Related papers: The Compression Gap: Why Discrete Tokenization Lim…
Vision-Language-Action (VLA) models leveraging the native autoregressive paradigm of Vision-Language Models (VLMs) have demonstrated superior instruction-following and training efficiency. Central to this paradigm is action tokenization,…
Recent advancements in vision-language models (VLMs) have improved performance by increasing the number of visual tokens, which are often significantly longer than text tokens. However, we observe that most real-world scenarios do not…
Vision-Language-Action (VLA) models have demonstrated strong multi-modal reasoning capabilities, enabling direct action generation from visual perception and language instructions in an end-to-end manner. However, their substantial…
Autonomous driving has long relied on modular "Perception-Decision-Action" pipelines, where hand-crafted interfaces and rule-based components often break down in complex or long-tailed scenarios. Their cascaded design further propagates…
Vision-Language-Action (VLA) models have shown remarkable promise in robotics manipulation, yet their high computational cost hinders real-time deployment. Existing token pruning methods suffer from a fundamental trade-off: aggressive…
Action chunking has recently emerged as a standard practice in flow-based Vision-Language-Action (VLA) models. However, the effect and choice of the execution horizon - the number of actions to be executed from each predicted chunk -…
Large Vision-Language Models (LVLMs) use their vision encoders to translate images into representations for downstream reasoning, but the encoders often underperform in domain-specific visual tasks such as medical image diagnosis or…
Vector Quantization (VQ) is a method for discretizing latent representations and has become a major part of the deep learning toolkit. It has been theoretically and empirically shown that discretization of representations leads to improved…
Robot foundation models, particularly Vision-Language-Action (VLA) models, have garnered significant attention for their ability to enhance robot policy learning, greatly improving robot's generalization and robustness. OpenAI's recent…
Vision-language action (VLA) policies often report strong manipulation benchmark performance with relatively few demonstrations, but it remains unclear whether this reflects robust language-to-object grounding or reliance on…
In this paper, we propose GTA-VLA(Guide, Think, Act), an interactive Vision-Language-Action (VLA) framework that enables spatially steerable embodied reasoning by allowing users to guide robot policies with explicit visual cues. Existing…
In recent years, Vision-Language-Action (VLA) models have become a vital research direction in robotics due to their impressive multimodal understanding and generalization capabilities. Despite the progress, their practical deployment is…
Scaling Vision-Language-Action (VLA) models requires massive datasets that are both semantically coherent and physically feasible. However, existing scene generation methods often lack context-awareness, making it difficult to synthesize…
Vision Transformers (ViTs) can learn strong image-level representations while their patch representations become less effective for dense prediction during prolonged training. We revisit this dense degradation phenomenon and argue that it…
Multimodal large language models (MLLMs) have achieved rapid progress, yet their scaling behavior remains less clearly characterized and often less predictable than that of text-only LLMs. Increasing model size and task diversity often…
Vision-Language-Action systems follow instructions to execute multi-step tasks in multimodal environments. Recent VLA approaches typically rely on post-hoc correction mechanisms or operate under fixed task decompositions and alignment…
Learning universal policies from cross-embodied data remains a fundamental challenge in robotics. Although Vision-Language-Action (VLA) models are pre-trained on large and diverse datasets, they typically rely on embodiment-specific…
Multimodal latent reasoning has emerged as a promising paradigm that replaces explicit Chain-of-Thought (CoT) decoding with implicit feature propagation, simultaneously enhancing representation informativeness and reducing inference…
Vision-Language-Action (VLA) models aim to predict robotic actions based on visual observations and language instructions. Existing approaches require fine-tuning pre-trained visionlanguage models (VLMs) as visual and language features are…
Despite the excellent performance of vision-language pre-trained models (VLPs) on conventional VQA task, they still suffer from two problems: First, VLPs tend to rely on language biases in datasets and fail to generalize to…