Xin Wang

Tianyu Zhang, Luyi Han, Anna D'Angelo et al.

Magnetic resonance imaging (MRI) is the most sensitive technique for breast cancer detection among current clinical imaging modalities. Contrast-enhanced MRI (CE-MRI) provides superior differentiation between tumors and invaded healthy tissue, and has become an indispensable technique in the detection and evaluation of cancer. However, the use of gadolinium-based contrast agents (GBCA) to obtain CE-MRI may be associated with nephrogenic systemic fibrosis and may lead to bioaccumulation in the brain, posing a potential risk to human health. Moreover, and likely more important, the use of gadolinium-based contrast agents requires the cannulation of a vein, and the injection of the contrast media which is cumbersome and places a burden on the patient. To reduce the use of contrast agents, diffusion-weighted imaging (DWI) is emerging as a key imaging technique, although currently usually complementing breast CE-MRI. In this study, we develop a multi-sequence fusion network to synthesize CE-MRI based on T1-weighted MRI and DWIs. DWIs with different b-values are fused to efficiently utilize the difference features of DWIs. Rather than proposing a pure data-driven approach, we invent a multi-sequence attention module to obtain refined feature maps, and leverage hierarchical representation information fused at different scales while utilizing the contributions from different sequences from a model-driven approach by introducing the weighted difference module. The results show that the multi-b-value DWI-based fusion model can potentially be used to synthesize CE-MRI, thus theoretically reducing or avoiding the use of GBCA, thereby minimizing the burden to patients. Our code is available at \url{https://github.com/Netherlands-Cancer-Institute/CE-MRI}.

Yitao Zhu, Zhenrong Shen, Zihao Zhao et al.

The common practice in developing computer-aided diagnosis (CAD) models based on transformer architectures usually involves fine-tuning from ImageNet pre-trained weights. However, with recent advances in large-scale pre-training and the practice of scaling laws, Vision Transformers (ViT) have become much larger and less accessible to medical imaging communities. Additionally, in real-world scenarios, the deployments of multiple CAD models can be troublesome due to problems such as limited storage space and time-consuming model switching. To address these challenges, we propose a new method MeLo (Medical image Low-rank adaptation), which enables the development of a single CAD model for multiple clinical tasks in a lightweight manner. It adopts low-rank adaptation instead of resource-demanding fine-tuning. By fixing the weight of ViT models and only adding small low-rank plug-ins, we achieve competitive results on various diagnosis tasks across different imaging modalities using only a few trainable parameters. Specifically, our proposed method achieves comparable performance to fully fine-tuned ViT models on four distinct medical imaging datasets using about 0.17% trainable parameters. Moreover, MeLo adds only about 0.5MB of storage space and allows for extremely fast model switching in deployment and inference. Our source code and pre-trained weights are available on our website (https://absterzhu.github.io/melo.github.io/).

Hong Chen, Xin Wang, Guanning Zeng et al.

Customized text-to-video generation aims to generate text-guided videos with user-given subjects, which has gained increasing attention. However, existing works are primarily limited to single-subject oriented text-to-video generation, leaving the more challenging problem of customized multi-subject generation unexplored. In this paper, we fill this gap and propose a novel VideoDreamer framework, which can generate temporally consistent text-guided videos that faithfully preserve the visual features of the given multiple subjects. Specifically, VideoDreamer adopts the pretrained Stable Diffusion with temporal modules as its base video generator, taking the power of the text-to-image model to generate diversified content. The video generator is further customized for multi-subjects, which leverages the proposed Disen-Mix Finetuning and Human-in-the-Loop Re-finetuning strategy, to tackle the attribute binding problem of multi-subject generation. Additionally, we present a disentangled motion customization strategy to finetune the temporal modules so that we can generate videos with both customized subjects and motions. To evaluate the performance of customized multi-subject text-to-video generation, we introduce the MultiStudioBench benchmark. Extensive experiments demonstrate the remarkable ability of VideoDreamer to generate videos with new content such as new events and backgrounds, tailored to the customized multiple subjects.

Wei Feng, Xin Wang, Hong Chen et al.

Video generation has witnessed great success recently, but their application in generating long videos still remains challenging due to the difficulty in maintaining the temporal consistency of generated videos and the high memory cost during generation. To tackle the problems, in this paper, we propose a brave and new idea of Multi-sentence Video Grounding for Long Video Generation, connecting the massive video moment retrieval to the video generation task for the first time, providing a new paradigm for long video generation. The method of our work can be summarized as three steps: (i) We design sequential scene text prompts as the queries for video grounding, utilizing the massive video moment retrieval to search for video moment segments that meet the text requirements in the video database. (ii) Based on the source frames of retrieved video moment segments, we adopt video editing methods to create new video content while preserving the temporal consistency of the retrieved video. Since the editing can be conducted segment by segment, and even frame by frame, it largely reduces the memory cost. (iii) We also attempt video morphing and personalized generation methods to improve the subject consistency of long video generation, providing ablation experimental results for the subtasks of long video generation. Our approach seamlessly extends the development in image/video editing, video morphing and personalized generation, and video grounding to the long video generation, offering effective solutions for generating long videos at low memory cost.

Wei Feng, Xin Wang, Hong Chen et al.

Recently, researchers have attempted to investigate the capability of LLMs in handling videos and proposed several video LLM models. However, the ability of LLMs to handle video grounding (VG), which is an important time-related video task requiring the model to precisely locate the start and end timestamps of temporal moments in videos that match the given textual queries, still remains unclear and unexplored in literature. To fill the gap, in this paper, we propose the LLM4VG benchmark, which systematically evaluates the performance of different LLMs on video grounding tasks. Based on our proposed LLM4VG, we design extensive experiments to examine two groups of video LLM models on video grounding: (i) the video LLMs trained on the text-video pairs (denoted as VidLLM), and (ii) the LLMs combined with pretrained visual description models such as the video/image captioning model. We propose prompt methods to integrate the instruction of VG and description from different kinds of generators, including caption-based generators for direct visual description and VQA-based generators for information enhancement. We also provide comprehensive comparisons of various VidLLMs and explore the influence of different choices of visual models, LLMs, prompt designs, etc, as well. Our experimental evaluations lead to two conclusions: (i) the existing VidLLMs are still far away from achieving satisfactory video grounding performance, and more time-related video tasks should be included to further fine-tune these models, and (ii) the combination of LLMs and visual models shows preliminary abilities for video grounding with considerable potential for improvement by resorting to more reliable models and further guidance of prompt instructions.

Xin He, Wenqi Fan, Mingchen Sun et al.

In recent years, researchers have attempted to exploit social relations to improve the performance in recommendation systems. Generally, most existing social recommendation methods heavily depends on substantial domain knowledge and expertise in primary recommendation tasks for designing useful auxiliary tasks. Meanwhile, Self-Supervised Learning (SSL) recently has received considerable attention in the field of recommendation, since it can provide self-supervision signals in assisting the improvement of target recommendation systems by constructing self-supervised auxiliary tasks from raw data without human-annotated labels. Despite the great success, these SSL-based social recommendations are insufficient to adaptively balance various self-supervised auxiliary tasks, since assigning equal weights on various auxiliary tasks can result in sub-optimal recommendation performance, where different self-supervised auxiliary tasks may contribute differently to improving the primary social recommendation across different datasets. To address this issue, in this work, we propose Adaptive Self-supervised Learning for Social Recommendations (AdasRec) by taking advantage of various self-supervised auxiliary tasks. More specifically, an adaptive weighting mechanism is proposed to learn adaptive weights for various self-supervised auxiliary tasks, so as to balance the contribution of such self-supervised auxiliary tasks for enhancing representation learning in social recommendations. The adaptive weighting mechanism is used to assign different weights on auxiliary tasks to achieve an overall weighting of the entire auxiliary tasks and ultimately assist the primary recommendation task, achieved by a meta learning optimization problem with an adaptive weighting network. Comprehensive experiments on various real-world datasets are constructed to verify the effectiveness of our proposed method.

Zhongwei Wan, Xinjian Wu, Yu Zhang et al.

Generative inference in Large Language Models (LLMs) is impeded by the growing memory demands of Key-Value (KV) cache, especially for longer sequences. Traditional KV cache eviction strategies, which discard less critical KV pairs based on attention scores, often degrade generation quality, leading to issues such as context loss or hallucinations. In this work, we introduce Dynamic Discriminative Operations (D2O), a KV cache compression method that optimizes KV cache size dynamically and discriminatively at two levels without fine-tuning, while preserving essential context. At layer level, D2O leverages the varying densities of attention weights between shallow and deep layers to dynamically determine which layers should avoid excessive eviction via a novel dynamic allocation strategy to minimize information loss. At token level, D2O incorporates a compensation mechanism that maintains a similarity threshold to re-discriminate the importance of currently discarded tokens, determining whether they should be recalled and merged with similar tokens. We conduct experiments on various benchmarks and LLM architectures. Our results show that D2O not only achieves significant memory savings and enhances inference throughput by more than 3$\times$ but also maintains high-quality long-text generation.

Cheng Gong, Erica Cooper, Xin Wang et al.

Self-supervised learning (SSL) representations from massively multilingual models offer a promising solution for low-resource language speech tasks. Despite advancements, language adaptation in TTS systems remains an open problem. This paper explores the language adaptation capability of ZMM-TTS, a recent SSL-based multilingual TTS system proposed in our previous work. We conducted experiments on 12 languages using limited data with various fine-tuning configurations. We demonstrate that the similarity in phonetics between the pre-training and target languages, as well as the language category, affects the target language's adaptation performance. Additionally, we find that the fine-tuning dataset size and number of speakers influence adaptability. Surprisingly, we also observed that using paired data for fine-tuning is not always optimal compared to audio-only data. Beyond speech intelligibility, our analysis covers speaker similarity, language identification, and predicted MOS.