Related papers: DA-Mamba: Dialogue-aware selective state-space mod…
State space models (SSMs) for language modelling promise an efficient and performant alternative to quadratic-attention Transformers, yet show variable performance on recalling basic information from the context. While performance on…
Transformer structure has achieved great success in multiple applied machine learning communities, such as natural language processing (NLP), computer vision (CV) and information retrieval (IR). Transformer architecture's core mechanism\,…
Two-view correspondence learning aims to discern true and false correspondences between image pairs by recognizing their underlying different information. Previous methods either treat the information equally or require the explicit storage…
Recent work in open-domain conversational agents has demonstrated that significant improvements in model engagingness and humanness metrics can be achieved via massive scaling in both pre-training data and model size (Adiwardana et al.,…
Long-term time series forecasting (LTSF) provides longer insights into future trends and patterns. Over the past few years, deep learning models especially Transformers have achieved advanced performance in LTSF tasks. However, LTSF faces…
Domain Adaptive Object Detection (DAOD) aims to transfer detectors from a labeled source domain to an unlabeled target domain. Existing DAOD methods employ multi-granularity feature alignment to learn domain-invariant representations.…
The Mamba-based model has demonstrated outstanding performance across tasks in computer vision, natural language processing, and speech processing. However, in the realm of speech processing, the Mamba-based model's performance varies…
In this thesis, we leverage the neural copy mechanism and memory-augmented neural networks (MANNs) to address existing challenge of neural task-oriented dialogue learning. We show the effectiveness of our strategy by achieving good…
Pan-sharpening involves integrating information from low-resolution multi-spectral and high-resolution panchromatic images to generate high-resolution multi-spectral counterparts. While recent advancements in the state space model,…
Understanding videos is one of the fundamental directions in computer vision research, with extensive efforts dedicated to exploring various architectures such as RNN, 3D CNN, and Transformers. The newly proposed architecture of state space…
We introduce VideoMamba, a novel adaptation of the pure Mamba architecture, specifically designed for video recognition. Unlike transformers that rely on self-attention mechanisms leading to high computational costs by quadratic complexity,…
We present Schr\"odinger Bridge Mamba (SBM), a novel model for efficient speech enhancement by integrating the Schr\"odinger Bridge (SB) training paradigm and the Mamba architecture. Experiments of joint denoising and dereverberation tasks…
Recent advances in deep learning have made it possible to predict phenotypic measures directly from functional magnetic resonance imaging (fMRI) brain volumes, sparking significant interest in the neuroimaging community. However, existing…
Time series prediction plays a pivotal role across diverse domains such as finance, healthcare, energy systems, and environmental modeling. However, existing approaches often struggle to balance efficiency, scalability, and accuracy,…
Multi-modal image fusion integrates complementary information from different modalities to produce enhanced and informative images. Although State-Space Models, such as Mamba, are proficient in long-range modeling with linear complexity,…
Recent advancements in unified multimodal understanding and visual generation (or multimodal generation) models have been hindered by their quadratic computational complexity and dependence on large-scale training data. We present…
Dynamic graph modeling aims to uncover evolutionary patterns in real-world systems, enabling accurate social recommendation and early detection of cancer cells. Inspired by the success of recent state space models in efficiently capturing…
Multi-modal emotion recognition in conversations is a challenging problem due to the complex and complementary interactions between different modalities. Audio and textual cues are particularly important for understanding emotions from a…
Balancing fine-grained local modeling with long-range dependency capture under computational constraints remains a central challenge in sequence modeling. While Transformers provide strong token mixing, they suffer from quadratic…
Long-term dense action anticipation is very challenging since it requires predicting actions and their durations several minutes into the future based on provided video observations. To model the uncertainty of future outcomes, stochastic…