Related papers: Narrowing the Coordinate-frame Gap in Behavior Pre…
The unsupervised Pretraining method has been widely used in aiding human action recognition. However, existing methods focus on reconstructing the already present frames rather than generating frames which happen in future.In this paper, We…
Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold. However, current agentic systems lack a principled understanding of when and why…
Wearable collaborative robots stand to assist human wearers who need fall prevention assistance or wear exoskeletons. Such a robot needs to be able to constantly adapt to the surrounding scene based on egocentric vision, and predict the ego…
Diffusion generative models have demonstrated remarkable success in visual domains such as image and video generation. They have also recently emerged as a promising approach in robotics, especially in robot manipulations. Diffusion models…
Recently, large language models (LLMs) have shown great promise in time series forecasting. However, most existing LLM-based forecasting methods still follow a static generative paradigm that directly maps historical observations to future…
Modeling how human moves in the space is useful for policy-making in transportation, public safety, and public health. Human movements can be viewed as a dynamic process that human transits between states (\eg, locations) over time. In the…
Recently, model-based agents have achieved better performance than model-free ones using the same computational budget and training time in single-agent environments. However, due to the complexity of multi-agent systems, it is tough to…
A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the…
Trajectory prediction is a fundamental task in Autonomous Vehicles (AVs) and Intelligent Transportation Systems (ITS), supporting efficient motion planning and real-time traffic safety management. Diffusion models have recently demonstrated…
Despite impressive advancements in Autonomous Driving Systems (ADS), navigation in complex road conditions remains a challenging problem. There is considerable evidence that evaluating the subjective risk level of various decisions can…
Consider scene understanding problems such as predicting where a person is probably reaching, or inferring the pose of 3D objects from depth images, or inferring the probable street crossings of pedestrians at a busy intersection. This…
Accurate motion forecasting is crucial for safe autonomous driving (AD). This study proposes CoT-Drive, a novel approach that enhances motion forecasting by leveraging large language models (LLMs) and a chain-of-thought (CoT) prompting…
Classical paradigms for distributed learning, such as federated or decentralized gradient descent, employ consensus mechanisms to enforce homogeneity among agents. While these strategies have proven effective in i.i.d. scenarios, they can…
Accurate trajectory prediction is critical for safe autonomous navigation, yet the impact of dataset design on model performance remains understudied. This work systematically examines how feature selection, cross-dataset transfer, and…
Accurate motion forecasting for traffic agents is crucial for ensuring the safety and efficiency of autonomous driving systems in dynamically changing environments. Mainstream methods adopt a one-query-one-trajectory paradigm, where each…
World modelling, i.e. building a representation of the rules that govern the world so as to predict its evolution, is an essential ability for any agent interacting with the physical world. Recent applications of the Transformer…
Learning a latent dynamics model provides a task-agnostic representation of an agent's understanding of its environment. Leveraging this knowledge for model-based reinforcement learning (RL) holds the potential to improve sample efficiency…
Collaborative decision making in multi-agent systems typically requires a predefined communication protocol among agents. Usually, agent-level observations are locally processed and information is exchanged using the predefined protocol,…
Video prediction is a fundamental task for various downstream applications, including robotics and world modeling. Although general video prediction models have achieved remarkable performance in standard scenarios, occlusion is still an…
We describe the results of analytic calculations and computer simulations of adaptive predictors (predictive agents) responding to an evolving chaotic environment and to one another. Our simulations are designed to quantify adaptation and…