Related papers: Seeing Realism from Simulation: Efficient Video Tr…

Vision-language-action (VLA) models represent a promising direction for developing general-purpose robotic systems, demonstrating the ability to combine visual understanding, language comprehension, and action generation. However,…

Vision-Language-Action (VLA) models have emerged as a unified paradigm for robotic perception and control, enabling emergent generalization and long-horizon task execution. However, their deployment in dynamic, real-world environments is…

A more robust and holistic language-video representation is the key to pushing video understanding forward. Despite the improvement in training strategies, the quality of the language-video dataset is less attention to. The current plain…

In this study, we present an efficient and effective approach for achieving temporally consistent synthetic-to-real video translation in videos of varying lengths. Our method leverages off-the-shelf conditional image diffusion models,…

Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in robotic manipulation,enabling robots to execute natural language commands through end-to-end learning from visual observations.However, deploying large-scale…

Vision-Language-Action (VLA) models remain brittle in long-horizon, contact-rich manipulation because success-only imitation provides little supervision for execution drift, while failed rollouts are often discarded. We introduce RePO-VLA,…

We introduce RynnVLA-002, a unified Vision-Language-Action (VLA) and world model. The world model leverages action and visual inputs to predict future image states, learning the underlying physics of the environment to refine action…

Simulation offers a promising approach for cheaply scaling training data for generalist policies. To scalably generate data from diverse and realistic tasks, existing algorithms either rely on large language models (LLMs) that may…

Long-form video understanding remains challenging for Vision-Language Models (VLMs) due to the inherent tension between computational constraints and the need to capture information distributed across thousands of frames. Existing…

Post-training Vision-Language-Action (VLA) models via reinforcement learning (RL) in learned world models has emerged as an effective strategy to adapt to new tasks without costly real-world interactions. However, while using imagined…

Current Vision-Language-Action (VLA) models typically treat the deepest representation of a vision-language backbone as universally optimal for action prediction. However, robotic manipulation is composed of many frequent closed-loop…

Recent progress in video-text retrieval has been driven largely by advancements in model architectures and training strategies. However, the representation learning capabilities of videotext retrieval models remain constrained by lowquality…

Robotic manipulation requires sophisticated commonsense reasoning, a capability naturally possessed by large-scale Vision-Language Models (VLMs). While VLMs show promise as zero-shot planners, their lack of grounded physical understanding…

We propose the Vision-and-Augmented-Language Transformer (VAuLT). VAuLT is an extension of the popular Vision-and-Language Transformer (ViLT), and improves performance on vision-and-language (VL) tasks that involve more complex text inputs…

Executing language-conditioned tasks in dynamic visual environments remains a central challenge in embodied AI. Existing Vision-Language-Action (VLA) models predominantly adopt reactive state-to-action mappings, often leading to…

Foundation models applied in robotics, particularly \textbf{Vision--Language--Action (VLA)} models, hold great promise for achieving general-purpose manipulation. Yet, systematic real-world evaluations and cross-model comparisons remain…

This paper presents RynnVLA-001, a vision-language-action(VLA) model built upon large-scale video generative pretraining from human demonstrations. We propose a novel two-stage pretraining methodology. The first stage, Ego-Centric Video…

Teaching robots desired skills in real-world environments remains challenging, especially for non-experts. A key bottleneck is that collecting robotic data often requires expertise or specialized hardware, limiting accessibility and…

This paper presents a novel approach for pretraining robotic manipulation Vision-Language-Action (VLA) models using a large corpus of unscripted real-life video recordings of human hand activities. Treating human hand as dexterous robot…

Vision-language-action models (VLAs) have shown generalization capabilities in robotic manipulation tasks by inheriting from vision-language models (VLMs) and learning action generation. Most VLA models focus on interpreting vision and…