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…

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…

The paper proposes CTRL-STEER, a closed-loop framework that adaptively adjusts intervention strength to stabilize concept regulation and improve task success in Vision-Language-Action models without r…

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…

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-…

This paper introduces a proactive multi-modal assistant system and a large-scale dataset for procedural assistance.

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 unified framework to evaluate how different types of memory transfer benefit multi-trajectory inference for tool-use LLM agents, finding that the optimal memory method depends cri…

The paper introduces 3DCodeBench, a systematic benchmark and platform for evaluating Vision-Language Model (VLM) agents' ability to generate procedural 3D models from text and images using code.

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…

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.

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…

Reasmory introduces a structured programming framework that uses explicit 3D memory and a Domain-Specific Language (DSL) to reliably enhance Vision-Language Models' spatial reasoning capabilities, ach…

The paper introduces Staged Executable Inverse Graphics (SEIG), an agentic framework that uses general-purpose Vision-Language Models (VLMs) to reconstruct editable 3D scenes directly into executable…

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…

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…

This paper presents Mana, a sim-to-real framework for dexterous articulated tool manipulation.

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 introduces TRAP, an adversarial attack that demonstrates how physical patches can hijack the Chain-of-Thought (CoT) reasoning process in Vision-Language-Action (VLA) models, forcing them to…

The paper proposes MERIT, a dual-level, multi-horizon memory retrieval framework that significantly improves the performance of interactive text-to-SQL agents by providing both global and local memory…