Spatio-Temporal LLM: Reasoning about Environments and Actions
This addresses a problem for agents operating in the real world by improving holistic spatio-temporal understanding, though it appears incremental as it builds on existing MLLM frameworks.
The paper tackles the challenge of multimodal large language models (MLLMs) struggling with spatio-temporal prompts that require understanding entire environments from point clouds and actions from video clips, and it shows that their proposed STLLM baselines outperform existing models on the collected REA dataset.
Despite significant recent progress of Multimodal Large Language Models (MLLMs), current MLLMs are challenged by "spatio-temporal" prompts, i.e., prompts that refer to 1) the entirety of an environment encoded in a point cloud that the MLLM should consider; and simultaneously also refer to 2) actions that happened in part of the environment and are encoded in a short ego-centric video clip. However, such a holistic spatio-temporal understanding is important for agents operating in the real world. To address this challenge, we first develop a framework to collect a large-scale dataset. Using the collected "Reasoning about Environments and Actions" (REA) dataset, we show that recent MLLMs indeed struggle to correctly answer "spatio-temporal" prompts. Building on this dataset, we study two spatio-temporal LLM (STLLM) baselines: 1) STLLM-3D, which directly fuses point cloud, video, and text representations as inputs to the LLM; and 2) STLLM-Aligner, which aligns spatial context with video and text before LLM decoding. Both baselines aim to enhance spatial understanding of environments and temporal grounding of egocentric observations. On REA, the STLLM baselines outperform existing models, demonstrating the effectiveness of our designs. Code and data are available at https://zoezheng126.github.io/STLLM-website/.