Related papers: Latent Bridge: Feature Delta Prediction for Effici…

Current Vision-Language-Action (VLA) models predominantly rely on end-to-end fine-tuning. While effective, this paradigm compromises the inherent generalization capabilities of Vision-Language Models (VLMs) and incurs catastrophic…

Vision--Language--Action (VLA) models that encode actions using a discrete tokenization scheme are increasingly adopted for robotic manipulation, but existing decoding paradigms remain fundamentally limited. Whether actions are decoded…

Vision-Language-Action (VLA) models achieve over 95% success on standard benchmarks. However, through systematic experiments, we find that current state-of-the-art VLA models largely ignore language instructions. Prior work lacks: (1)…

This paper presents UnderwaterVLA, a novel framework for autonomous underwater navigation that integrates multimodal foundation models with embodied intelligence systems. Underwater operations remain difficult due to hydrodynamic…

Recent studies on Vision-Language-Action (VLA) models have shifted from the end-to-end action-generation paradigm toward a pipeline involving task planning followed by action generation, demonstrating improved performance on various…

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for embodied intelligence, enabling robots to perform tasks based on natural language instructions and current visual input. However, existing VLA models struggle with…

Vision-Language-Action (VLA) models, trained via flow-matching or diffusion objectives, excel at learning complex behaviors from large-scale, multi-modal datasets (e.g., human teleoperation, scripted policies). However, since VLAs…

Cross-lingual adaptation has proven effective in spoken language understanding (SLU) systems with limited resources. Existing methods are frequently unsatisfactory for intent detection and slot filling, particularly for distant languages…

Most existing Vision-Language-Action (VLA) models rely primarily on RGB information, while ignoring geometric cues crucial for spatial reasoning and manipulation. In this work, we introduce GLaD, a geometry-aware VLA framework that…

Vision-Language-Action (VLA) models have shown great potential for embodied AI by integrating visual perception, language understanding, and action execution. In real-time deployment, these models must process continuous visual streams,…

Vision-Language-Action (VLA) models have emerged as a promising paradigm for building embodied agents that ground perception and language into action. However, most existing approaches rely on direct action prediction, lacking the ability…

Vision-Language-Action (VLA) models have significantly advanced the capabilities of robotic agents in executing diverse tasks; however, they still face challenges in contact-rich manipulation scenarios that require precise physical…

Capturing long-range dependencies (LRD) efficiently is a core challenge in visual recognition, and state-space models (SSMs) have recently emerged as a promising alternative to self-attention for addressing it. However, adapting SSMs into…

Improving embodied reasoning in multimodal-large-language models (MLLMs) is essential for building vision-language-action models (VLAs) on top of them to readily translate multimodal understanding into low-level actions. Accordingly, recent…

Vision-Language-Action (VLA) models show promise for robotic control, yet performance in complex household environments remains sub-optimal. Mobile manipulation requires reasoning about global scene layout, fine-grained geometry, and…

Most existing vision-language-action (VLA) models for robotic manipulation lack progress awareness, typically relying on hand-crafted heuristics for task termination. This limitation is particularly severe in long-horizon tasks involving…

Efficient long-short temporal modeling is key for enhancing the performance of action recognition task. In this paper, we propose a new two-stream action recognition network, termed as MENet, consisting of a Motion Enhancement (ME) module…

Vision-language-action (VLA) reasoning tasks require agents to interpret multimodal instructions, perform long-horizon planning, and act adaptively in dynamic environments. Existing approaches typically train VLA models in an end-to-end…

Vision Language Models (VLMs) have recently been leveraged to generate robotic actions, forming Vision-Language-Action (VLA) models. However, directly adapting a pretrained VLM for robotic control remains challenging, particularly when…

The capability of performing long-horizon, language-guided robotic manipulation tasks critically relies on leveraging historical information and generating coherent action sequences. However, such capabilities are often overlooked by…