Related papers: Behavioral Simulations in MapReduce
Learning a perception and reasoning module for robotic assistants to plan steps to perform complex tasks based on natural language instructions often requires large free-form language annotations, especially for short high-level…
Test-time compute scaling has emerged as a powerful paradigm for enhancing mathematical reasoning in large language models (LLMs) by allocating additional computational resources during inference. However, current methods employ uniform…
In a multi-agent system, agents share their local observations to gain global situational awareness for decision making and collaboration using a message passing system. When to send a message, how to encode a message, and how to leverage…
Due to decelerating gains in single-core CPU performance, computationally expensive simulations are increasingly executed on highly parallel hardware platforms. Agent-based simulations, where simulated entities act with a certain degree of…
Efficient localization and high-quality rendering in large-scale scenes remain a significant challenge due to the computational cost involved. While Scene Coordinate Regression (SCR) methods perform well in small-scale localization, they…
We explore the use of the Cell Broadband Engine (Cell/BE for short) for combinatorial optimization applications: we present a parallel version of a constraint-based local search algorithm that has been implemented on a multiprocessor…
Simulation code for conventional supercomputers serves as a reference for neuromorphic computing systems. The present bottleneck of distributed large-scale spiking neuronal network simulations is the communication between compute nodes.…
Predicting and planning interactive behaviors in complex traffic situations presents a challenging task. Especially in scenarios involving multiple traffic participants that interact densely, autonomous vehicles still struggle to interpret…
We present Megaverse, a new 3D simulation platform for reinforcement learning and embodied AI research. The efficient design of our engine enables physics-based simulation with high-dimensional egocentric observations at more than 1,000,000…
We present GRACE, a simulation-native agent for autonomous experimental design in high-energy and nuclear physics. Given multimodal input in the form of a natural-language prompt or a published experimental paper, the agent extracts a…
User simulators are essential for the scalable training and evaluation of interactive AI systems. However, existing approaches often rely on shallow user profiling, struggle to maintain persona consistency over long interactions, and are…
Reinforcement learning (RL) has made a lot of advances for solving a single problem in a given environment; but learning policies that generalize to unseen variations of a problem remains challenging. To improve sample efficiency for…
Scaling data and models has played a pivotal role in the remarkable progress of computer vision and language. Inspired by these domains, recent efforts in robotics have similarly focused on scaling both data and model size to develop more…
Recent Multi-Agent Reinforcement Learning (MARL) literature has been largely focused on Centralized Training with Decentralized Execution (CTDE) paradigm. CTDE has been a dominant approach for both cooperative and mixed environments due to…
More and more large data collections are gathered worldwide in various IT systems. Many of them possess the networked nature and need to be processed and analysed as graph structures. Due to their size they require very often usage of…
With more advanced natural language understanding and reasoning capabilities, large language model (LLM)-powered agents are increasingly developed in simulated environments to perform complex tasks, interact with other agents, and exhibit…
Simulating student learning behaviors in open-ended problem-solving environments holds potential for education research, from training adaptive tutoring systems to stress-testing pedagogical interventions. However, collecting authentic data…
Advancing Multi-Agent Pathfinding (MAPF) and Multi-Robot Motion Planning (MRMP) requires platforms that enable transparent, reproducible comparisons across modeling choices. Existing tools either scale under simplifying assumptions (grids,…
Embodied agents capable of complex physical skills can improve productivity, elevate life quality, and reshape human-machine collaboration. We aim at autonomous training of embodied agents for various tasks involving mainly large foundation…
Real-world data collection for embodied agents remains costly and unsafe, calling for scalable, realistic, and simulator-ready 3D environments. However, existing scene-generation systems often rely on rule-based or task-specific pipelines,…