Related papers: A Modular-based Strategy for Mitigating Gradient C…

Recent advances in simultaneous speech translation (SST) focus on the decision policies that enable the use of offline-trained ST models for simultaneous inference. These decision policies not only control the quality-latency trade-off in…

Speech enhancement (SE) is proved effective in reducing noise from noisy speech signals for downstream automatic speech recognition (ASR), where multi-task learning strategy is employed to jointly optimize these two tasks. However, the…

Cognitive control, the ability to coordinate competing information sources in pursuit of goals, is fundamental to intelligent behavior. We systematically investigate whether Vision Language Models (VLMs) exhibit cognitive control and how…

User simulators are essential to conversational AI, enabling scalable agent development and evaluation through simulated interactions. While current Large Language Models (LLMs) have advanced user simulation capabilities, we reveal that…

Attention is the core mechanism of today's most used architectures for natural language processing and has been analyzed from many perspectives, including its effectiveness for machine translation-related tasks. Among these studies,…

Multimodal Large Language Models (MLLMs) have achieved notable success in enhancing translation performance by integrating multimodal information. However, existing research primarily focuses on image-guided methods, whose applicability is…

The Mixture-of-Experts (MoE) has gained increasing attention in studying Large Vision-Language Models (LVLMs). It uses a sparse model to replace the dense model, achieving comparable performance while activating fewer parameters during…

Incremental Decoding is an effective framework that enables the use of an offline model in a simultaneous setting without modifying the original model, making it suitable for Low-Latency Simultaneous Speech Translation. However, this…

Incremental semantic segmentation aims to continually learn the segmentation of new coming classes without accessing the training data of previously learned classes. However, most current methods fail to address catastrophic forgetting and…

In medical healthcare, obtaining detailed annotations is challenging, highlighting the need for robust Vision-Language Models (VLMs). Pretrained VLMs enable fine-tuning on small datasets or zero-shot inference, achieving performance…

Despite the success of deep learning in computer vision and natural language processing, Gradient Boosted Decision Tree (GBDT) is yet one of the most powerful tools for applications with tabular data such as e-commerce and FinTech. However,…

Empirical risk minimization (ERM) is a cornerstone of modern machine learning (ML), supported by advances in optimization theory that ensure efficient solutions with provable algorithmic and statistical learning rates. Privacy, memory,…

Simultaneous translation of unbounded streaming speech remains a challenging problem due to the need for effectively processing the history speech context and past translations so that quality and latency, including computation overhead,…

With the increased audiovisualisation of communication, the need for live subtitles in multilingual events is more relevant than ever. In an attempt to automatise the process, we aim at exploring the feasibility of simultaneous speech…

Reinforcement learning (RL) has played a central role in recent advances in large reasoning models (LRMs), yielding strong gains in verifiable and open-ended reasoning. However, training a single general-purpose LRM across diverse domains…

Although multi-task learning (MTL) has been a preferred approach and successfully applied in many real-world scenarios, MTL models are not guaranteed to outperform single-task models on all tasks mainly due to the negative effects of…

Gradient Boosted Decision Tree (GBDT) is a widely-used machine learning algorithm that has been shown to achieve state-of-the-art results on many standard data science problems. We are interested in its application to multioutput problems…

Multimodal learning helps to comprehensively understand the world, by integrating different senses. Accordingly, multiple input modalities are expected to boost model performance, but we actually find that they are not fully exploited even…

Spoken language understanding (SLU) is a core task in task-oriented dialogue systems, which aims at understanding the user's current goal through constructing semantic frames. SLU usually consists of two subtasks, including intent detection…

Despite imperfect score-matching causing drift in training and sampling distributions of diffusion models, recent advances in diffusion-based acoustic models have revolutionized data-sufficient single-speaker Text-to-Speech (TTS)…