English
Related papers

Related papers: Can vision language models learn intuitive physics…

200 papers

Learning to control robots directly based on images is a primary challenge in robotics. However, many existing reinforcement learning approaches require iteratively obtaining millions of robot samples to learn a policy, which can take…

Robotics · Computer Science 2019-08-02 AJ Piergiovanni , Alan Wu , Michael S. Ryoo

Unlike reinforcement learning (RL) agents, humans remain capable multitaskers in changing environments. In spite of only experiencing the world through their own observations and interactions, people know how to balance focusing on tasks…

Artificial Intelligence · Computer Science 2024-07-02 Rishav Bhagat , Jonathan Balloch , Zhiyu Lin , Julia Kim , Mark Riedl

Understanding physical transformations is fundamental for reasoning in dynamic environments. While Vision Language Models (VLMs) show promise in embodied applications, whether they genuinely understand physical transformations remains…

Artificial Intelligence · Computer Science 2026-03-10 Dezhi Luo , Yijiang Li , Maijunxian Wang , Tianwei Zhao , Bingyang Wang , Siheng Wang , Pinyuan Feng , Pooyan Rahmanzadehgervi , Ziqiao Ma , Hokin Deng

Multi-task ``vision-language-action'' (VLA) models have recently demonstrated increasing promise as generalist foundation models for robotics, achieving non-trivial performance out of the box on new tasks in new environments. However, for…

Robotics · Computer Science 2025-08-05 Kaustubh Sridhar , Souradeep Dutta , Dinesh Jayaraman , Insup Lee

Fine-tuning large pre-trained models has become the de facto strategy for developing both task-specific and general-purpose machine learning systems, including developing models that are safe to deploy. Despite its clear importance, there…

Contact-rich manipulation demands human-like integration of perception and force feedback: vision should guide task progress, while high-frequency interaction control must stabilize contact under uncertainty. Existing learning-based…

Recent research looks to harness the general knowledge and reasoning of large language models (LLMs) into agents that accomplish user-specified goals in interactive environments. Vision-language models (VLMs) extend LLMs to multi-modal data…

Machine Learning · Computer Science 2025-05-07 Jake Grigsby , Yuke Zhu , Michael Ryoo , Juan Carlos Niebles

There have been numerous advances in reinforcement learning, but the typically unconstrained exploration of the learning process prevents the adoption of these methods in many safety critical applications. Recent work in safe reinforcement…

Machine Learning · Computer Science 2019-10-02 David Isele , Alireza Nakhaei , Kikuo Fujimura

Vision-Language-Action (VLA) models show strong generalization for robotic control, but finetuning them with reinforcement learning (RL) is constrained by the high cost and safety risks of real-world interaction. Training VLA models in…

Robotics · Computer Science 2026-03-24 Zhilong Zhang , Haoxiang Ren , Yihao Sun , Yifei Sheng , Haonan Wang , Haoxin Lin , Zhichao Wu , Pierre-Luc Bacon , Yang Yu

Reasoning about objects, relations, and physics is central to human intelligence, and a key goal of artificial intelligence. Here we introduce the interaction network, a model which can reason about how objects in complex systems interact,…

Artificial Intelligence · Computer Science 2016-12-02 Peter W. Battaglia , Razvan Pascanu , Matthew Lai , Danilo Rezende , Koray Kavukcuoglu

The field of visual representation learning has seen explosive growth in the past years, but its benefits in robotics have been surprisingly limited so far. Prior work uses generic visual representations as a basis to learn (task-specific)…

Robotics · Computer Science 2023-08-16 Jianren Wang , Sudeep Dasari , Mohan Kumar Srirama , Shubham Tulsiani , Abhinav Gupta

Autonomous inspection in hazardous environments requires AI agents that can interpret high-level goals and execute precise control. A key capability for such agents is spatial grounding, for example when a drone must center a detected…

Artificial Intelligence · Computer Science 2025-11-25 Xian Yeow Lee , Lasitha Vidyaratne , Gregory Sin , Ahmed Farahat , Chetan Gupta

A chief goal of artificial intelligence is to build machines that think like people. Yet it has been argued that deep neural network architectures fail to accomplish this. Researchers have asserted these models' limitations in the domains…

Machine Learning · Computer Science 2024-08-09 Luca M. Schulze Buschoff , Elif Akata , Matthias Bethge , Eric Schulz

Most recent successes in robot reinforcement learning involve learning a specialized single-task agent. However, robots capable of performing multiple tasks can be much more valuable in real-world applications. Multi-task reinforcement…

Robotics · Computer Science 2024-07-19 Elie Aljalbout , Nikolaos Sotirakis , Patrick van der Smagt , Maximilian Karl , Nutan Chen

Deep networks trained on demonstrations of human driving have learned to follow roads and avoid obstacles. However, driving policies trained via imitation learning cannot be controlled at test time. A vehicle trained end-to-end to imitate…

Robotics · Computer Science 2018-03-05 Felipe Codevilla , Matthias Müller , Antonio López , Vladlen Koltun , Alexey Dosovitskiy

Large language models (LLMs) have demonstrated that large-scale pretraining enables systems to adapt rapidly to new problems with little supervision in the language domain. This success, however, has not translated as effectively to the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Pablo Acuaviva , Aram Davtyan , Mariam Hassan , Sebastian Stapf , Ahmad Rahimi , Alexandre Alahi , Paolo Favaro

We empirically investigate how pre-training on data of different modalities, such as language and vision, affects fine-tuning of Transformer-based models to Mujoco offline reinforcement learning tasks. Analysis of the internal…

Machine Learning · Computer Science 2022-11-21 Shiro Takagi

One of the most basic skills a robot should possess is predicting the effect of physical interactions with objects in the environment. This enables optimal action selection to reach a certain goal state. Traditionally, dynamics are…

Robotics · Computer Science 2020-10-13 Alina Kloss , Stefan Schaal , Jeannette Bohg

Humans can infer accurate mechanical outcomes from only a few observations, a capability known as mechanics intuition. The mechanisms behind such data-efficient learning remain unclear. Here, we propose a reinforcement learning framework in…

Computational Physics · Physics 2026-01-30 Jingruo Peng , Shuze Zhu

Consider a prosthetic arm, learning to adapt to its user's control signals. We propose Interaction-Grounded Learning for this novel setting, in which a learner's goal is to interact with the environment with no grounding or explicit reward…

Machine Learning · Computer Science 2021-07-15 Tengyang Xie , John Langford , Paul Mineiro , Ida Momennejad