making the pronunciations of polyphonic characters and long-tail characters controllable. We also performed a comparative analysis of the Vector Quantization (VQ) with Finite-Scalar Quantization (FSQ) for codebook utilization of acoustic speech tokens. To further enhance the effect and stability of voice cloning, we introduce a conformer-based speech conditional encoder and replace the speechcode decoder with BigVGAN2. Compared with XTTS, it has achieved significant improvements in naturalness, content consistency, and zero-shot voice cloning. As for the popular TTS systems in the open-source, such as Fish-Speech, CosyVoice2, FireRedTTS and F5-TTS, IndexTTS has a relatively simple training process, more controllable usage, and faster inference speed. Moreover, its performance surpasses that of these systems. Our demos are available at https://index-tts.github.io.

Run Luo, Lu Wang, Wanwei He et al.

Existing efforts in building Graphical User Interface (GUI) agents largely rely on the training paradigm of supervised fine-tuning on Large Vision-Language Models (LVLMs). However, this approach not only demands extensive amounts of training data but also struggles to effectively understand GUI screenshots and generalize to unseen interfaces. The issue significantly limits its application in real-world scenarios, especially for high-level tasks. Inspired by Reinforcement Fine-Tuning (RFT) in large reasoning models (e.g., DeepSeek-R1), which efficiently enhances the problem-solving capabilities of large language models in real-world settings, we propose \name, the first reinforcement learning framework designed to enhance the GUI capabilities of LVLMs in high-level real-world task scenarios, through unified action space rule modeling. By leveraging a small amount of carefully curated high-quality data across multiple platforms (including Windows, Linux, MacOS, Android, and Web) and employing policy optimization algorithms such as Group Relative Policy Optimization (GRPO) to update the model, \name achieves superior performance using only 0.02\% of the data (3K vs. 13M) compared to previous state-of-the-art methods like OS-Atlas across eight benchmarks spanning three different platforms (mobile, desktop, and web). These results demonstrate the immense potential of reinforcement learning based on unified action space rule modeling in improving the execution capabilities of LVLMs for real-world GUI agent tasks.

Wang Lu, Jindong Wang, Yiqiang Chen et al.

There is a growing interest in applying machine learning techniques to healthcare. Recently, federated learning (FL) is gaining popularity since it allows researchers to train powerful models without compromising data privacy and security. However, the performance of existing FL approaches often deteriorates when encountering non-iid situations where there exist distribution gaps among clients, and few previous efforts focus on personalization in healthcare. In this article, we propose FedAP to tackle domain shifts and then obtain personalized models for local clients. FedAP learns the similarity between clients based on the statistics of the batch normalization layers while preserving the specificity of each client with different local batch normalization. Comprehensive experiments on five healthcare benchmarks demonstrate that FedAP achieves better accuracy compared to state-of-the-art methods (e.g., 10% accuracy improvement for PAMAP2) with faster convergence speed.

Yiqiang Chen, Wang Lu, Jindong Wang et al.

The success of machine learning applications often needs a large quantity of data. Recently, federated learning (FL) is attracting increasing attention due to the demand for data privacy and security, especially in the medical field. However, the performance of existing FL approaches often deteriorates when there exist domain shifts among clients, and few previous works focus on personalization in healthcare. In this article, we propose FedHealth 2, an extension of FedHealth \cite{chen2020fedhealth} to tackle domain shifts and get personalized models for local clients. FedHealth 2 obtains the client similarities via a pretrained model, and then it averages all weighted models with preserving local batch normalization. Wearable activity recognition and COVID-19 auxiliary diagnosis experiments have evaluated that FedHealth 2 can achieve better accuracy (10%+ improvement for activity recognition) and personalized healthcare without compromising privacy and security.

Wang Lu, Yiqiang Chen, Jindong Wang et al.

It is expensive and time-consuming to collect sufficient labeled data for human activity recognition (HAR). Domain adaptation is a promising approach for cross-domain activity recognition. Existing methods mainly focus on adapting cross-domain representations via domain-level, class-level, or sample-level distribution matching. However, they might fail to capture the fine-grained locality information in activity data. The domain- and class-level matching are too coarse that may result in under-adaptation, while sample-level matching may be affected by the noise seriously and eventually cause over-adaptation. In this paper, we propose substructure-level matching for domain adaptation (SSDA) to better utilize the locality information of activity data for accurate and efficient knowledge transfer. Based on SSDA, we propose an optimal transport-based implementation, Substructural Optimal Transport (SOT), for cross-domain HAR. We obtain the substructures of activities via clustering methods and seeks the coupling of the weighted substructures between different domains. We conduct comprehensive experiments on four public activity recognition datasets (i.e. UCI-DSADS, UCI-HAR, USC-HAD, PAMAP2), which demonstrates that SOT significantly outperforms other state-of-the-art methods w.r.t classification accuracy (9%+ improvement). In addition, our mehtod is 5x faster than traditional OT-based DA methods with the same hyper-parameters.

Luyang Huang, Lingfei Wu, Lu Wang

Sequence-to-sequence models for abstractive summarization have been studied extensively, yet the generated summaries commonly suffer from fabricated content, and are often found to be near-extractive. We argue that, to address these issues, the summarizer should acquire semantic interpretation over input, e.g., via structured representation, to allow the generation of more informative summaries. In this paper, we present ASGARD, a novel framework for Abstractive Summarization with Graph-Augmentation and semantic-driven RewarD. We propose the use of dual encoders---a sequential document encoder and a graph-structured encoder---to maintain the global context and local characteristics of entities, complementing each other. We further design a reward based on a multiple choice cloze test to drive the model to better capture entity interactions. Results show that our models produce significantly higher ROUGE scores than a variant without knowledge graph as input on both New York Times and CNN/Daily Mail datasets. We also obtain better or comparable performance compared to systems that are fine-tuned from large pretrained language models. Human judges further rate our model outputs as more informative and containing fewer unfaithful errors.

Lu Wang, Wenchao Yu, Wei Wang et al.

Graph representation learning, aiming to learn low-dimensional representations which capture the geometric dependencies between nodes in the original graph, has gained increasing popularity in a variety of graph analysis tasks, including node classification and link prediction. Existing representation learning methods based on graph neural networks and their variants rely on the aggregation of neighborhood information, which makes it sensitive to noises in the graph. In this paper, we propose Graph Denoising Policy Network (short for GDPNet) to learn robust representations from noisy graph data through reinforcement learning. GDPNet first selects signal neighborhoods for each node, and then aggregates the information from the selected neighborhoods to learn node representations for the down-stream tasks. Specifically, in the signal neighborhood selection phase, GDPNet optimizes the neighborhood for each target node by formulating the process of removing noisy neighborhoods as a Markov decision process and learning a policy with task-specific rewards received from the representation learning phase. In the representation learning phase, GDPNet aggregates features from signal neighbors to generate node representations for down-stream tasks, and provides task-specific rewards to the signal neighbor selection phase. These two phases are jointly trained to select optimal sets of neighbors for target nodes with maximum cumulative task-specific rewards, and to learn robust representations for nodes. Experimental results on node classification task demonstrate the effectiveness of GDNet, outperforming the state-of-the-art graph representation learning methods on several well-studied datasets. Additionally, GDPNet is mathematically equivalent to solving the submodular maximizing problem, which theoretically guarantees the best approximation to the optimal solution with GDPNet.

Lu Wang, Wei Zhang, Xiaofeng He et al.

Dynamic treatment recommendation systems based on large-scale electronic health records (EHRs) become a key to successfully improve practical clinical outcomes. Prior relevant studies recommend treatments either use supervised learning (e.g. matching the indicator signal which denotes doctor prescriptions), or reinforcement learning (e.g. maximizing evaluation signal which indicates cumulative reward from survival rates). However, none of these studies have considered to combine the benefits of supervised learning and reinforcement learning. In this paper, we propose Supervised Reinforcement Learning with Recurrent Neural Network (SRL-RNN), which fuses them into a synergistic learning framework. Specifically, SRL-RNN applies an off-policy actor-critic framework to handle complex relations among multiple medications, diseases and individual characteristics. The "actor" in the framework is adjusted by both the indicator signal and evaluation signal to ensure effective prescription and low mortality. RNN is further utilized to solve the Partially-Observed Markov Decision Process (POMDP) problem due to the lack of fully observed states in real world applications. Experiments on the publicly real-world dataset, i.e., MIMIC-3, illustrate that our model can reduce the estimated mortality, while providing promising accuracy in matching doctors' prescriptions.