25 accepted papers
Inference-time compute has re-emerged as a practical way to improve LLM reasoning. Most test-time scaling (TTS) algorithms rely on autoregressive decoding, which is ill-suited to discrete diffusion language models (dLLMs) due to their parallel decoding over the entire sequence. As a result, developi…
In large-scale heterogeneous robot systems (HRS), scheduling efficiency in terms of throughput and makespan relies on exploiting parallel execution, while human-issued safety and precedence instructions impose rigid temporal-logic constraints that create severe combinatorial complexity and challenge…
Recent advancements in multi-robot navigation have explored methods that combine Large Language Models (LLMs) for tasks like scene understanding or high-level decision-making. However, these approaches face challenges with high inference latency and potential hallucinations. To address these challen
Existing trajectory prediction methods exhibit significant performance degradation under distribution shifts during test time. Although test-time training techniques have been explored to enable adaptation, current approaches rely on an offline pre-trained predictor that lacks online learning flexib…
Query-based models are extensively used in 3D object detection tasks, with a wide range of pre-trained checkpoints readily available online. However, despite their popularity, these models often require an excessive number of object queries, far surpassing the actual number of objects to detect. The
Autonomous navigation in complex dynamic environments remains a fundamental challenge in robotics, and many reinforcement learning (RL) algorithms have demonstrated promising results, especially the on-policy ones. However, the inherent sample efficiency issue is still a fundamental problem to be so…
Egocentricly comprehending the causes and effects of car accidents is crucial for the safety of self-driving cars, and synthesizing causal-entity reflected accident videos can facilitate the capability test to respond to unaffordable accidents in reality. However, incorporating causal relations as s…
Autonomous vehicle trajectory planning faces significant challenges in dynamic traffic environments due to the complex and mixed causal relationships between critical scene elements (e.g., pedestrians, vehicles, road markings) and safe decision-making. To identify the causal factors influencing plan
We present MM-AU a novel dataset for Multi-Modal Accident video Understanding. MM-AU contains 11727 in-the-wild ego-view accident videos each with temporally aligned text descriptions. We annotate over 2.23 million object boxes and 58650 pairs of video-based accident reasons covering 58 accident cat…
High-Definition (HD) map construction is essential for autonomous driving to accurately understand the surrounding environment. Most existing methods rely on single-frame inputs to predict local map, which often fail to effectively capture the temporal correlations between frames. This limitation re
In autonomous driving, predicting the behavior (turning left, stopping, etc.) of target vehicles is crucial for the self-driving vehicle to make safe decisions and avoid accidents. Existing deep learning-based methods have shown excellent and accurate performance, but the black-box nature makes it u…
LiDAR-Camera online calibration is of great significance for building a stable autonomous driving perception system. For online calibration, a key challenge lies in constructing a unified and robust representation between multi-modal sensor data. Most methods extract features manually or implicitly…
Predicting the future trajectories of the traffic agents is a gordian technique in autonomous driving. However, trajectory prediction suffers from data imbalance in the prevalent datasets, and the tailed data is often more complicated and safety-critical. In this paper, we focus on dealing with the…
Vision-based localization in a prior map is of crucial importance for autonomous vehicles. Given a query image, the goal is to estimate the camera pose corresponding to the prior map, and the key is the registration problem of camera images within the map. While autonomous vehicles drive on the road
Learning an optimal policy for autonomous driving task to confront with complex environment is a long- studied challenge. Imitative reinforcement learning is accepted as a promising approach to learn a robust driving policy through expert demonstrations and interactions with environments. However, t…
Skeleton-based human action recognition has attracted great interest thanks to the easy accessibility of the human skeleton data. Recently, there is a trend of using very deep feedforward neural networks to model the 3D coordinates of joints without considering the computational efficiency. In this…
In autonomous driving community, numerous benchmarks have been established to assist the tasks of 3D/2D object detection, stereo vision, semantic/instance segmentation. However, the more meaningful dynamic evolution of the surrounding objects of ego-vehicle is rarely exploited, and lacks a large-sca…
Robust 3D perception using LiDAR is of prime importance for robotics, and its fundamental core lies in precise object modelling resisting to noise and outliers. In this paper, a precise 3D object modelling algorithm is designed especially for the intelligent vehicles. The proposed algorithm is advan…
This paper proposes a SEG-VoxelNet that takes RGB images and LiDAR point clouds as inputs for accurately detecting 3D vehicles in autonomous driving scenarios, which for the first time introduces semantic segmentation technique to assist the 3D LiDAR point cloud based detection. Specifically, SEG-Vo…
In crowd scenarios, reliable trajectory prediction of pedestrians requires insightful understanding of their social behaviors. These behaviors have been well investigated by plenty of studies, while it is hard to be fully expressed by hand-craft rules. Recent studies based on LSTM networks have show…
Highly accurate mapping and localization is of prime importance for mobile robotics, and its core lies in efficient scan matching. Previous research are focusing on designing a robust objective function and the residual error distribution is often ignored or simply assumed as unitary or mixture of s…
Recurrent neural networks (RNNs) are capable of modeling the temporal dynamics of complex sequential information. However, the structures of existing RNN neurons mainly focus on controlling the contributions of current and historical information but do not explore the different importance levels of…
We develop a unified framework for complex event retrieval, recognition and recounting. The framework is based on a compact video representation that exploits the temporal correlations in image features. Our feature alignment procedure identifies and removes the feature redundancies across frames an…
Skeleton-based human action recognition has recently attracted increasing attention due to the popularity of 3D skeleton data. One main challenge lies in the large view variations in captured human actions. We propose a novel view adaptation scheme to automatically regulate observation viewpoints du…
Color composition is an important property for many computer vision tasks like image retrieval and object classification. In this paper we address the problem of inferring the color composition of the intrinsic reflectance of objects, where the shadows and highlights may change the observed color dr…