19 accepted papers
Normalizing Flows (NFs) have been established as a principled framework for generative modeling. Standard NFs consist of a forward process and a reverse process: the forward process maps data to noise, while the reverse process generates samples by inverting it. Typical NF forward transformations ar
Humanoid robots are expected to operate reliably over long horizons while executing versatile whole-body skills. Yet Reinforcement Learning (RL) motion policies typically lose stability under prolonged operation, sensor/actuator noise, and real world disturbances. In this work, we propose a Selectiv
Modern diffusion/flow-based models for image generation typically exhibit two core characteristics: (i) using multi-step sampling, and (ii) operating in a latent space. Recent advances have made encouraging progress on each aspect individually, paving the way toward one-step diffusion/flow without l…
Legged robots offer significant potential for navigating complex industrial terrains, but their capabilities are often constrained by perception systems struggling to interpret intricate 3D geometry. Conventional 2D/2.5D representations like depth or elevation maps fail to capture complex 3D geometr…
This paper explores the application of large language models (LLMs) in nursing and elderly care, focusing on AI-driven patient monitoring and interaction. We introduce a novel Chinese nursing dataset and implement incremental pre-training (IPT) and supervised fine-tuning (SFT) techniques to enhance…
Large real-world driving datasets have sparked significant research into various aspects of learning-based motion planners for autonomous driving. These include data augmentation, model architecture, reward design, training strategies, and planner pipelines. In this paper, we review and benchmark pr
In robotic reinforcement learning, the Sim2Real gap remains a critical challenge. However, the impact of Static friction on Sim2Real has been underexplored. Conventional domain randomization methods typically exclude Static friction from their parameter space. In our robotic reinforcement learning t
It is widely believed that noise conditioning is indispensable for denoising diffusion models to work successfully. This work challenges this belief. Motivated by research on blind image denoising, we investigate a variety of denoising-based generative models in the absence of noise conditioning. To…
This paper presents an effective approach for learning novel 4D embodied world models, which predict the dynamic evolution of 3D scenes over time in response to an embodied agent's actions, providing both spatial and temporal consistency. We propose to learn a 4D world model by training on RGB-DN (R…
The increasing demands in analyzing complex associated scenes pose necessities to researching multi-image understanding abilities. Compared with understanding individual images, both the alignments and differences between images are essential aspects of understanding the intricate relationships for
Learning-based vehicle planning is receiving increasing attention with the emergence of diverse driving simulators and large-scale driving datasets. While offline reinforcement learning (RL) is well suited for these safety-critical tasks, it still struggles to plan over extended periods. In this wor…
Aspect Sentiment Triplet Extraction (ASTE) aims to co-extract the sentiment triplets in a given corpus. Existing approaches within the pretraining-finetuning paradigm tend to either meticulously craft complex tagging schemes and classification heads, or incorporate external semantic augmentation to…
Offline Reinforcement Learning (RL) enables policy learning without active interactions, making it especially appealing for self-driving tasks. Recent successes of Transformers inspire casting offline RL as sequence modeling, which, however, fails in stochastic environments with incorrect assumption…
Motion prediction is crucial in enabling safe motion planning for autonomous vehicles in interactive scenarios. It allows the planner to identify potential conflicts with other traffic agents and generate safe plans. Existing motion predictors often focus on reducing prediction errors, yet it remain…
Interactive traffic simulation is crucial to autonomous driving systems by enabling testing for planners in a more scalable and safe way compared to real-world road testing. Existing approaches learn an agent model from large-scale driving data to simulate realistic traffic scenarios, yet it remains…
Predicting future motions of road participants is an important task for driving autonomously in urban scenes. Existing models excel at predicting marginal trajectories for single agents, yet it remains an open question to jointly predict scene compliant trajectories over multiple agents. The challen…
The autonomous robots consisting of an immovable lander and a rover are widely deployed to explore extraterrestrial planets. However, these robots have two main limitations: (1) the separate design for lander and rover respectively results in heavy mass and big volume of the whole system, which incr…
This paper proposes a method of tire force estimation designed for use in navigation decision making for Unmanned Ground Vehicles (UGVs) operating on off-road terrains. This method (called the Centroid Method) uses a 3D point cloud representation of the terrain to determine tire-ground interaction,…
This paper describes a method of vehicle state prediction for an autonomous high-speed off-road Unmanned Ground Vehicle (UGV). Effective vehicle state prediction will allow a UGV to plan its navigation such that states (such as vertical acceleration induced by the terrain roughness) never exceed a d…