# Traj-VLN: Learning Pixel-Space Interaction via Autoregressive Trajectory Generation

arXiv: https://arxiv.org/abs/2607.10744 · HTML: https://mlsanity.com/paper/2607.10744/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 25 of its 27 references that are in the map.
- First posted on arXiv 12 Jul 2026.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2004.02857/) (2020)
- [Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding](https://mlsanity.com/paper/2010.07954/) (2020)
- [NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation](https://mlsanity.com/paper/2402.15852/) (2024)
- [NaVILA: Legged Robot Vision-Language-Action Model for Navigation](https://mlsanity.com/paper/2412.04453/) (2024)
- [Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks](https://mlsanity.com/paper/2412.06224/) (2024)
- [Towards Learning a Generalist Model for Embodied Navigation](https://mlsanity.com/paper/2312.02010/) (2023)
- [Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigation](https://mlsanity.com/paper/2203.02764/) (2022)
- [Waypoint Models for Instruction-guided Navigation in Continuous Environments](https://mlsanity.com/paper/2110.02207/) (2021)
- [StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling](https://mlsanity.com/paper/2507.05240/) (2025)
- [Scaling Data Generation in Vision-and-Language Navigation](https://mlsanity.com/paper/2307.15644/) (2023)
- [JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation](https://mlsanity.com/paper/2509.22548/) (2025)
- [Affordances-Oriented Planning using Foundation Models for Continuous Vision-Language Navigation](https://mlsanity.com/paper/2407.05890/) (2024)
- [Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigation](https://mlsanity.com/paper/2512.08186/) (2025)
- [Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting](https://mlsanity.com/paper/2509.22195/) (2025)
- [NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2506.23468/) (2025)
- [Sim-to-Real Transfer via 3D Feature Fields for Vision-and-Language Navigation](https://mlsanity.com/paper/2406.09798/) (2024)
- [SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving](https://mlsanity.com/paper/2512.10719/) (2025)
- [SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models](https://mlsanity.com/paper/2509.17664/) (2025)
- [Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation](https://mlsanity.com/paper/2505.11886/) (2025)
- [VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory](https://mlsanity.com/paper/2601.08665/) (2026)
- [Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation](https://mlsanity.com/paper/2606.01621/) (2026)

## Abstract (arXiv)

Benefiting from the powerful priors embedded in large-scale pre-training data and the emerging commonsense reasoning ability, large language models (LLMs) have shown unprecedented generalization capabilities in many research fields. Recently, projecting visual embeddings into the language space via vision-language models (VLMs) to achieve sim-toreal and cross-scene generalization has become a prevailing paradigm in the field of Vision-and-Language Navigation in Continuous Environments (VLN-CE). VLN requires an embodied agent to navigate through unseen environments following natural linguistic instructions. We emphasize that a VLN task can be decomposed into a sequence of sub-tasks, each corresponding to a process of 3D spatial interaction with the environments described by instructions such as "walk to the end of the sofa and turn left." However, such spatial interactions involving moving into the image along the direction of depth sensing are puzzling for VLMs as they were predominantly trained on conversations with RGB images. Rather than incorporating depth or 3D geometric information-which VLMs rarely encounter during pretrainingwe propose an alternative approach: fine-tuning VLMs to learn navigation interactions directly in 2D pixel space through autoregressive trajectory generation. Given a linguistic instruction and historical observations, our model sequentially predicts a series of pixel coordinates, drawing a trajectory from the bottom center of the current observation. While prior work has proved that pixel-goal supervision outperforms learning of discrete actions, our experiments further verify that the supervision of pixel-space trajectory significantly enhances VLN performance. Moreover, we demonstrate that our flagship model achieves state-of-the-art level performance with relatively limited computational resources and training data.