Vision Language Models are In-Context Value Learners
- URL: http://arxiv.org/abs/2411.04549v1
- Date: Thu, 07 Nov 2024 09:17:50 GMT
- Title: Vision Language Models are In-Context Value Learners
- Authors: Yecheng Jason Ma, Joey Hejna, Ayzaan Wahid, Chuyuan Fu, Dhruv Shah, Jacky Liang, Zhuo Xu, Sean Kirmani, Peng Xu, Danny Driess, Ted Xiao, Jonathan Tompson, Osbert Bastani, Dinesh Jayaraman, Wenhao Yu, Tingnan Zhang, Dorsa Sadigh, Fei Xia,
- Abstract summary: We present Generative Value Learning (GVL), a universal value function estimator that leverages the world knowledge embedded in vision-language models (VLMs) to predict task progress.
Without any robot or task specific training, GVL can in-context zero-shot and few-shot predict effective values for more than 300 distinct real-world tasks.
- Score: 89.29486557646624
- License:
- Abstract: Predicting temporal progress from visual trajectories is important for intelligent robots that can learn, adapt, and improve. However, learning such progress estimator, or temporal value function, across different tasks and domains requires both a large amount of diverse data and methods which can scale and generalize. To address these challenges, we present Generative Value Learning (\GVL), a universal value function estimator that leverages the world knowledge embedded in vision-language models (VLMs) to predict task progress. Naively asking a VLM to predict values for a video sequence performs poorly due to the strong temporal correlation between successive frames. Instead, GVL poses value estimation as a temporal ordering problem over shuffled video frames; this seemingly more challenging task encourages VLMs to more fully exploit their underlying semantic and temporal grounding capabilities to differentiate frames based on their perceived task progress, consequently producing significantly better value predictions. Without any robot or task specific training, GVL can in-context zero-shot and few-shot predict effective values for more than 300 distinct real-world tasks across diverse robot platforms, including challenging bimanual manipulation tasks. Furthermore, we demonstrate that GVL permits flexible multi-modal in-context learning via examples from heterogeneous tasks and embodiments, such as human videos. The generality of GVL enables various downstream applications pertinent to visuomotor policy learning, including dataset filtering, success detection, and advantage-weighted regression -- all without any model training or finetuning.
Related papers
- DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control [7.626715427413578]
Vision-language-action (VLA) models have shown promise for generalizable robot skills.
Current VLA models often focus on scaling the vision-language model (VLM) component, while the action space representation remains a critical bottleneck.
This paper introduces DexVLA, a novel framework designed to enhance the efficiency and generalization capabilities ofVLAs for complex, long-horizon tasks.
arXiv Detail & Related papers (2025-02-09T11:25:56Z) - HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation [54.03004125910057]
We show that hierarchical vision-language-action models can be more effective in utilizing off-domain data than standard monolithic VLA models.
We show that, with the hierarchical design, the high-level VLM can transfer across significant domain gaps between the off-domain finetuning data and real-robot testing scenarios.
arXiv Detail & Related papers (2025-02-08T07:50:22Z) - VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks [100.3234156027118]
We present VLABench, an open-source benchmark for evaluating universal LCM task learning.
VLABench provides 100 carefully designed categories of tasks, with strong randomization in each category of task and a total of 2000+ objects.
The benchmark assesses multiple competencies including understanding of mesh&texture, spatial relationship, semantic instruction, physical laws, knowledge transfer and reasoning.
arXiv Detail & Related papers (2024-12-24T06:03:42Z) - STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning [8.860366821983211]
STRAP is a technique for leveraging pre-trained vision foundation models and dynamic time warping to retrieve sub-sequences of trajectories from large training corpora in a robust fashion.
This work proposes STRAP, a technique for leveraging pre-trained vision foundation models and dynamic time warping to retrieve sub-sequences of trajectories from large training corpora in a robust fashion.
arXiv Detail & Related papers (2024-12-19T18:54:06Z) - TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies [95.30717188630432]
We introduce visual trace prompting to facilitate VLA models' spatial-temporal awareness for action prediction.
We develop a new TraceVLA model by finetuning OpenVLA on our own collected dataset of 150K robot manipulation trajectories.
We present a compact VLA model based on 4B Phi-3-Vision, pretrained on the Open-X-Embodiment and finetuned on our dataset.
arXiv Detail & Related papers (2024-12-13T18:40:51Z) - TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation [32.406783380729024]
Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor control and instruction comprehension through end-to-end learning processes.
Current VLA models face significant challenges: they are slow during inference and require extensive pre-training on large amounts of robotic data.
We introduce a new family of compact vision-language-action models, called TinyVLA, which offers two key advantages over existing VLA models.
arXiv Detail & Related papers (2024-09-19T07:10:18Z) - Expanding Frozen Vision-Language Models without Retraining: Towards
Improved Robot Perception [0.0]
Vision-language models (VLMs) have shown powerful capabilities in visual question answering and reasoning tasks.
In this paper, we demonstrate a method of aligning the embedding spaces of different modalities to the vision embedding space.
We show that using multiple modalities as input improves the VLM's scene understanding and enhances its overall performance in various tasks.
arXiv Detail & Related papers (2023-08-31T06:53:55Z) - ALP: Action-Aware Embodied Learning for Perception [60.64801970249279]
We introduce Action-Aware Embodied Learning for Perception (ALP)
ALP incorporates action information into representation learning through a combination of optimizing a reinforcement learning policy and an inverse dynamics prediction objective.
We show that ALP outperforms existing baselines in several downstream perception tasks.
arXiv Detail & Related papers (2023-06-16T21:51:04Z) - A survey on knowledge-enhanced multimodal learning [1.8591405259852054]
Multimodal learning has been a field of increasing interest, aiming to combine various modalities in a single joint representation.
Especially in the area of visiolinguistic (VL) learning multiple models and techniques have been developed, targeting a variety of tasks that involve images and text.
VL models have reached unprecedented performances by extending the idea of Transformers, so that both modalities can learn from each other.
arXiv Detail & Related papers (2022-11-19T14:00:50Z) - SimVLM: Simple Visual Language Model Pretraining with Weak Supervision [48.98275876458666]
We present a minimalist pretraining framework, named Simple Visual Language Model (SimVLM)
SimVLM reduces the training complexity by exploiting large-scale weak supervision.
It achieves new state-of-the-art results on a wide range of discriminative and generative vision-language benchmarks.
arXiv Detail & Related papers (2021-08-24T18:14:00Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.