Related papers: RaCo: Ranking and Covariance for Practical Learned…

Clinicians need ranking systems that work in real time and still justify their choices. Motivated by the need for a low-latency, decoder-based reranker, we present OG-Rank, a single-decoder approach that pairs a pooled first-token scoring…

Coordinate-based neural representations have shown significant promise as an alternative to discrete, array-based representations for complex low dimensional signals. However, optimizing a coordinate-based network from randomly initialized…

Deep regression models typically learn in an end-to-end fashion without explicitly emphasizing a regression-aware representation. Consequently, the learned representations exhibit fragmentation and fail to capture the continuous nature of…

Visual Teach-and-Repeat Navigation is a direct solution for mobile robot to be deployed in unknown environments. However, robust trajectory repeat navigation still remains challenged due to environmental changing and dynamic objects. In…

Deep learning models in robotics often output point estimates with poorly calibrated confidences, offering no native mechanism to quantify predictive reliability under novel, noisy, or out-of-distribution inputs. Conformal prediction (CP)…

This paper introduces AdaptoVision, a novel convolutional neural network (CNN) architecture designed to efficiently balance computational complexity and classification accuracy. By leveraging enhanced residual units, depth-wise separable…

Multimodal learning has been lacking principled ways of combining information from different modalities and learning a low-dimensional manifold of meaningful representations. We study multimodal learning and sensor fusion from a latent…

Video prediction methods generally consume substantial computing resources in training and deployment, among which keypoint-based approaches show promising improvement in efficiency by simplifying dense image prediction to light keypoint…

We propose a method to detect and reconstruct multiple 3D objects from a single RGB image. The key idea is to optimize for detection, alignment and shape jointly over all objects in the RGB image, while focusing on realistic and physically…

The integration of reinforcement learning (RL) into large language models (LLMs) has opened new opportunities for recommender systems by eliciting reasoning and improving user preference modeling. However, RL-based LLM recommendation faces…

The ability to plan into the future while utilizing only raw high-dimensional observations, such as images, can provide autonomous agents with broad capabilities. Visual model-based reinforcement learning (RL) methods that plan future…

Collaborative learning is an important tool to train multiple clients more effectively by enabling communication among clients. Identifying helpful clients, however, presents challenging and often introduces significant overhead. In this…

An important challenge for autonomous agents such as robots is to maintain a spatially and temporally consistent model of the world. It must be maintained through occlusions, previously-unseen views, and long time horizons (e.g., loop…

World models learned from high-dimensional visual observations allow agents to make decisions and plan directly in latent space, avoiding pixel-level reconstruction. However, recent latent predictive architectures (JEPAs), including the…

Most high-dimensional matrix recovery problems are studied under the assumption that the target matrix has certain intrinsic structures. For image data related matrix recovery problems, approximate low-rankness and smoothness are the two…

Neural models have shown promise in solving NP-hard graph combinatorial optimization (CO) problems. Once trained, they offer fast inference and reasonably high-quality solutions for in-distribution testing instances, but they generally fall…

The study of object representations in computer vision has primarily focused on developing representations that are useful for image classification, object detection, or semantic segmentation as downstream tasks. In this work we aim to…

Interest in derivative-free optimization (DFO) and "evolutionary strategies" (ES) has recently surged in the Reinforcement Learning (RL) community, with growing evidence that they can match state of the art methods for policy optimization…

Estimation of a precision matrix (i.e., inverse covariance matrix) is widely used to exploit conditional independence among continuous variables. The influence of abnormal observations is exacerbated in a high dimensional setting as the…

Retrieval augmented generation (RAG) has transformed text based question answering, yet its extension to visual domains remains hindered by fundamental challenges: bridging the modality gap between image queries and text heavy knowledge…