Related papers: MemFlow: A Lightweight Forward Memorizing Framewor…

Backpropagation provides a generalized configuration for overcoming catastrophic forgetting. Optimizers such as SGD and Adam are commonly used for weight updates in continual learning and continual pre-training. However, access to gradient…

With the widespread deployment of deep learning models, they influence their environment in various ways. The induced distribution shifts can lead to unexpected performance degradation in deployed models. Existing methods to anticipate…

The core challenge for streaming video generation is maintaining the content consistency in long context, which poses high requirement for the memory design. Most existing solutions maintain the memory by compressing historical frames with…

Optical flow is a classical task that is important to the vision community. Classical optical flow estimation uses two frames as input, whilst some recent methods consider multiple frames to explicitly model long-range information. The…

Graphical forecasting models learn the structure of time series data via projecting onto a graph, with recent techniques capturing spatial-temporal associations between variables via edge weights. Hierarchical variants offer a distinct…

We study a new highly-practical problem setting that enables resource-constrained edge devices to adapt a pre-trained model to their local data distributions. Recognizing that device's data are likely to come from multiple latent domains…

Deep learning models, in particular \textit{image} models, have recently gained generalisability and robustness. %are becoming more general and robust by the day. In this work, we propose to exploit such advances in the realm of…

The expansion of large language models is increasingly limited by the constrained memory capacity of modern GPUs. To mitigate this, Mixture-of-Experts (MoE) architectures activate only a small portion of parameters during inference,…

Flow Matching (FM) has recently emerged as a leading approach for high-fidelity visual generation, offering a robust continuous-time alternative to ordinary differential equation (ODE) based models. However, despite their success, FM models…

Longitudinal brain analysis is essential for understanding healthy aging and identifying pathological deviations. Longitudinal registration of sequential brain MRI underpins such analyses. However, existing methods are limited by reliance…

Machine learning models deployed on edge devices have enabled numerous exciting new applications, such as humanoid robots, AR glasses, and autonomous vehicles. However, the computing resources available on these edge devices are not…

Flow-matching models deliver state-of-the-art fidelity in image and video generation, but the inherent sequential denoising process renders them slower. Existing acceleration methods like distillation, trajectory truncation, and consistency…

Object recognition is a key enabler across industry and defense. As technology changes, algorithms must keep pace with new requirements and data. New modalities and higher resolution sensors should allow for increased algorithm robustness.…

Diffusion and flow models have become the dominant paradigm for generative modeling on Riemannian manifolds, with successful applications in protein backbone generation and DNA sequence design. However, these methods require tens to…

Remote sensing segmentation in real deployment is inherently continual: new semantic categories emerge, and acquisition conditions shift across seasons, cities, and sensors. Despite recent progress, many incremental approaches still treat…

Conventional diffusion models typically relies on a fixed forward process, which implicitly defines complex marginal distributions over latent variables. This can often complicate the reverse process' task in learning generative…

Foundational language models show a remarkable ability to learn new concepts during inference via context data. However, similar work for images lag behind. To address this challenge, we introduce FLoWN, a flow matching model that learns to…

Recent advancements in large language models (LLMs) and their multimodal variants have led to remarkable progress across various domains, demonstrating impressive capabilities and unprecedented potential. In the era of ubiquitous…

Flow matching models have emerged as a powerful framework for realistic image generation by learning to reverse a corruption process that progressively adds Gaussian noise. However, because noise is injected in the latent domain, its impact…

Flow based generative models have charted an impressive path across multiple visual generation tasks by adhering to a simple principle: learning velocity representations of a linear interpolant. However, we observe that training velocity…