mlsanityData to 14 Oct 2026

Are Transformers Truly Foundational for Robotics?

arXiv 2411.16917 ↗First posted 25 Nov 2024cs.RO cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Generative Pre-Trained Transformers (GPTs) are hyped to revolutionize robotics. Here we question their utility. GPTs for autonomous robotics demand enormous and costly compute, excessive training times and (often) offboard wireless control. We contrast GPT state of the art with how tiny insect brains have achieved robust autonomy with none of these constraints. We highlight lessons that can be learned from biology to enhance the utility of GPTs in robotics.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 23 of its 58 references that are in the map. First posted on arXiv 25 Nov 2024.

Builds on

23 of 58 references.

References · 23

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  3. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  4. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,729
  5. 2022Diffusion Models in Vision: A Surveycited by 1,015
  6. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  7. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
  8. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  9. 2019Multimodal Transformer for Unaligned Multimodal Language Sequencescited by 645
  10. 2024GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Modelscited by 550
  11. 2024Hallucination is Inevitable: An Innate Limitation of Large Language Modelscited by 332
  12. 2020The Next Decade in AI: Four Steps Towards Robust Artificial Intelligencecited by 195
11 more
  1. 2022Will we run out of data? Limits of LLM scaling based on human-generated datacited by 195
  2. 2024Mobile Edge Intelligence for Large Language Models: A Contemporary Surveycited by 128
  3. 2021Position Information in Transformers: An Overviewcited by 103
  4. 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 103
  5. 2023Evaluating Cognitive Maps and Planning in Large Language Models with CogEvalcited by 77
  6. 2024No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performancecited by 75
  7. 2024Evaluating the Robustness of Analogical Reasoning in Large Language Modelscited by 31
  8. 2023Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination?cited by 26
  9. 2024A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debatescited by 23
  10. 2023Gradient-based Planning with World Modelscited by 19
  11. 2022A Rubric for Human-like Agents and NeuroAIcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Explainable Deep Convolutional Multi-Type Anomaly Detectioncited by 0
  2. 2026A New Strategy for Artificial Intelligence: Training Foundation Models Directly on Human Brain Datacited by 0