No article text was recorded for this version.
pre-trained visual representations
Version 1 of 134 papers43 conceptsfrozen 2026-10-04
Papers in this version
- Blog: The Unsurprising Effectiveness of Pre-Trained Vision Models for Control
- Blog: The (Un)Surprising Effectiveness of Pre-Trained Vision Models for Control
- Blog: Learning Visual Servoing with Deep Features and Fitted Q-Iteration
- Blog: PaLM-E: An Embodied Multimodal Language Model
- Blog: RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization
- Blog: SurgicAI: A Hierarchical Platform for Fine-Grained Surgical Policy Learning and Benchmarking
- Blog: The Unsurprising Effectiveness of Pre-Trained Vision Models for Control
- Blog: Improving Vision-and-Language Navigation with Image-Text Pairs from the Web
- Blog: Focus-Then-Decide: Segmentation-Assisted Reinforcement Learning
- Blog: Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation
- Blog: PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations
- Blog: Unsupervised Perceptual Rewards for Imitation Learning
- Blog: DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
- Blog: Open-Set Detection, Tracking, and Following in Real-Time
- Blog: R3M: A Universal Visual Representation for Robot Manipulation
- Blog: $\pi$2vec: Policy Representation with Successor Features
- Blog: CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learning
- Blog: What do we learn from a large-scale study of pre-trained visual representations in sim and real environments?
- Blog: Generalizable Coarse-to-Fine Robot Manipulation via Language-Aligned 3D Keypoints
- Blog: Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning
- Blog: The Surprising Effectiveness of Representation Learning for Visual Imitation
- Blog: Teaching iCub to recognize objects using deep Convolutional Neural Networks
- Blog: Skill Fusion in Hybrid Robotic Framework for Visual Object Goal Navigation
- Blog: PlaceNav: Topological Navigation through Place Recognition
- Blog: Topological mapping for traversability-aware long-range navigation in off-road terrain
- Blog: A3VLM: Actionable Articulation-Aware Vision Language Model
- Blog: FewSOL: A Dataset for Few-Shot Object Learning in Robotic Environments
- Blog: Real-World Robot Learning with Masked Visual Pre-training
- Blog: FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing
- Blog: Imagine Beyond ! Distributionally Robust Autoencoding for State Space Coverage in Online Reinforcement Learning
- Blog: A Survey on Robotics with Foundation Models: toward Embodied AI
- Blog: RRL: Resnet as representation for Reinforcement Learning
- Blog: Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours
- Blog: Embodied Visual Navigation with Automatic Curriculum Learning in Real Environments
History & citation
Current · Permanent link
- This direction split from Frozen Visual Backbones for Sample Efficient Robotic Control (79% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_pre_trained_visual_representations_91aa2b77,
title = {pre-trained visual representations},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/pre-trained-visual-representations/rdr_91aa2b774fe548658d1e5b84f6ced2ec},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_pre_trained_visual_representations_91aa2b77_v1,
title = {pre-trained visual representations},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/pre-trained-visual-representations/rdr_91aa2b774fe548658d1e5b84f6ced2ec/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}