相关论文: Interfacing Foundation Models' Embeddings

Unlike vision and language domains, graph learning lacks a shared input space, as input features differ across graph datasets not only in semantics, but also in value ranges and dimensionality. This misalignment prevents graph models from…

Vision foundation models can perform generalized object classification in zero-shot mode, and face/person recognition when they are fine-tuned. However, fine-tuned models suffer from catastrophic forgetting. We create models that perform…

Vision foundation models have been explored recently to build general-purpose vision systems. However, predominant paradigms, driven by casting instance-level tasks as an object-word alignment, bring heavy cross-modality interaction, which…

Recent advances in multimodal Parameter-Efficient Fine-Tuning (PEFT) have significantly improved performance on downstream tasks such as few-shot retrieval. However, most existing approaches focus on task-specific gains while neglecting the…

Textual network embeddings aim to learn a low-dimensional representation for every node in the network so that both the structural and textual information from the networks can be well preserved in the representations. Traditionally, the…

The proposed method extends upon the representational output of semantic instance segmentation by explicitly including both visible and occluded parts. A fully convolutional network is trained to produce consistent pixel-level embedding…

Attribute recognition is a crucial but challenging task due to viewpoint changes, illumination variations and appearance diversities, etc. Most of previous work only consider the attribute-level feature embedding, which might perform poorly…

Large Language Model (LLM) inference is growing increasingly complex with the rise of Mixture-of-Experts (MoE) models and disaggregated architectures that decouple components like prefill/decode (PD) or attention/FFN (AF) for heterogeneous…

Foundation models, while highly effective, are often resource-intensive, requiring substantial inference time and memory. This paper addresses the challenge of making these models more accessible with limited computational resources by…

Fusion-based place recognition is an emerging technique jointly utilizing multi-modal perception data, to recognize previously visited places in GPS-denied scenarios for robots and autonomous vehicles. Recent fusion-based place recognition…

Unified multi-model representation spaces are the foundation of multimodal understanding and generation. However, the billions of model parameters and catastrophic forgetting problems make it challenging to further enhance pre-trained…

When existing retrieval-augmented generation (RAG) solutions are intended to be used for new knowledge domains, it is necessary to update their encoders, which are taken to be pretrained large language models (LLMs). However, fully…

Model merging constructs versatile models by integrating task-specific models without requiring labeled data or expensive joint retraining. Although recent methods improve adaptability to heterogeneous tasks by generating customized merged…

We present FoundationPose, a unified foundation model for 6D object pose estimation and tracking, supporting both model-based and model-free setups. Our approach can be instantly applied at test-time to a novel object without fine-tuning,…

During the last years, many advances have been made in tasks like3D model retrieval, 3D model classification, and 3D model segmentation.The typical 3D representations such as point clouds, voxels, and poly-gon meshes are mostly suitable for…

Pathology foundation models (PFMs) have demonstrated strong representational capabilities through self-supervised pre-training on large-scale, unannotated histopathology image datasets. However, their diverse yet opaque pretraining…

Remarkable achievements have been attained by deep neural networks in various applications. However, the increasing depth and width of such models also lead to explosive growth in both storage and computation, which has restricted the…

Deep Learning (DL) models have been widely deployed on IoT devices with the help of advancements in DL algorithms and chips. However, the limited resources of edge devices make these on-device DL models hard to be generalizable to diverse…

In recent years, network embedding methods have garnered increasing attention because of their effectiveness in various information retrieval tasks. The goal is to learn low-dimensional representations of vertexes in an information network…

Network representation learning has traditionally been used to find lower dimensional vector representations of the nodes in a network. However, there are very important edge driven mining tasks of interest to the classical network analysis…