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…

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…

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…

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…

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

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…

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…

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…

VLESA is a novel framework that monitors human activities from egocentric video to predict and intervene in dangerous actions by incorporating goal-conditioned safety checks based on inferred intent.

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…

This paper introduces Camera-Centric VLA, a new model for Vision-Language-Action policies that predicts camera-centric actions and hand-eye matrix, allowing the policy to figure out camera geometry on…

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…

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…

BORA is an offline-to-online RL framework that enhances dexterous VLA models for real-world robotics by using an action-conditioned critic and a lightweight residual adaptation mechanism to correct ex…

This paper introduces FurnitureVLA, a systematic study of real-scale bimanual furniture assembly using Vision-Language-Action models, improving simulation success from 48% to 80% and reducing errors.

TempoVLA is a novel Vision-Language-Action model that enables controllable execution speed for robot manipulation by explicitly conditioning the policy on the desired speed.

The paper proposes EAGLE, a novel evidence-aligned multi-agent framework, demonstrating that requiring shared visual evidence among agents is crucial for achieving reliable and trustworthy consensus i…