# NaturalVLM: Leveraging Fine-grained Natural Language for Affordance-Guided Visual Manipulation

arXiv: https://arxiv.org/abs/2403.08355 · HTML: https://mlsanity.com/paper/2403.08355/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 33 references that are in the map.
- First posted on arXiv 13 Mar 2024.

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://mlsanity.com/paper/2110.07602/) (2021)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [CLIPort: What and Where Pathways for Robotic Manipulation](https://mlsanity.com/paper/2109.12098/) (2021)
- [CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks](https://mlsanity.com/paper/2112.03227/) (2021)
- [Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation](https://mlsanity.com/paper/2209.05451/) (2022)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [VIMA: General Robot Manipulation with Multimodal Prompts](https://mlsanity.com/paper/2210.03094/) (2022)
- [BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments](https://mlsanity.com/paper/2108.03332/) (2021)
- [Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model](https://mlsanity.com/paper/2305.11176/) (2023)
- [ManipulaTHOR: A Framework for Visual Object Manipulation](https://mlsanity.com/paper/2104.11213/) (2021)
- [Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration](https://mlsanity.com/paper/2105.06411/) (2021)
- [VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation](https://mlsanity.com/paper/2206.08522/) (2022)
- [FabricFlowNet: Bimanual Cloth Manipulation with a Flow-based Policy](https://mlsanity.com/paper/2111.05623/) (2021)
- [ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts](https://mlsanity.com/paper/2205.15509/) (2022)
- [PyRep: Bringing V-REP to Deep Robot Learning](https://mlsanity.com/paper/1906.11176/) (2019)
- [INVIGORATE: Interactive Visual Grounding and Grasping in Clutter](https://mlsanity.com/paper/2108.11092/) (2021)
- [AlphaBlock: Embodied Finetuning for Vision-Language Reasoning in Robot Manipulation](https://mlsanity.com/paper/2305.18898/) (2023)

## Built on by (most cited first, 10 of 10)

- [HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model](https://mlsanity.com/paper/2503.10631/) (2025)
- [RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning](https://mlsanity.com/paper/2409.14674/) (2024)
- [Fast-in-Slow: A Dual-System Foundation Model Unifying Fast Manipulation within Slow Reasoning](https://mlsanity.com/paper/2506.01953/) (2025)
- [UniGarmentManip: A Unified Framework for Category-Level Garment Manipulation via Dense Visual Correspondence](https://mlsanity.com/paper/2405.06903/) (2024)
- [AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning](https://mlsanity.com/paper/2502.11124/) (2025)
- [RAGNet: Large-scale Reasoning-based Affordance Segmentation Benchmark towards General Grasping](https://mlsanity.com/paper/2507.23734/) (2025)
- [EqvAfford: SE(3) Equivariance for Point-Level Affordance Learning](https://mlsanity.com/paper/2408.01953/) (2024)
- [VideoAfford: Grounding 3D Affordance from Human-Object-Interaction Videos via Multimodal Large Language Model](https://mlsanity.com/paper/2602.09638/) (2026)
- [SKT: Integrating State-Aware Keypoint Trajectories with Vision-Language Models for Robotic Garment Manipulation](https://mlsanity.com/paper/2409.18082/) (2024)
- [KineVLA: Towards Kinematics-Aware Vision-Language-Action Models with Bi-Level Action Decomposition](https://mlsanity.com/paper/2603.17524/) (2026)

## Abstract (arXiv)

Enabling home-assistant robots to perceive and manipulate a diverse range of 3D objects based on human language instructions is a pivotal challenge. Prior research has predominantly focused on simplistic and task-oriented instructions, i.e., "Slide the top drawer open". However, many real-world tasks demand intricate multi-step reasoning, and without human instructions, these will become extremely difficult for robot manipulation. To address these challenges, we introduce a comprehensive benchmark, NrVLM, comprising 15 distinct manipulation tasks, containing over 4500 episodes meticulously annotated with fine-grained language instructions. We split the long-term task process into several steps, with each step having a natural language instruction. Moreover, we propose a novel learning framework that completes the manipulation task step-by-step according to the fine-grained instructions. Specifically, we first identify the instruction to execute, taking into account visual observations and the end-effector's current state. Subsequently, our approach facilitates explicit learning through action-prompts and perception-prompts to promote manipulation-aware cross-modality alignment. Leveraging both visual observations and linguistic guidance, our model outputs a sequence of actionable predictions for manipulation, including contact points and end-effector poses. We evaluate our method and baselines using the proposed benchmark NrVLM. The experimental results demonstrate the effectiveness of our approach. For additional details, please refer to https://sites.google.com/view/naturalvlm.