Cover Image

VLAs are Confined yet Capable of Generalizing to Novel Instructions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Li, Quanyi
Format:	Preprint
Published:	2025
Subjects:	Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Running VLAs at Real-time Speed
by: Ma, Yunchao, et al.
Published: (2025)

SITCOM: Scaling Inference-Time COMpute for VLAs
by: Saxena, Ayudh, et al.
Published: (2025)

Do World Action Models Generalize Better than VLAs? A Robustness Study
by: Zhang, Zhanguang, et al.
Published: (2026)

Shallow-π: Knowledge Distillation for Flow-based VLAs
by: Jeon, Boseong, et al.
Published: (2026)

Primitive Subspaces Mediate Few-Shot Transfer in VLAs
by: Singh, Anya, et al.
Published: (2026)

How Do VLAs Effectively Inherit from VLMs?
by: Zhang, Chuheng, et al.
Published: (2025)

How VLAs (Really) Work In Open-World Environments
by: Rasouli, Amir, et al.
Published: (2026)

FASTER: Rethinking Real-Time Flow VLAs
by: Lu, Yuxiang, et al.
Published: (2026)

Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs
by: Zhao, Jianchao, et al.
Published: (2026)

Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting
by: Hancock, Asher J., et al.
Published: (2025)

Notes-to-Self: Scratchpad Augmented VLAs for Memory Dependent Manipulation Tasks
by: Haresh, Sanjay, et al.
Published: (2026)

cVLA: Towards Efficient Camera-Space VLAs
by: Argus, Max, et al.
Published: (2025)

Realtime-VLA V2: Learning to Run VLAs Fast, Smooth, and Accurate
by: Yang, Chen, et al.
Published: (2026)

VLA-0: Building State-of-the-Art VLAs with Zero Modification
by: Goyal, Ankit, et al.
Published: (2025)

Differentiate-and-Inject: Enhancing VLAs via Functional Differentiation Induced by In-Parameter Structural Reasoning
by: Hou, Jingyi, et al.
Published: (2026)

Scaling Sim-to-Real Reinforcement Learning for Robot VLAs with Generative 3D Worlds
by: Choi, Andrew, et al.
Published: (2026)

Lost in Fog: Sensor Perturbations Expose Reasoning Fragility in Driving VLAs
by: Priyadershi, Abhinaw, et al.
Published: (2026)

Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs
by: Niu, Jiahui, et al.
Published: (2026)

Affordance Field Intervention: Enabling VLAs to Escape Memory Traps in Robotic Manipulation
by: Xu, Siyu, et al.
Published: (2025)

LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World
by: Kim, Hojune, et al.
Published: (2026)

When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs
by: Fang, Yu, et al.
Published: (2026)

VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference
by: Tang, Jiaming, et al.
Published: (2025)

The Price Is Not Right: Neuro-Symbolic Methods Outperform VLAs on Structured Long-Horizon Manipulation Tasks with Significantly Lower Energy Consumption
by: Duggan, Timothy, et al.
Published: (2026)

What Frozen VLAs Already Know About Success: A Probing Study of Value-Like Structure in Foundation Robot Policies
by: Zhang, Jiachen, et al.
Published: (2026)

Learning H-Infinity Locomotion Control
by: Long, Junfeng, et al.
Published: (2024)

Learning from Active Human Involvement through Proxy Value Propagation
by: Peng, Zhenghao, et al.
Published: (2025)

VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAs
by: Yuan, Haoran, et al.
Published: (2026)

$π$-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs
by: Wang, Siting, et al.
Published: (2026)

mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs
by: Pai, Jonas, et al.
Published: (2025)

Soft yet Effective Robots via Holistic Co-Design
by: Stölzle, Maximilian, et al.
Published: (2025)

Toward Task Capable Active Matter: Learning to Avoid Clogging in Confined Collectives via Collisions
by: Aina, Kehinde O., et al.
Published: (2025)

Grounded World Model for Semantically Generalizable Planning
by: Li, Quanyi, et al.
Published: (2026)

GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction
by: Chen, Xiao, et al.
Published: (2024)

Self-driving cars: Are we there yet?
by: Atasever, Merve, et al.
Published: (2025)

Training Adversarial yet Safe Agent to Characterize Safety Performance of Highly Automated Vehicles
by: Zhu, Minghao, et al.
Published: (2024)

Navigating Robot Swarm Through a Virtual Tube with Flow-Adaptive Distribution Control
by: Zhang, Yongwei, et al.
Published: (2025)

On the Generalization Capabilities, Design Choices and Limitations of Keypoint Imitation Learning
by: Lips, Thomas, et al.
Published: (2026)

How VLAs Fail Differently: Black-Box Action Monitoring Reveals Architecture-Specific Failure Signatures
by: Gupta, Krishnam
Published: (2026)

COMPASS: Confined-space Manipulation Planning with Active Sensing Strategy
by: Li, Qixuan, et al.
Published: (2025)

AI-Enabled Capabilities to Facilitate Next-Generation Rover Surface Operations
by: Luna, Cristina, et al.
Published: (2025)