AssemLM: Spatial Reasoning Multimodal Large Language Models for Robotic Assembly

• URL: http://arxiv.org/abs/2604.08983v1
• Date: Fri, 10 Apr 2026 05:43:39 GMT
• Title: AssemLM: Spatial Reasoning Multimodal Large Language Models for Robotic Assembly
• Abstract summary: We propose AssemLM, a spatial multimodal large language model tailored for robotic assembly.<n>AssemLM integrates assembly manuals, point clouds, and textual instructions to reason about and predict task-critical 6D assembly poses.<n>Our model achieves state-of-the-art performance in 6D pose reasoning across diverse assembly scenarios.
• Score: 45.963541758601274
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Spatial reasoning is a fundamental capability for embodied intelligence, especially for fine-grained manipulation tasks such as robotic assembly. While recent vision-language models (VLMs) exhibit preliminary spatial awareness, they largely rely on coarse 2D perception and lack the ability to perform accurate reasoning over 3D geometry, which is crucial for precise assembly operations. To address this limitation, we propose AssemLM, a spatial multimodal large language model tailored for robotic assembly. AssemLM integrates assembly manuals, point clouds, and textual instructions to reason about and predict task-critical 6D assembly poses, enabling explicit geometric understanding throughout the assembly process. To effectively bridge raw 3D perception and high-level reasoning, we adopt a specialized point cloud encoder to capture fine-grained geometric and rotational features, which are then integrated into the multimodal language model to support accurate 3D spatial reasoning for assembly tasks. In addition, we construct AssemBench, a large-scale dataset and benchmark for assembly-oriented spatial reasoning, comprising over 900K multimodal samples with precise 6D pose annotations. AssemBench extends spatial reasoning evaluation beyond 2D and grounding tasks into full 3D geometric inference, filling a critical gap in existing embodied AI benchmarks. Extensive experiments demonstrate that AssemLM achieves state-of-the-art performance in 6D pose reasoning across diverse assembly scenarios. Furthermore, real-robot evaluations show that our model can support fine-grained and multi-step assembly execution in real-world settings, demonstrating its potential for robotic assembly applications.

Related papers

• OmniCAD: A Large-Scale Benchmark for 3D Spatial Reasoning in Robotics Assemblies [12.751658252598366]
  We introduce OmniCAD, a large-scale benchmark for assembly-aware 3D spatial reasoning across diverse industrial systems.<n> OmniCAD contains 25k mechanical assemblies, with an average of 12 parts per assembly and 21 types of mate relationships.<n>We will open-source the benchmark, evaluation code, and tool interfaces to support research on accurate, physically valid, and scalable 3D assembly reasoning.
  arXiv  Detail & Related papers  (2026-08-23T22:42:28Z)
• Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding [34.1504914582344]
  3D Visual Grounding aims to localize objects in 3D scenes via natural language descriptions.<n>We propose "Think, Act, Build (TAB)", a generative 2D-to-3D reconstruction paradigm operating directly on raw RGB-D streams.<n>To overcome the multi-view coverage deficit caused by strict VLM semantic tracking, we introduce the Semantic-Anchored Geometric Expansion.
  arXiv  Detail & Related papers  (2026-04-01T06:12:16Z)
• Zero-Shot Robotic Manipulation via 3D Gaussian Splatting-Enhanced Multimodal Retrieval-Augmented Generation [24.066642344610873]
  Existing end-to-end approaches of robotic manipulation often lack generalization to unseen objects or tasks due to limited data and poor interpretability.<n>We propose RobMRAG, a 3D Gaussian Splatting-Enhanced Multimodal Retrieval-Augmented Generation framework for zero-shot robotic manipulation.<n>Our method improves the success rate by 7.76% compared to the best-performing zero-shot baseline under the same setting, and by 6.54% compared to the state-of-the-art supervised baseline.
  arXiv  Detail & Related papers  (2026-02-28T06:48:05Z)
• Video Spatial Reasoning with Object-Centric 3D Rollout [58.12446467377404]
  We propose Object-Centric 3D Rollout (OCR) to enable robust video spatial reasoning.<n>OCR introduces structured perturbations to the 3D geometry of selected objects during training.<n>OCR compels the model to reason holistically across the entire scene.
  arXiv  Detail & Related papers  (2025-11-17T09:53:41Z)
• Abstract 3D Perception for Spatial Intelligence in Vision-Language Models [100.13033631690114]
  Vision-language models (VLMs) struggle with 3D-related tasks such as spatial cognition and physical understanding.<n>We introduce SandboxVLM, a framework that leverages abstract bounding boxes to encode geometric structure and physical kinematics for VLM.<n>Our approach consistently improves spatial intelligence, achieving an 8.3% gain on SAT Real compared with baseline methods.
  arXiv  Detail & Related papers  (2025-11-14T04:16:09Z)
• Point Linguist Model: Segment Any Object via Bridged Large 3D-Language Model [51.02616473941499]
  3D object segmentation with Large Language Models (LLMs) has become a prevailing paradigm due to its broad semantics, task flexibility, and strong generalization.<n>However, this paradigm is hindered by representation misalignment: LLMs process high-level semantic tokens, whereas 3D point clouds convey only dense geometric structures.<n>We present the Point Linguist Model (PLM), a general framework that bridges the representation gap between LLMs and dense 3D point clouds.
  arXiv  Detail & Related papers  (2025-09-09T15:01:28Z)
• SeqAffordSplat: Scene-level Sequential Affordance Reasoning on 3D Gaussian Splatting [85.87902260102652]
  We introduce the novel task of Sequential 3D Gaussian Affordance Reasoning.<n>We then propose SeqSplatNet, an end-to-end framework that directly maps an instruction to a sequence of 3D affordance masks.<n>Our method sets a new state-of-the-art on our challenging benchmark, effectively advancing affordance reasoning from single-step interactions to complex, sequential tasks at the scene level.
  arXiv  Detail & Related papers  (2025-07-31T17:56:55Z)
• VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction [86.82819259860186]
  We introduce VLM-3R, a unified framework for Vision-Language Models (VLMs) that incorporates 3D Reconstructive instruction tuning.<n>VLM-3R processes monocular video frames by employing a geometry encoder to derive implicit 3D tokens that represent spatial understanding.
  arXiv  Detail & Related papers  (2025-05-26T17:56:30Z)
• LLMI3D: MLLM-based 3D Perception from a Single 2D Image [77.13869413871028]
  multimodal large language models (MLLMs) excel in general capacity but underperform in 3D tasks.<n>In this paper, we propose solutions for weak 3D local spatial object perception, poor text-based geometric numerical output, and inability to handle camera focal variations.<n>We employ parameter-efficient fine-tuning for a pre-trained MLLM and develop LLMI3D, a powerful 3D perception MLLM.
  arXiv  Detail & Related papers  (2024-08-14T10:00:16Z)

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.