相关论文: Sigma: The Key for Vision-Language-Action Models t…

Vision-Language-Action (VLA) policies translate language and visual inputs into robot actions, where their hidden representations directly shape closed-loop behavior. However, mechanistic interpretability tools from language and…

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…

Building generalist embodied agents requires integrating perception, language understanding, and action, which are core capabilities addressed by Vision-Language-Action (VLA) approaches based on multimodal foundation models, including…

While Multimodal Large Language Models (MLLMs) excel at general vision-language tasks, visuospatial cognition - reasoning about spatial layouts, relations, and dynamics - remains a significant challenge. Existing models often lack the…

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for open-world robot manipulation, but their practical deployment is often constrained by cost: billion-scale VLM backbones and iterative diffusion/flow-based action…

Chinese-Vicuna is an open-source, resource-efficient language model designed to bridge the gap in Chinese instruction-following capabilities by fine-tuning Meta's LLaMA architecture using Low-Rank Adaptation (LoRA). Targeting low-resource…

While vision-language models have advanced significantly, their application in language-conditioned robotic manipulation is still underexplored, especially for contact-rich tasks that extend beyond visually dominant pick-and-place…

Word alignment which aims to extract lexicon translation equivalents between source and target sentences, serves as a fundamental tool for natural language processing. Recent studies in this area have yielded substantial improvements by…

Open-vocabulary semantic segmentation models associate vision and text to label pixels from an undefined set of classes using textual queries, providing versatile performance on novel datasets. However, large shifts between training and…

Reasoning Vision Language Action (VLA) models improve robotic instruction-following by generating step-by-step textual plans before low-level actions, an approach inspired by Chain-of-Thought (CoT) reasoning in language models. Yet even…

Vision-Language-Action (VLA) models drive next-generation autonomous systems, but training them requires scalable, high-quality annotations from complex environments. Current cloud pipelines rely on generic vision-language models (VLMs)…

Here we build a hierarchical modular network called Language guided machine action (LGMA), whose modules process information stream mimicking human cortical network that allows to achieve multiple general tasks such as language guided…

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 development of Vision-Language-Action (VLA) models has been significantly accelerated by pre-trained Vision-Language Models (VLMs). However, most existing end-to-end VLAs treat the VLM primarily as a multimodal encoder, directly mapping…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities by integrating visual and textual inputs, yet modality alignment remains one of the most challenging aspects. Current MLLMs typically rely on simple adapter…

Recent large pretrained models such as LLMs (e.g., GPT series) and VLAs (e.g., OpenVLA) have achieved notable progress on multimodal tasks, yet they are built upon a multi-input single-output (MISO) paradigm. We show that this paradigm…

A person's demonstration often serves as a key reference for others learning the same task. However, RGB video, the dominant medium for representing these demonstrations, often fails to capture fine-grained contextual cues such as intent,…

The recent advancements of Large Language Models (LLMs) have spurred considerable research interest in extending their linguistic capabilities beyond text to other modalities, which leads to emergence of speech-based LLMs (SpeechLMs) with…

Recent advancements in Large Language Models have successfully transitioned towards System 2 reasoning, yet applying these paradigms to video understanding remains challenging. While prevailing research attributes failures in Video-LLMs to…

Recent advances in vision-language-action (VLA) models have shown promise in integrating image generation with action prediction to improve generalization and reasoning in robot manipulation. However, existing methods are limited to…