相关论文: Masked Trajectory Models for Prediction, Represent…

Multi-object tracking (MOT) and trajectory prediction are two critical components in modern 3D perception systems that require accurate modeling of multi-agent interaction. We hypothesize that it is beneficial to unify both tasks under one…

Deploying learned control policies in real-world environments poses a fundamental challenge. When system dynamics change unexpectedly, performance degrades until models are retrained on new data. We introduce Reflexive World Models (RWM), a…

How do masked language models (MLMs) such as BERT learn contextual representations? In this work, we analyze the learning dynamics of MLMs. We find that MLMs adopt sampled embeddings as anchors to estimate and inject contextual semantics to…

Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models (ARMs) for language modeling. However, MDMs are known to learn substantially more slowly than ARMs, which may become problematic when scaling…

A key component of model-based reinforcement learning (RL) is a dynamics model that predicts the outcomes of actions. Errors in this predictive model can degrade the performance of model-based controllers, and complex Markov decision…

Trajectory prediction is a challenging problem that requires considering interactions among multiple actors and the surrounding environment. While data-driven approaches have been used to address this complex problem, they suffer from…

This paper studies sequence modeling for prediction tasks with long range dependencies. We propose a new formulation for state space models (SSMs) based on learning linear dynamical systems with the spectral filtering algorithm (Hazan et…

Model-driven engineering problems often require complex model transformations (MTs), i.e., MTs that are chained in extensive sequences. Pertinent examples of such problems include model synchronization, automated model repair, and design…

Multimodal learning seeks to combine data from multiple input sources to enhance the performance of different downstream tasks. In real-world scenarios, performance can degrade substantially if some input modalities are missing. Existing…

Representation multi-task learning (MTL) has achieved tremendous success in practice. However, the theoretical understanding of these methods is still lacking. Most existing theoretical works focus on cases where all tasks share the same…

Multi-task learning (MTL) aims to improve the generalization of several related tasks by learning them jointly. As a comparison, in addition to the joint training scheme, modern meta-learning allows unseen tasks with limited labels during…

Object recognition and motion understanding are key components of perception that complement each other. While self-supervised learning methods have shown promise in their ability to learn from unlabeled data, they have primarily focused on…

We propose and show the efficacy of a new method to address generic inverse problems. Inverse modeling is the task whereby one seeks to determine the control parameters of a natural system that produce a given set of observed measurements.…

How to learn discriminative video representation from unlabeled videos is challenging but crucial for video analysis. The latest attempts seek to learn a representation model by predicting the appearance contents in the masked regions.…

The prosperity of Multimodal Large Language Models (MLLMs) has stimulated the demand for video reasoning segmentation, which aims to segment video objects based on human instructions. Previous studies rely on unidirectional and implicit…

Multi-task learning (MTL) improves prediction performance in different contexts by learning models jointly on multiple different, but related tasks. Network data, which are a priori data with a rich relational structure, provide an…

Analyzing and forecasting trajectories of agents like pedestrians plays a pivotal role for embodied intelligent applications. The inherent indeterminacy of human behavior and complex social interaction among a rich variety of agents make…

Long Short-Term Memory (LSTM) networks are often used to capture temporal dependency patterns. By stacking multi-layer LSTM networks, it can capture even more complex patterns. This paper explores the effectiveness of applying stacked LSTM…

Most offline reinforcement learning (RL) algorithms return a target policy maximizing a trade-off between (1) the expected performance gain over the behavior policy that collected the dataset, and (2) the risk stemming from the…

Autonomous driving technology can improve traffic safety and reduce traffic accidents. In addition, it improves traffic flow, reduces congestion, saves energy and increases travel efficiency. In the relatively mature automatic driving…