Related papers: TrajTok: Technical Report for 2025 Waymo Open Sim …

Driving scene understanding task involves detecting static elements such as lanes, traffic signs, and traffic lights, and their relationships with each other. To facilitate the development of comprehensive scene understanding solutions…

Autonomous vehicles (AVs) must navigate dynamic urban environments where occlusions and perception limitations introduce significant uncertainties. This research builds upon and extends existing approaches in risk-aware motion planning and…

This paper jointly addresses three key limitations in conventional pedestrian trajectory forecasting: pedestrian perception errors, real-world data collection costs, and person ID annotation costs. We propose a novel framework, RealTraj,…

Recent spatio-temporal data applications, such as car-shar\-ing and smart cities, impose new challenges regarding the scalability and timeliness of data processing systems. Trajectory compression is a promising approach for scaling up…

The development of unified multimodal large language models (MLLMs) is fundamentally challenged by the granularity gap between visual understanding and generation: understanding requires high-level semantic abstractions, while image…

Large language models (LLMs) exhibit strong reasoning capabilities but typically require expensive post-training to reach high performance. Recent test-time alignment methods offer a lightweight alternative, but have been explored mainly…

A critical step in topology optimization (TO) is finding sensitivities. Manual derivation and implementation of the sensitivities can be quite laborious and error-prone, especially for non-trivial objectives, constraints and material…

VQ-based image generation typically follows a two-stage pipeline: a tokenizer encodes images into discrete tokens, and a generative model learns their dependencies for reconstruction. However, improved tokenization in the first stage does…

Trajectory prediction is a safety-critical tool for autonomous vehicles to plan and execute actions. Our work addresses two key challenges in trajectory prediction, learning multimodal outputs, and better predictions by imposing constraints…

This paper presents YatSim, an open-source program for simulating consensus-based control strategies in urban traffic networks. Urban traffic is a multi-agent system which requires agreement among the agents to guarantees performance,…

Image tokenization has enabled major advances in autoregressive image generation by providing compressed, discrete representations that are more efficient to process than raw pixels. While traditional approaches use 2D grid tokenization,…

LLM agents rely heavily on high-quality trajectory data to guide their problem-solving behaviors, yet producing such data requires substantial task design, high-capacity model generation, and manual filtering. Despite the high cost of…

In this article we briefly present our contributions toward Trading Agent Competition (TAC); an international forum for promotion of research into the trading agent problems. Moreover, we present some strategies proposed and used in the…

Learning interactive motion behaviors among multiple agents is a core challenge in autonomous driving. While imitation learning models generate realistic trajectories, they often inherit biases from datasets dominated by safe…

Real-world time series data are inherently multivariate, often exhibiting complex inter-channel dependencies. Each channel is typically sampled at its own period and is prone to missing values due to various practical and operational…

We propose Token Turing Machines (TTM), a sequential, autoregressive Transformer model with memory for real-world sequential visual understanding. Our model is inspired by the seminal Neural Turing Machine, and has an external memory…

Visual observation of objects is essential for many robotic applications, such as object reconstruction and manipulation, navigation, and scene understanding. Machine learning algorithms constitute the state-of-the-art in many fields but…

Visual object tracking has focused predominantly on opaque objects, while transparent object tracking received very little attention. Motivated by the uniqueness of transparent objects in that their appearance is directly affected by the…

Future Tele-operated Driving (ToD) applications place challenging Quality of Service (QoS) demands on existing mobile communication networks that are of highly important to comply with for safe operation. New remote control and platooning…

Modelling student knowledge is a key challenge when leveraging AI in education, with major implications for personalised learning. The Knowledge Tracing (KT) task aims to predict how students will respond to educational questions in…