Related papers: RoboStream: Weaving Spatio-Temporal Reasoning with…
Long-horizon robotic manipulation requires bridging the gap between high-level planning (System 2) and low-level control (System 1). Current Vision-Language-Action (VLA) models often entangle these processes, performing redundant multimodal…
Vision-Language-Action (VLA) models have recently shown strong generalization, with some approaches seeking to explicitly generate linguistic reasoning traces or predict future observations prior to execution. However, explicit reasoning…
Learning long-horizon robotic manipulation requires jointly achieving expressive behavior modeling, real-time inference, and stable execution, which remains challenging for existing generative policies. Diffusion-based approaches offer…
Topological strategies for navigation meaningfully reduce the space of possible actions available to a robot, allowing use of heuristic priors or learning to enable computationally efficient, intelligent planning. The challenges in…
Despite impressive high-level video comprehension, multimodal language models struggle with spatial reasoning across time and space. While current spatial training approaches rely on real-world video data, obtaining diverse footage with…
Video diffusion models are moving beyond short, plausible clips toward world simulators that must remain consistent under camera motion, revisits, and intervention. Yet spatial memory remains a key bottleneck: explicit 3D structures can…
The ability to navigate and interact with complex environments is central to real-world embodied agents, yet navigation in unseen environments remains challenging due to "experiential amnesia," where existing trajectory-driven or reactive…
The development of generalist robot manipulation policies has seen significant progress, driven by large-scale demonstration data across diverse environments. However, the high cost and inefficiency of collecting real-world demonstrations…
Spatial reasoning in large language models (LLMs) has gained increasing attention due to applications in navigation and planning. Despite strong general language capabilities, LLMs still struggle with spatial transformations and multi-step…
We present Points2Plans, a framework for composable planning with a relational dynamics model that enables robots to solve long-horizon manipulation tasks from partial-view point clouds. Given a language instruction and a point cloud of the…
Reasoning is central to purposeful action, yet most robotic foundation models map perception and instructions directly to control, which limits adaptability, generalization, and semantic grounding. We introduce Action Reasoning Models…
Solving complex, long-horizon robotic manipulation tasks requires a deep understanding of physical interactions, reasoning about their long-term consequences, and precise high-level planning. Vision-Language Models (VLMs) offer a general…
Capturing spatial relationships from visual inputs is a cornerstone of human-like general intelligence. Several previous studies have tried to enhance the spatial awareness of Vision-Language Models (VLMs) by adding extra expert encoders,…
Despite recent advancements in Multi-modal Large Language Models (MLLMs) on diverse understanding tasks, these models struggle to solve problems which require extensive multi-step reasoning. This is primarily due to the progressive dilution…
Humans excel at spatial reasoning tasks like Tangram puzzle assembly through cognitive processes involving mental rotation, iterative refinement, and visual feedback. Inspired by how humans solve Tangram puzzles through trial-and-error,…
Multimodal large language models (MLLMs) have achieved strong performance on perception-oriented tasks, yet their ability to perform mathematical spatial reasoning, defined as the capacity to parse and manipulate two- and three-dimensional…
Humans possess the visual-spatial intelligence to remember spaces from sequential visual observations. However, can Multimodal Large Language Models (MLLMs) trained on million-scale video datasets also ``think in space'' from videos? We…
Visual reasoning, particularly spatial reasoning, is a challenging cognitive task that requires understanding object relationships and their interactions within complex environments, especially in robotics domain. Existing vision_language…
In the endeavor to make autonomous robots take actions, task planning is a major challenge that requires translating high-level task descriptions to long-horizon action sequences. Despite recent advances in language model agents, they…
Genuine spatial reasoning relies on the capacity to construct and manipulate coherent internal spatial representations, often conceptualized as mental models, rather than merely processing surface linguistic associations. While large…