ServiceNow AI Research

Multi-modal Learning

StarVector: Generating Scalable Vector Graphics Code from Images and Text
Scalable Vector Graphics (SVGs) are vital for modern image rendering due to their scalability and versatility. Previous SVG generation …
Multimodal foundation world models for generalist embodied agents
Learning generalist agents, able to solve multitudes of tasks in different domains is a long-standing problem. Reinforcement learning …
Representing Positional Information in Generative World Models for Object Manipulation
The ability to predict outcomes of interactions between embodied agents and objects is paramount in the robotic setting. While …
VCR: Visual Caption Restoration
We introduce Visual Caption Restoration (VCR), a novel vision-language task that challenges models to accurately restore partially …
WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks
The ability of large language models (LLMs) to mimic human-like intelligence has led to a surge in LLM-based autonomous agents. Though …
Multimodal foundation world models for generalist embodied agents
Learning generalist embodied agents, able to solve multitudes of tasks in different domains is a long-standing problem. Reinforcement …
InCoRo: In-Context Learning for Robotics Control with Feedback Loops
One of the challenges in robotics is to enable robotic units with the reasoning capability that would be robust enough to execute …
StarVector: Generating Scalable Vector Graphics Code from Images and Text
Scalable Vector Graphics (SVGs) have become integral in modern image rendering and graphic design applications due to their infinite …
Are Diffusion Models Vision-And-Language Reasoners?
Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, …