Related papers: Beyond Adapter Retrieval: Latent Geometry-Preservi…

Ultrasound imaging faces a trade-off between image quality and hardware complexity caused by dense transducers. Sparse arrays are one popular solution to mitigate this challenge. This work proposes an end-to-end optimization framework that…

Learning compact and meaningful latent space representations has been shown to be very useful in generative modeling tasks for visual data. One particular example is applying Vector Quantization (VQ) in variational autoencoders (VQ-VAEs,…

Geometric diffusion models have shown remarkable success in molecular dynamics and structure generation. However, efficiently fine-tuning them for downstream tasks with varying geometric controls remains underexplored. In this work, we…

In high-dimensional settings, sparse structures are critical for efficiency in term of memory and computation complexity. For a linear system, to find the sparsest solution provided with an over-complete dictionary of features directly is…

Domain adaptation refers to the process of learning prediction models in a target domain by making use of data from a source domain. Many classic methods solve the domain adaptation problem by establishing a common latent space, which may…

Transformers are a popular choice for classification tasks and as backbones for object detection tasks. However, their high latency brings challenges in their adaptation to lightweight object detection systems. We present an approximation…

In recent years, Generative Adversarial Networks have become ubiquitous in both research and public perception, but how GANs convert an unstructured latent code to a high quality output is still an open question. In this work, we…

Existing image restoration approaches typically employ extensive networks specifically trained for designated degradations. Despite being effective, such methods inevitably entail considerable storage costs and computational overheads due…

In recent years, the development of diffusion models has led to significant progress in image and video generation tasks, with pre-trained models like the Stable Diffusion series playing a crucial role. Inspired by model pruning which…

Most point cloud compression methods operate in the voxel or octree domain which is not the original representation of point clouds. Those representations either remove the geometric information or require high computational power for…

The pretrain-then-finetune paradigm has been widely used in various unimodal and multimodal tasks. However, finetuning all the parameters of a pre-trained model becomes prohibitive as the model size grows exponentially. To address this…

Deeply-learned planning methods are often based on learning representations that are optimized for unrelated tasks. For example, they might be trained on reconstructing the environment. These representations are then combined with predictor…

Current parameter-efficient fine-tuning (PEFT) methods build adapters widely agnostic of the context of downstream task to learn, or the context of important knowledge to maintain. As a result, there is often a performance gap compared to…

Learning long-horizon manipulation tasks efficiently is a central challenge in robot learning from demonstration. Unlike recent endeavors that focus on directly learning the task in the action domain, we focus on inferring what the robot…

Recently, several approaches successfully demonstrated that weight-sharing Neural Architecture Search (NAS) can effectively explore a search space of elastic low-rank adapters (LoRA), allowing the parameter-efficient fine-tuning (PEFT) and…

Sparse matrices are favorable objects in machine learning and optimization. When such matrices are used, in place of dense ones, the overall complexity requirements in optimization can be significantly reduced in practice, both in terms of…

We propose a novel shape representation useful for analyzing and processing shape collections, as well for a variety of learning and inference tasks. Unlike most approaches that capture variability in a collection by using a template model…

In this work, we investigate the potential of weights to serve as effective representations, focusing on neural fields. Our key insight is that constraining the optimization space through a pre-trained base model and low-rank adaptation…

Adapter-based tuning has recently arisen as an alternative to fine-tuning. It works by adding light-weight adapter modules to a pretrained language model (PrLM) and only updating the parameters of adapter modules when learning on a…

Fully fine-tuning pretrained large-scale transformer models has become a popular paradigm for video-language modeling tasks, such as temporal language grounding and video-language summarization. With a growing number of tasks and limited…