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.

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…

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 introduces a diagnostic framework to determine if World-Action Models (WAMs) provide genuinely actionable behavioral improvements beyond simply achieving task success, finding that WAMs ofte…

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…

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…

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…

The paper proposes a robust sim-to-sim-to-real DRL approach to enable double-Ackermann robots to achieve full pose control despite significant actuation uncertainties and discrepancies between simulat…

DeMaVLA is a generalizable Vision-Language-Action foundation model designed for deformable object manipulation, achieving strong real-world performance on folding tasks by leveraging large-scale real-…

GSAM introduces a generalizable and safe robotic framework for articulated object manipulation, significantly improving success rates and reducing variability across diverse tasks by integrating commo…

The paper proposes VERA, a decoupled policy that uses an action-free video world model combined with an embodiment-specific Inverse Dynamics Model (IDM) to achieve generalizable, zero-shot robot contr…

The paper proposes Visual Gradient Steering (VGS), a method that decomposes the distillation loss into language and visual components and steers the optimization to prioritize visual grounding, signif…

The paper introduces MiraBench, a new benchmark that evaluates the action-conditioned reliability of robotic world models, finding that visual fidelity is insufficient and that optimism bias is a perv…

VLA-Pro is a plug-and-play framework that enhances cross-task generalization in Vision-Language-Action models by storing and dynamically retrieving task-specific procedural memories, achieving signifi…

The paper proposes a memory-augmented, traversability-aware framework for outdoor VLN that maintains stable, goal-consistent guidance even when semantic cues are interrupted or unavailable.

The paper introduces SpatialAct, a challenging benchmark that reveals a significant 'reasoning-to-action gap,' showing that current VLMs struggle to maintain coherent spatial understanding and perform…

The paper formally addresses the challenging question of cross-domain transferability of latent predictive models by proposing a structured framework that quantifies the relationship between source an…

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…