# Selective Visual Representations Improve Convergence and Generalization for Embodied AI

arXiv: https://arxiv.org/abs/2311.04193 · HTML: https://mlsanity.com/paper/2311.04193/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 71 of its 89 references that are in the map.
- First posted on arXiv 7 Nov 2023.

## Builds on (most cited first, 30 of 71)

- [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)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [SAPIEN: A SimulAted Part-based Interactive ENvironment](https://mlsanity.com/paper/2003.08515/) (2020)
- [Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2004.02857/) (2020)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [Reinforcement Learning with Unsupervised Auxiliary Tasks](https://mlsanity.com/paper/1611.05397/) (2016)
- [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://mlsanity.com/paper/2206.06994/) (2022)
- [Bottleneck Transformers for Visual Recognition](https://mlsanity.com/paper/2101.11605/) (2021)
- [DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames](https://mlsanity.com/paper/1911.00357/) (2019)
- [Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks](https://mlsanity.com/paper/2306.13831/) (2023)
- [Learning to Explore using Active Neural SLAM](https://mlsanity.com/paper/2004.05155/) (2020)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects](https://mlsanity.com/paper/2006.13171/) (2020)

## Built on by (most cited first, 19 of 19)

- [SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning](https://mlsanity.com/paper/2503.03480/) (2025)
- [PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators](https://mlsanity.com/paper/2406.20083/) (2024)
- [FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning](https://mlsanity.com/paper/2409.16578/) (2024)
- [SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World](https://mlsanity.com/paper/2312.02976/) (2023)
- [MetaScenes: Towards Automated Replica Creation for Real-world 3D Scans](https://mlsanity.com/paper/2505.02388/) (2025)
- [Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences](https://mlsanity.com/paper/2312.09337/) (2023)
- [The One RING: a Robotic Indoor Navigation Generalist](https://mlsanity.com/paper/2412.14401/) (2024)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [VANP: Learning Where to See for Navigation with Self-Supervised Vision-Action Pre-Training](https://mlsanity.com/paper/2403.08109/) (2024)
- [DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenes](https://mlsanity.com/paper/2410.02730/) (2024)
- [FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations](https://mlsanity.com/paper/2504.08368/) (2025)
- [IL3D: A Large-Scale Indoor Layout Dataset for LLM-Driven 3D Scene Generation](https://mlsanity.com/paper/2510.12095/) (2025)
- [Generalizable Dense Reward for Long-Horizon Robotic Tasks](https://mlsanity.com/paper/2604.00055/) (2026)
- [Narrate2Nav: Real-Time Visual Navigation with Implicit Language Reasoning in Human-Centric Environments](https://mlsanity.com/paper/2506.14233/) (2025)
- [DiSCO-3D : Discovering and segmenting Sub-Concepts from Open-vocabulary queries in NeRF](https://mlsanity.com/paper/2507.14596/) (2025)
- [3D-Belief: Embodied Belief Inference via Generative 3D World Modeling](https://mlsanity.com/paper/2605.11367/) (2026)
- [Language-Instructed Vision Embeddings for Controllable and Generalizable Perception](https://mlsanity.com/paper/2606.19584/) (2026)
- [SHED Light on Segmentation for Dense Prediction](https://mlsanity.com/paper/2601.22529/) (2026)
- [Vision-Language Grounding as Bidirectional Concept Correspondence](https://mlsanity.com/paper/2608.07886/) (2026)

## Abstract (arXiv)

Embodied AI models often employ off the shelf vision backbones like CLIP to encode their visual observations. Although such general purpose representations encode rich syntactic and semantic information about the scene, much of this information is often irrelevant to the specific task at hand. This introduces noise within the learning process and distracts the agent's focus from task-relevant visual cues. Inspired by selective attention in humans-the process through which people filter their perception based on their experiences, knowledge, and the task at hand-we introduce a parameter-efficient approach to filter visual stimuli for embodied AI. Our approach induces a task-conditioned bottleneck using a small learnable codebook module. This codebook is trained jointly to optimize task reward and acts as a task-conditioned selective filter over the visual observation. Our experiments showcase state-of-the-art performance for object goal navigation and object displacement across 5 benchmarks, ProcTHOR, ArchitecTHOR, RoboTHOR, AI2-iTHOR, and ManipulaTHOR. The filtered representations produced by the codebook are also able generalize better and converge faster when adapted to other simulation environments such as Habitat. Our qualitative analyses show that agents explore their environments more effectively and their representations retain task-relevant information like target object recognition while ignoring superfluous information about other objects. Code and pretrained models are available at our project website: https://embodied-codebook.github.io.