Related papers: PRISM: Distributed Inference for Foundation Models…

Foundation models have achieved remarkable success across many domains, relying on pretraining over vast amounts of data. Graph-structured data often lacks the same scale as unstructured data, making the development of graph foundation…

Image segmentation is a long-standing challenge in computer vision, studied continuously over several decades, as evidenced by seminal algorithms such as N-Cut, FCN, and MaskFormer. With the advent of foundation models (FMs), contemporary…

High-dimensional recordings of dynamical processes are often characterized by a much smaller set of effective variables, evolving on low-dimensional manifolds. Identifying these latent dynamics requires solving two intertwined problems:…

Diffusion-based solvers for partial differential equations (PDEs) are often bottle-necked by slow gradient-based test-time optimization routines that use PDE residuals for loss guidance. They additionally suffer from optimization…

Large pre-trained models have exhibited remarkable achievements across various domains. The substantial training costs associated with these models have led to wide studies of fine-tuning for effectively harnessing their capabilities in…

Gradient sparsification is a widely adopted solution for reducing the excessive communication traffic in distributed deep learning. However, most existing gradient sparsifiers have relatively poor scalability because of considerable…

Semi-implicit distributions have shown great promise in variational inference and generative modeling. Hierarchical semi-implicit models, which stack multiple semi-implicit layers, enhance the expressiveness of semi-implicit distributions…

Detecting glass regions is a challenging task due to the ambiguity of their transparency and reflection properties. These transparent glasses share the visual appearance of both transmitted arbitrary background scenes and reflected objects,…

Comparing post-training LLM variants, such as quantized, LoRA-adapted, and distilled models, requires a diagnostic that identifies how a variant has drifted, not only whether it has degraded. Existing similarity scores such as CKA and SVCCA…

Vision Foundation Models (VFM) pre-trained on large-scale unlabeled data have achieved remarkable success on general computer vision tasks, yet typically suffer from significant domain gaps when applied to agriculture. In this context, we…

The large number of parameters in Pretrained Language Models enhance their performance, but also make them resource-intensive, making it challenging to deploy them on commodity hardware like a single GPU. Due to the memory and power…

Wearable medical sensors (WMSs) are revolutionizing smart healthcare by enabling continuous, real-time monitoring of user physiological signals, especially in the field of consumer healthcare. The integration of WMSs and modern machine…

Video dataset condensation aims to reduce the immense computational cost of video processing. However, it faces a fundamental challenge regarding the inseparable interdependence between spatial appearance and temporal dynamics. Prior work…

Large language models (LLMs) have achieved remarkable success across various artificial intelligence tasks. However, their enormous sizes and computational demands pose significant challenges for the deployment on edge devices. To address…

Deploying large language model (LLM)-driven conversational agents in enterprise settings requires prompts that are simultaneously correct at launch and resilient to the non-deterministic behavioral drift that characterizes production LLM…

Deep learning has significantly advanced PET image re-construction, achieving remarkable improvements in image quality through direct training on sinogram or image data. Traditional methods often utilize masks for inpainting tasks, but…

Neural networks achieve state-of-the-art performance in many supervised learning tasks when the training data distribution matches the test data distribution. However, their performance drops significantly under domain (covariate) shift, a…

Vision Foundation Models (VFMs) pretrained on massive datasets exhibit impressive performance on various downstream tasks, especially with limited labeled target data. However, due to their high inference compute cost, these models cannot…

The success of large language models has inspired the computer vision community to explore image segmentation foundation model that is able to zero/few-shot generalize through prompt engineering. Segment-Anything(SAM), among others, is the…

The recent development of deep learning large models in medicine shows remarkable performance in medical image analysis and diagnosis, but their large number of parameters causes memory and inference latency challenges. Knowledge…