Related papers: DAM: Dynamic Adapter Merging for Continual Video Q…

Large language models (LLMs) have shown remarkable reasoning capabilities, yet aligning such abilities to small language models (SLMs) remains a challenge due to distributional mismatches and limited model capacity. Existing reasoning…

Recent progress has been made in region-aware vision-language modeling, particularly with the emergence of the Describe Anything Model (DAM). DAM is capable of generating detailed descriptions of any specific image areas or objects without…

I introduce a novel associative memory model named Correlated Dense Associative Memory (CDAM), which integrates both auto- and hetero-association in a unified framework for continuous-valued memory patterns. Employing an arbitrary graph…

Recently, several spatial-temporal memory-based methods have verified that storing intermediate frames and their masks as memory are helpful to segment target objects in videos. However, they mainly focus on better matching between the…

Continual learning in natural language processing plays a crucial role in adapting to evolving data and preventing catastrophic forgetting. Despite significant progress, existing methods still face challenges, such as inefficient parameter…

The demand for lightweight models in image classification tasks under resource-constrained environments necessitates a balance between computational efficiency and robust feature representation. Traditional attention mechanisms, despite…

Deep learning methods for Visual Place Recognition (VPR) have advanced significantly, largely driven by large-scale datasets. However, most existing approaches are trained on a single dataset, which can introduce dataset-specific inductive…

Adaptive gradient methods, such as Adam and LAMB, have demonstrated excellent performance in the training of large language models. Nevertheless, the need for adaptivity requires maintaining second-moment estimates of the per-parameter…

We introduce a new method inspired by Adam that enhances convergence speed and achieves better loss function minima. Traditional optimizers, including Adam, apply uniform or globally adjusted learning rates across neural networks without…

Universal domain adaptation (UniDA) aims to transfer knowledge from the source domain to the target domain without any prior knowledge about the label set. The challenge lies in how to determine whether the target samples belong to common…

Video object segmentation methods like SAM2 achieve strong performance through memory-based architectures but struggle under large viewpoint changes due to reliance on appearance features. Traditional 3D instance segmentation methods…

Delay alignment modulation (DAM) is a novel transmission technique for wireless systems with high spatial resolution by leveraging delay compensation and path-based beamforming, to mitigate the inter-symbol interference (ISI) without…

Stochastic gradient descent-based algorithms are widely used for training deep neural networks but often suffer from slow convergence. To address the challenge, we leverage the framework of the alternating direction method of multipliers…

Dynamic Random Access Memory (DRAM) is the de-facto choice for main memory devices due to its cost-effectiveness. It offers a larger capacity and higher bandwidth compared to SRAM but is slower than the latter. With each passing generation,…

Although the current different types of SAM adaptation methods have achieved promising performance for various downstream tasks, such as prompt-based ones and adapter-based ones, most of them belong to the one-step adaptation paradigm. In…

Despite impressive advancements in recent multimodal reasoning approaches, they are still limited in flexibility and efficiency, as these models typically process only a few fixed modality inputs and require updates to numerous parameters.…

In many real-world scenarios, data to train machine learning models become available over time. However, neural network models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon…

Matching-based networks have achieved state-of-the-art performance for video object segmentation (VOS) tasks by storing every-k frames in an external memory bank for future inference. Storing the intermediate frames' predictions provides…

Long-form video understanding remains challenging due to the extended temporal structure and dense multimodal cues. Despite recent progress, many existing approaches still rely on hand-crafted reasoning pipelines or employ token-consuming…

Infrared-visible object detection aims to achieve robust even full-day object detection by fusing the complementary information of infrared and visible images. However, highly dynamically variable complementary characteristics and commonly…