Technical Report of RoboSpatial Challenge at CVPR 2026: Selective Reasoning Activation and Reference-Frame Disambiguation for Embodied Spatial Reasoning

• URL: http://arxiv.org/abs/2606.31645v1
• Date: Tue, 30 Jun 2026 13:25:59 GMT
• Title: Technical Report of RoboSpatial Challenge at CVPR 2026: Selective Reasoning Activation and Reference-Frame Disambiguation for Embodied Spatial Reasoning
• Abstract summary: We present RoboSpatialBrain, our submission to the RoboSpatial Challenge at the Embodied Reasoning in Action Workshop.<n>RoboSpatialBrain combines two training-free, inference-time mechanisms.<n>RoboSpatialBrain achieved first place in the RoboSpatial Challenge, with an overall success rate of 80.9% on RoboSpatial-Home.
• Score: 55.11480729304395
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-language models achieve strong general perception but often struggle with the spatial reasoning required for embodied tasks. We present RoboSpatialBrain, our submission to the RoboSpatial Challenge at the Embodied Reasoning in Action Workshop, CVPR 2026, built on RoboBrain2.5-8B-NV. RoboSpatialBrain combines two training-free, inference-time mechanisms: a forced <think> prefix activation strategy paired with a task-specific post-prompt that elicits deliberate reasoning on context and compatibility tasks, and an explicit reference-frame redirection pipeline that resolves camera-centric and object-centric ambiguity for context tasks. We additionally explore fine-tuning RoboBrain2.5 on compatibility data and present a detailed analysis of its interaction with prompting. RoboSpatialBrain achieved first place in the RoboSpatial Challenge, with an overall success rate of 80.9\% on RoboSpatial-Home. Code is available at https://github.com/YuxiangXie2003/RoboSpatialBrain.

Related papers

• RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures [51.85284871989367]
  We propose RoboTALES, a framework that learns task-aligned simulated futures and uses them to train robot policies.<n>Our approach introduces two key innovations: (1) a hierarchical LLM-based planner that breaks complex tasks into a sequence of subgoals to guide the model's imagination; and (2) a VLM-based critic that evaluates these imagined'' futures and uses reward-based feedback to keep the model's internal representations focused on the goal.
  arXiv  Detail & Related papers  (2026-07-07T08:58:29Z)
• RoboWits: Unexpected Challenges for Robotic Creative Problem Solving [58.58727722988084]
  We introduce RoboWits, a bi-manual robotic benchmark designed to evaluate cognitive reasoning, creative tool use, and robustness to unexpected conditions.<n>Using the pipeline, we curated 30 diverse seed tasks and 208 tasks with mutations and graded difficulty across geometry, material, and assembly-based reasoning.<n>Our results reveal a significant performance gap: while pre-trained VLAs exhibit preliminary success on seed tasks after single-task fine-tuning, they struggle to perform on mutated tasks.
  arXiv  Detail & Related papers  (2026-05-28T17:57:15Z)
• RoboKA: KAN Informed Multimodal Learning for RoboCall Surveillance System [11.827126059853342]
  Wide exploration on robocall surveillance research is hindered due to limited access to public datasets, due to privacy concerns.<n>We first curate Robo-SAr, a synthetic robocall dataset designed for robocall surveillance research.<n>We propose RoboKA, a multimodal fusion framework designed to model structured nonlinear interactions between acoustic and linguistic cues that characterize adversarial robocall strategies.
  arXiv  Detail & Related papers  (2026-04-30T19:25:53Z)
• Robobench: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models as Embodied Brain [62.01012517796797]
  Building robots that can perceive, reason, and act in dynamic, unstructured environments remains a core challenge.<n>Recent embodied systems often adopt a dual-system paradigm, where System 2 handles high-level reasoning while System 1 executes low-level control.<n>We introduce RoboBench, a benchmark that systematically evaluates multimodal large language models (MLLMs) as embodied brains.
  arXiv  Detail & Related papers  (2025-10-20T17:59:03Z)
• RoboPilot: Generalizable Dynamic Robotic Manipulation with Dual-thinking Modes [5.47460315248808]
  We present RoboPilot, a dual-thinking closed-loop framework for robotic manipulation.<n>RoboPilot supports adaptive reasoning for complex tasks in real-world dynamic environments.<n>We show that RoboPilot outperforms state-of-the-art baselines by 25.9% in task success rate.
  arXiv  Detail & Related papers  (2025-09-30T18:25:47Z)
• Robix: A Unified Model for Robot Interaction, Reasoning and Planning [28.191138548365203]
  Robix is a unified model that integrates robot reasoning, task planning, and natural language interaction within a single vision-language architecture.<n>Robix dynamically generates atomic commands for the low-level controller and verbal responses for human interaction.
  arXiv  Detail & Related papers  (2025-09-01T03:53:47Z)
• RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied Systems [41.89907261427986]
  Embodied agents face persistent challenges in real-world environments, including partial observability, limited spatial reasoning, and high-latency multi-memory integration.<n>We present RoboMemory, a brain-inspired framework that unifies Spatial, Temporal, Episodic, and Semantic memory under a parallelized architecture for efficient long-horizon planning and interactive environmental learning.<n> Experiments on EmbodiedBench show that RoboMemory, built on Qwen2.5-VL-72B-Ins, improves average success rates by 25% over its baseline and exceeds the closed-source state-of-the-art (SOTA) Gemini-1.5-
  arXiv  Detail & Related papers  (2025-08-02T15:39:42Z)
• Benchmarking Generalizable Bimanual Manipulation: RoboTwin Dual-Arm Collaboration Challenge at CVPR 2025 MEIS Workshop [120.2806035123366]
  RoboTwin Dual-Arm Collaboration Challenge was held at the 2nd MEIS Workshop, CVPR 2025.<n>Competitors totally tackled 17 dual-arm manipulation tasks, covering rigid, deformable, and tactile-based scenarios.<n>Report outlines the competition setup, task design, evaluation methodology, key findings and future direction.
  arXiv  Detail & Related papers  (2025-06-29T17:56:41Z)
• RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics [67.11221574129937]
  Spatial referring is a fundamental capability of embodied robots to interact with the 3D physical world.<n>We propose RoboRefer, a 3D-aware VLM that can first achieve precise spatial understanding.<n>RoboRefer advances generalized multi-step spatial reasoning via reinforcement fine-tuning.
  arXiv  Detail & Related papers  (2025-06-04T17:59:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.