Related papers: SPANER: Shared Prompt Aligner for Multimodal Seman…

Existing approaches for fine-grained visual recognition focus on learning marginal region-based representations while neglecting the spatial and scale misalignments, leading to inferior performance. In this paper, we propose the…

We introduce Scaffold Prompt Tuning (ScaPT), a novel prompt-based framework for adapting large-scale functional magnetic resonance imaging (fMRI) pre-trained models to downstream tasks, with high parameter efficiency and improved…

Weakly supervised LiDAR semantic segmentation has made significant strides with limited labeled data. However, most existing methods focus on the network training under weak supervision, while efficient annotation strategies remain largely…

Multimodal recommendation systems have attracted increasing attention for their improved performance by leveraging items' multimodal information. Prior methods often build modality-specific item-item semantic graphs from raw modality…

Cross-modal alignment is a crucial task in multimodal learning aimed at achieving semantic consistency between vision and language. This requires that image-text pairs exhibit similar semantics. Traditional algorithms pursue embedding…

Parameter-Efficient Fine-Tuning (PEFT) is widely used for adapting Large Language Models (LLMs) for various tasks. Recently, there has been an increasing demand for fine-tuning a single LLM for multiple tasks because it requires overall…

Parameter-efficient fine-tuning (PEFT) has emerged as a scalable solution for adapting large foundation models. While low-rank adaptation (LoRA) is widely used in speech applications, its state-of-the-art variants, e.g., VeRA, DoRA, PiSSA,…

Soft prompts have emerged as a powerful alternative to adapters in parameter-efficient fine-tuning (PEFT), enabling large language models (LLMs) to adapt to downstream tasks without architectural changes or parameter updates. While prior…

Recently, foundation models trained on massive datasets to adapt to a wide range of tasks have attracted considerable attention and are actively being explored within the computer vision community. Among these, the Segment Anything Model…

Multi-rater medical image segmentation captures the inherent ambiguity of clinical interpretation, where diagnostic boundaries vary across experts and imaging devices. Existing approaches often reduce this diversity to consensus labels or…

LiDAR and camera are two critical sensors for multi-modal 3D semantic segmentation and are supposed to be fused efficiently and robustly to promise safety in various real-world scenarios. However, existing multi-modal methods face two key…

It has been demonstrated that the art of prompt tuning is highly effective in efficiently extracting knowledge from pretrained foundation models, encompassing pretrained language models (PLMs), vision pretrained models, and vision-language…

Parameter-efficient fine-tuning (PEFT) has emerged as an effective method for adapting pre-trained language models to various tasks efficiently. Recently, there has been a growing interest in transferring knowledge from one or multiple…

Network embeddings, which learn low-dimensional representations for each vertex in a large-scale network, have received considerable attention in recent years. For a wide range of applications, vertices in a network are typically…

The Segment Anything Model (SAM), a vision foundation model, exhibits impressive zero-shot capabilities in general tasks but struggles in specialized domains. Parameter-efficient fine-tuning (PEFT) is a promising approach to unleash the…

Variational Autoencoders for multimodal data hold promise for many tasks in data analysis, such as representation learning, conditional generation, and imputation. Current architectures either share the encoder output, decoder input, or…

This paper presents a new technique for creating monolingual and cross-lingual meta-embeddings. Our method integrates multiple word embeddings created from complementary techniques, textual sources, knowledge bases and languages. Existing…

To address the annotation scarcity issue in some cases of semantic segmentation, there have been a few attempts to develop the segmentation model in the few-shot learning paradigm. However, most existing methods only focus on the…

Sentence embeddings enable us to capture the semantic similarity of short texts. Most sentence embedding models are trained for general semantic textual similarity tasks. Therefore, to use sentence embeddings in a particular domain, the…

Few-shot named entity recognition (NER) targets generalizing to unseen labels and/or domains with few labeled examples. Existing metric learning methods compute token-level similarities between query and support sets, but are not able to…