# Exploring the Potential of Encoder-free Architectures in 3D LMMs

arXiv: https://arxiv.org/abs/2502.09620 · HTML: https://mlsanity.com/paper/2502.09620/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 44 of its 58 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 44)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [Show-o: One Single Transformer to Unify Multimodal Understanding and Generation](https://mlsanity.com/paper/2408.12528/) (2024)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models](https://mlsanity.com/paper/2407.07895/) (2024)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2203.06604/) (2022)
- [InternLM2 Technical Report](https://mlsanity.com/paper/2403.17297/) (2024)
- [PointLLM: Empowering Large Language Models to Understand Point Clouds](https://mlsanity.com/paper/2308.16911/) (2023)
- [Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training](https://mlsanity.com/paper/2205.14401/) (2022)
- [Uni3D: Exploring Unified 3D Representation at Scale](https://mlsanity.com/paper/2310.06773/) (2023)
- [Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following](https://mlsanity.com/paper/2309.00615/) (2023)
- [Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning](https://mlsanity.com/paper/2403.11401/) (2024)
- [Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining](https://mlsanity.com/paper/2302.02318/) (2023)
- [Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders](https://mlsanity.com/paper/2212.06785/) (2022)

## Built on by (most cited first, 16 of 16)

- [MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning](https://mlsanity.com/paper/2506.05331/) (2025)
- [Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detection](https://mlsanity.com/paper/2507.03903/) (2025)
- [AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations](https://mlsanity.com/paper/2504.07836/) (2025)
- [PiSA: A Self-Augmented Data Engine and Training Strategy for 3D Understanding with Large Models](https://mlsanity.com/paper/2503.10529/) (2025)
- [Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs](https://mlsanity.com/paper/2506.05318/) (2025)
- [StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion](https://mlsanity.com/paper/2503.21775/) (2025)
- [Fence Theorem: Towards Dual-Objective Semantic-Structure Isolation in Preprocessing Phase for 3D Anomaly Detection](https://mlsanity.com/paper/2503.01100/) (2025)
- [A Review of 3D Object Detection with Vision-Language Models](https://mlsanity.com/paper/2504.18738/) (2025)
- [Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detection](https://mlsanity.com/paper/2505.05901/) (2025)
- [AutoMat: Enabling Automated Crystal Structure Reconstruction from Microscopy via Agentic Tool Use](https://mlsanity.com/paper/2505.12650/) (2025)
- [Point Cloud as a Foreign Language for Multi-modal Large Language Model](https://mlsanity.com/paper/2603.09173/) (2026)
- [REVISION:Reflective Intent Mining and Online Reasoning Auxiliary for E-commerce Visual Search System Optimization](https://mlsanity.com/paper/2510.22739/) (2025)
- [Efficient Encoder-Free Fourier-based 3D Large Multimodal Model](https://mlsanity.com/paper/2602.23153/) (2026)
- [Learning Discriminative Signed Distance Functions from Multi-scale Level-of-detail Features for 3D Anomaly Detection](https://mlsanity.com/paper/2605.03437/) (2026)
- [VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction](https://mlsanity.com/paper/2605.15186/) (2026)
- [How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining](https://mlsanity.com/paper/2609.35457/) (2026)

## Abstract (arXiv)

Encoder-free architectures have been preliminarily explored in the 2D Large Multimodal Models (LMMs), yet it remains an open question whether they can be effectively applied to 3D understanding scenarios. In this paper, we present the first comprehensive investigation into the potential of encoder-free architectures to alleviate the challenges of encoder-based 3D LMMs. These long-standing challenges include the failure to adapt to varying point cloud resolutions during inference and the point features from the encoder not meeting the semantic needs of Large Language Models (LLMs). We identify key aspects for 3D LMMs to remove the pre-trained encoder and enable the LLM to assume the role of the 3D encoder: 1) We propose the LLM-embedded Semantic Encoding strategy in the pre-training stage, exploring the effects of various point cloud self-supervised losses. And we present the Hybrid Semantic Loss to extract high-level semantics. 2) We introduce the Hierarchical Geometry Aggregation strategy in the instruction tuning stage. This incorporates inductive bias into the LLM layers to focus on the local details of the point clouds. To the end, we present the first Encoder-free 3D LMM, ENEL. Our 7B model rivals the state-of-the-art model, PointLLM-PiSA-13B, achieving 57.91%, 61.0%, and 55.20% on the classification, captioning, and VQA tasks, respectively. Our results show that the encoder-free architecture is highly promising for replacing encoder-based architectures in the field of 3D understanding. The code is released at https://github.com/Ivan-Tang-3D/ENEL