Related papers: SparseWorld: A Flexible, Adaptive, and Efficient 4…

Cooperative perception can increase the view field and decrease the occlusion of an ego vehicle, hence improving the perception performance and safety of autonomous driving. Despite the success of previous works on cooperative object…

World models aim to predict plausible futures consistent with past observations, a capability central to planning and decision-making in reinforcement learning. Yet, existing architectures face a fundamental memory trade-off: transformers…

State-of-the-art navigation methods leverage a spatial memory to generalize to new environments, but their occupancy maps are limited to capturing the geometric structures directly observed by the agent. We propose occupancy anticipation,…

In the context of autonomous vehicles, one of the most crucial tasks is to estimate the risk of the undertaken action. While navigating in complex urban environments, the Bayesian occupancy grid is one of the most popular types of maps,…

Neural radiance field (NeRF) has achieved great success in novel view synthesis and 3D representation for static scenarios. Existing dynamic NeRFs usually exploit a locally dense grid to fit the deformation field; however, they fail to…

Neural networks augmented with external memory have the ability to learn algorithmic solutions to complex tasks. These models appear promising for applications such as language modeling and machine translation. However, they scale poorly in…

We propose Sparse Sinkhorn Attention, a new efficient and sparse method for learning to attend. Our method is based on differentiable sorting of internal representations. Concretely, we introduce a meta sorting network that learns to…

We propose a general dynamic reduced-order modeling framework for typical experimental data: time-resolved sensor data and optional non-time-resolved PIV snapshots. This framework contains four steps. First, the sensor signals are lifted to…

Forecasting the evolution of 3D scenes and generating unseen scenarios via occupancy-based world models offers substantial potential for addressing corner cases in autonomous driving systems. While tokenization has revolutionized image and…

Occupancy grids encode for hot spots on a map that is represented by a two dimensional grid of disjoint cells. The problem is to recursively update the probability that each cell in the grid is occupied, based on a sequence of sensor…

World models are critical for autonomous driving to simulate environmental dynamics and generate synthetic data. Existing methods struggle to disentangle ego-vehicle motion (perspective shifts) from scene evolvement (agent interactions),…

Sparse representations has shown to be a very powerful model for real world signals, and has enabled the development of applications with notable performance. Combined with the ability to learn a dictionary from signal examples,…

While 3D object bounding box (bbox) representation has been widely used in autonomous driving perception, it lacks the ability to capture the precise details of an object's intrinsic geometry. Recently, occupancy has emerged as a promising…

Extraction of low-dimensional latent space from high-dimensional observation data is essential to construct a real-time robot controller with a world model on the extracted latent space. However, there is no established method for tuning…

While sparse attention mitigates the computational bottleneck of long-context LLM training, its distributed training process exhibits extreme heterogeneity in both \textit{1)} sequence length and \textit{2)} sparsity sensitivity, leading to…

Modeling multivariate time series as temporal signals over a (possibly dynamic) graph is an effective representational framework that allows for developing models for time series analysis. In fact, discrete sequences of graphs can be…

3D occupancy prediction is critical for comprehensive scene understanding in vision-centric autonomous driving. Recent advances have explored utilizing 3D semantic Gaussians to model occupancy while reducing computational overhead, but they…

Autonomous agents operating in dynamic and safety-critical environments require decision-making frameworks that are both computationally efficient and physically grounded. However, many existing approaches rely on end-to-end learning, which…

Distributional models provide a convenient way to model semantics using dense embedding spaces derived from unsupervised learning algorithms. However, the dimensions of dense embedding spaces are not designed to resemble human semantic…

Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of…