The paper proposes Continuous Reasoning for Vision-Language-Action (VLA) models, arguing that effective reasoning must be a shared, verifiable internal latent space rather than discrete text tokens, l…

The paper introduces FabriVLA, a lightweight Vision-Language-Action model that achieves strong performance on the Meta-World MT50 benchmark using a compact 1B scale VLM backbone and a flow-matching ac…

The paper introduces SceneActBench, a benchmark for evaluating vision-language model agents' ability to perform actions on multi-object 3D scenes.

This paper presents the first systematic study of membership inference attacks (MIAs) against Vision-Language-Action (VLA) models, demonstrating that these models are highly vulnerable to privacy brea…

Qwen-VLA introduces a unified embodied foundation model that extends vision-language understanding to continuous action generation, enabling robust, multi-task generalization across diverse robotic ta…

This paper introduces Vision-Language-Motion Maps (VLMM), an open-vocabulary, natural-language-queryable 3D map with fused motion attributes and per-element uncertainty, which outperforms semantic-onl…

The paper addresses the difficulty of using general vision-language models (VLMs) for fine-grained driver behavior recognition by creating a new, richly described dataset and demonstrating that fine-t…

The paper introduces a structured multi-level visual perturbation framework to systematically analyze how dependent VLA-based driving behavior is on visual information, revealing uneven visual groundi…

This paper proposes a two-stage training framework to pretrain action modules with motion priors before Vision-Language-Action (VLA) alignment, improving VLA performance and reducing optimization chal…

The paper proposes VLM3, a simple, scalable method that demonstrates standard Vision Language Models (VLMs) can natively learn 3D understanding by focusing on architectural simplicity and specific dat…

VLA-Trace is a diagnostic framework that analyzes Vision-Language-Action (VLA) models by tracing their internal representations and external behaviors, revealing that while these models are good at vi…

Proposed G$^3$VLA, a camera-aware geometric module for pretrained vision-language-action models, injecting calibrated structure into visual tokens using intrinsic-conditioned ray embeddings, projectiv…

The paper presents SenseNova-Vision, a unified multimodal model for computer vision tasks using natural language instructions and optional visual prompts, trained primarily on a new corpus and requiri…

The paper evaluates the performance of Vision-Language Models (VLMs) in a collaborative dialogue task requiring spatial reconstruction, finding that while detailed text representations improve results…

VISUALTHINK-VLA introduces a visual intermediate-reasoning framework that guides action prediction using compact visual evidence, achieving high accuracy and significantly low latency for real-time Vi…

This paper introduces LingBot-VA 2.0, a video-action foundation model designed for embodiment, with semantic visual-action tokenization, causal pretraining, sparse MoE backbone, and enhanced asynchron…

The paper argues that large language models (LLMs) are a special case of world models and proposes a continuous spectrum between token prediction and latent-space architectures.

The paper introduces pause-and-think-T, a reasoning-centric dataset and benchmark that enables compact Vision-Language Models to perform visually grounded, context-aware action suggestion, matching la…