20 accepted papers
Auto-bidding is a core component of real-time advertising systems, where decisions must optimize long-term performance under budget and cost constraints, while online exploration is prohibitively risky. Offline reinforcement learning and, more recently, Transformer-based sequence modeling have shown…
Parameter sharing is a central design choice in cooperative multi-agent reinforcement learning, yet it fundamentally conflicts with the need for role specialization in heterogeneous cooperative environments. Existing role-based methods typically learn monolithic role representations, which often suf
Federated Learning has been widely adopted in privacy-sensitive distributed machine learning. However, in heterogeneous scenarios where significant differences exist in user data distribution, computational capabilities, or network conditions, existing models often underperform. This paper models ke…
Recent advancements in large language models (LLMs) have significantly enhanced their knowledge and generative capabilities, leading to a surge of interest in leveraging LLMs for high-quality data synthesis. However, synthetic data generation via prompting LLMs remains challenging due to LLMs’ limit…
Aortic Dissection (AD) is a life-threatening disease that can be rapidly screened by using deep learning methods. However, deep learning model training requires a large amount of manual annotation of data. To improve the annotation efficiency and accuracy, we propose LABEL-SAM, a semi-automatic inte…
We propose MonoBox, an innovative box-supervised segmentation method constrained by monotonicity to liberate its training from the user-unfriendly box-tightness assumption. In contrast to conventional box-supervised segmentation, where the box edges must precisely touch the target boundaries, MonoBo…
Although deep neural networks have achieved remarkable success in various computer vision tasks, they face significant challenges in degraded image understanding due to domain shifts caused by quality variations. Drawing biological inspiration from the human visual system (HVS), which dynamically ad…
Advanced Deep Neural Networks (DNNs) perform well for high-quality images, but their performance dramatically decreases for degraded images. Data augmentation is commonly used to alleviate this problem, but using too much perturbed data might seriously decrease the performance on pristine images. To…
In long structured document retrieval, existing methods typically fine-tune pre-trained language models (PLMs) using contrastive learning on datasets lacking explicit structural information. This practice suffers from two critical issues: 1) current methods fail to leverage structural features and e
The issue of multimodal imbalance has attracted widespread attention recently, and spurred the proposal of numerous dataset-level modulation strategies. However, we observe that the degree of modality imbalance may vary significantly across different samples, suggesting that dataset-level strategies…
In this work, we address the task of table image to LaTeX code generation, with the goal of automating the reconstruction of high-quality, publication-ready tables from visual inputs. A central challenge of this task lies in accurately handling complex tables—those with large sizes, deeply nested st…
With the development of large language models (LLMs), detecting whether text is generated by a machine becomes increasingly challenging in the face of malicious use cases like the spread of false information, protection of intellectual property, and prevention of academic plagiarism. While well-trai…
With the launch of ChatGPT, large language models (LLMs) have attracted global attention. In the realm of article writing, LLMs have witnessed extensive utilization, giving rise to concerns related to intellectual property protection, personal privacy, and academic integrity. In response, AI-text de…
The widespread use of cloud-based face recognition technology raises privacy concerns as unauthorized access to face images can expose personal information or be exploited for fraudulent purposes. In response privacy-preserving face recognition (PPFR) schemes have emerged to hide visual information…
Multimodal learning has demonstrated a great advantage in emotion recognition tasks due to the richer information from different modalities. However, multimodal models may incline to rely on some modalities that are easier to be learned, while under-fit the other modalities and lead to sub-optimal r…
Large language models (LLMs) have exhibited remarkable capabilities in text generation tasks. However, the utilization of these models carries inherent risks, including but not limited to plagiarism, the dissemination of fake news, and issues in educational exercises. Although several detectors have…
In this paper, we propose a sequence-to-set method that can transform any sequence generative model based on maximum likelihood to a set generative model where we can evaluate the utility/probability of any set. An efficient importance sampling algorithm is devised to tackle the computational challe…
Speech emotion recognition is a challenging task due to the ambiguity of emotion, which makes it difficult to learn the features of emotion data using machine learning algorithms. However, previous studies conventionally ignore the ambiguity of emotion and treat the emotion data as the same difficul…
Recently the mask-based beamforming approach received tremendous interest and is widely studied for multi-channel noise robust automatic speech recognition (ASR). Among the known mask estimation models, the neural network based mask estimation approach has received the most attention, resulting in a…
The 3D talking head has been developed fast, in which both external and internal articulators were demonstrated. For Mandarin pronunciation, the aspiration airflow is crucial to discriminate confusable Mandarin consonants. In this paper, we present a 3D talking head system for articulatory and aspir…