# VCoT-Grasp: Grasp Foundation Models with Visual Chain-of-Thought Reasoning for Language-driven Grasp Generation

arXiv: https://arxiv.org/abs/2510.05827 · HTML: https://mlsanity.com/paper/2510.05827/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 42 of its 44 references that are in the map.
- First posted on arXiv 7 Oct 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 30 of 42)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning](https://mlsanity.com/paper/2403.16999/) (2024)
- [6-DOF GraspNet: Variational Grasp Generation for Object Manipulation](https://mlsanity.com/paper/1905.10520/) (2019)
- [A Study of BFLOAT16 for Deep Learning Training](https://mlsanity.com/paper/1905.12322/) (2019)
- [Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes](https://mlsanity.com/paper/2103.14127/) (2021)
- [AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains](https://mlsanity.com/paper/2212.08333/) (2022)
- [PaliGemma 2: A Family of Versatile VLMs for Transfer](https://mlsanity.com/paper/2412.03555/) (2024)
- [Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach](https://mlsanity.com/paper/1804.05172/) (2018)
- [Real-Time Grasp Detection Using Convolutional Neural Networks](https://mlsanity.com/paper/1412.3128/) (2014)
- [VGR: Visual Grounded Reasoning](https://mlsanity.com/paper/2506.11991/) (2025)
- [Deep Learning Approaches to Grasp Synthesis: A Review](https://mlsanity.com/paper/2207.02556/) (2022)
- [Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network](https://mlsanity.com/paper/1909.04810/) (2019)
- [Robotic Grasp Detection using Deep Convolutional Neural Networks](https://mlsanity.com/paper/1611.08036/) (2016)
- [End-to-end Trainable Deep Neural Network for Robotic Grasp Detection and Semantic Segmentation from RGB](https://mlsanity.com/paper/2107.05287/) (2021)
- [GraspGPT: Leveraging Semantic Knowledge from a Large Language Model for Task-Oriented Grasping](https://mlsanity.com/paper/2307.13204/) (2023)
- [VL-Grasp: a 6-Dof Interactive Grasp Policy for Language-Oriented Objects in Cluttered Indoor Scenes](https://mlsanity.com/paper/2308.00640/) (2023)
- [A Joint Modeling of Vision-Language-Action for Target-oriented Grasping in Clutter](https://mlsanity.com/paper/2302.12610/) (2023)
- [Grasp-Anything: Large-scale Grasp Dataset from Foundation Models](https://mlsanity.com/paper/2309.09818/) (2023)
- [Language-driven Grasp Detection](https://mlsanity.com/paper/2406.09489/) (2024)
- [ThinkGrasp: A Vision-Language System for Strategic Part Grasping in Clutter](https://mlsanity.com/paper/2407.11298/) (2024)

## Built on by (most cited first, 2 of 2)

- [AVI-HT: Adaptive Vision-IMU Fusion for 3D Hand Tracking](https://mlsanity.com/paper/2605.21714/) (2026)
- [A Physical Agentic Loop for Language-Guided Grasping with Execution-State Monitoring](https://mlsanity.com/paper/2604.07395/) (2026)

## Abstract (arXiv)

Robotic grasping is one of the most fundamental tasks in robotic manipulation, and grasp detection/generation has long been the subject of extensive research. Recently, language-driven grasp generation has emerged as a promising direction due to its practical interaction capabilities. However, most existing approaches either lack sufficient reasoning and generalization capabilities or depend on complex modular pipelines. Moreover, current grasp foundation models tend to overemphasize dialog and object semantics, resulting in inferior performance and restriction to single-object grasping. To maintain strong reasoning ability and generalization in cluttered environments, we propose VCoT-Grasp, an end-to-end grasp foundation model that incorporates visual chain-of-thought reasoning to enhance visual understanding for grasp generation. VCoT-Grasp adopts a multi-turn processing paradigm that dynamically focuses on visual inputs while providing interpretable reasoning traces. For training, we refine and introduce a large-scale dataset, VCoT-GraspSet, comprising 167K synthetic images with over 1.36M grasps, as well as 400+ real-world images with more than 1.2K grasps, annotated with intermediate bounding boxes. Extensive experiments on both VCoT-GraspSet and real robot demonstrate that our method significantly improves grasp success rates and generalizes effectively to unseen objects, backgrounds, and distractors. More details can be found at https://zhanghr2001.github.io/VCoT-Grasp.github.io.