Related papers: Efficient Joint Prediction of Multiple Future Toke…

Multi-task learning for dense prediction has emerged as a pivotal area in computer vision, enabling simultaneous processing of diverse yet interrelated pixel-wise prediction tasks. However, the substantial computational demands of…

Many Multi-Object Tracking (MOT) approaches exploit motion information to associate all the detected objects across frames. However, many methods that rely on filtering-based algorithms, such as the Kalman Filter, often work well in linear…

Logit Lens has been proposed for visualizing tokens that contribute most to LLM answers. Recently, Logit Lens was also shown to be applicable in autoregressive Vision-Language Models (VLMs), where it illustrates the conceptual content of…

Low-frequency word prediction remains a challenge in modern neural machine translation (NMT) systems. Recent adaptive training methods promote the output of infrequent words by emphasizing their weights in the overall training objectives.…

Aiming at efficient and dense chain-of-thought (CoT) reasoning, latent reasoning methods fine-tune Large Language Models (LLMs) to substitute discrete language tokens with continuous latent tokens. These methods consume fewer tokens…

Advancements in machine learning for molecular property prediction have improved accuracy but at the expense of higher computational cost and longer training times. Recently, the Joint Multi-domain Pre-training (JMP) foundation model has…

Learning efficient representations for decision-making policies is a challenge in imitation learning (IL). Current IL methods require expert demonstrations, which are expensive to collect. Additionally, they are not explicitly trained to…

As a new paradigm of visual content generation, autoregressive text-to-image models suffer from slow inference due to their sequential token-by-token decoding process, often requiring thousands of model forward passes to generate a single…

Making an accurate prediction of an unknown system only from a short-term time series is difficult due to the lack of sufficient information, especially in a multi-step-ahead manner. However, a high-dimensional short-term time series…

In this work, we aim to predict the future motion of vehicles in a traffic scene by explicitly modeling their pairwise interactions. Specifically, we propose a graph neural network that jointly predicts the discrete interaction modes and…

We introduce a new class of machine learning interatomic potentials - fast General Two- and Three-body Potential (GTTP), which is as fast as conventional empirical potentials and require computational time that remains constant with…

Predicting flight trajectories is a research area that holds significant merit. In this paper, we propose a data-driven learning framework, that leverages the predictive and feature extraction capabilities of the mixture models and…

Activity cliff prediction is a critical task in drug discovery and material design. Existing computational methods are limited to handling single binding targets, which restricts the applicability of these prediction models. In this paper,…

The rapid development of Wi-Fi technologies in recent years has caused a significant increase in the traffic usage. Hence, knowledge obtained from Wi-Fi network measurements can be helpful for a more efficient network management. In this…

In skeleton-based human action recognition, temporal pooling is a critical step for capturing spatiotemporal relationship of joint dynamics. Conventional pooling methods overlook the preservation of motion information and treat each frame…

Accurate traffic forecasting is a fundamental problem in intelligent transportation systems and learning long-range traffic representations with key information through spatiotemporal graph neural networks (STGNNs) is a basic assumption of…

The capability to jointly process multi-modal information is becoming an essential task. However, the limited number of paired multi-modal data and the large computational requirements in multi-modal learning hinder the development. We…

Learning multi-object dynamics from visual data using unsupervised techniques is challenging due to the need for robust, object representations that can be learned through robot interactions. This paper presents a novel framework with two…

Point cloud prediction is an important yet challenging task in the field of autonomous driving. The goal is to predict future point cloud sequences that maintain object structures while accurately representing their temporal motion. These…

An emerging way of tackling the dimensionality issues arising in the modeling of a multivariate process is to assume that the inherent data structure can be captured by a graph. Nevertheless, though state-of-the-art graph-based methods have…