VLA

Papers with VLA

Bring the Apple, Not the Sofa: Impact of Irrelevant Context in Embodied AI Commands on VLA Models (2026.eacl-srw)

Copied to clipboard

Andrey Moskalenko, Daria Pugacheva, Denis Shepelev, Andrey Kuznetsov, Vlad Shakhuro, Elena Tutubalina

Challenge:	Embodied AI is undergoing rapid development, with robots increasingly exhibiting practical utility in everyday environments.
Approach:	They evaluate the robustness of vision language action models under linguistic perturbations . they categorize irrelevant contexts into two groups according to their length and proximity to robot commands .
Outcome:	The proposed model can exhibit relative robustness to random context, with a performance drop within 10%, the authors show . human paraphrases of instructions lead to a drop of nearly 20%, the study shows .

Stable Language Guidance for Vision–Language–Action Models (2026.acl-long)

Copied to clipboard

Zhihao Zhan, Yuhao Chen, Jiaying Zhou, Qinhan Lyu, Hao Liu, Keze Wang, Liang Lin, Guangrun Wang

Visual Data in NLP

Challenge:	Existing vision-Language-Action models are notoriously brittle to linguistic perturbations.
Approach:	They propose a probabilistic framework that disentangles physical affordance from semantic execution.
Outcome:	The proposed framework disentangles physical affordance from semantic execution.

ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model (2025.emnlp-main)

Copied to clipboard

Zhongyi Zhou, Yichen Zhu, Minjie Zhu, Junjie Wen, Ning Liu, Zhiyuan Xu, Weibin Meng, Yaxin Peng, Chaomin Shen, Feifei Feng, Yi Xu

Multimodality

Challenge:	Recent advances in vision-language-action models prioritize robotic action mastery . however, models trained on visual-text pairs struggle to interpret multimodal data .
Approach:	They propose a framework that integrates multimodal data after initial control mastery and a Mixture-of-Experts architecture to minimize task interference.
Outcome:	The proposed framework surpasses state-of-the-art vision-language-action (VLA) methods on multimodal understanding benchmarks and achieves six times higher performance on visual question-answering datasets.

Limited Linguistic Diversity in Embodied AI Datasets (2026.acl-long)

Copied to clipboard

Selma Liliane Wanna, Agnes Luhtaru, Jonathan Salfity, Ryan Barron, Juston Moore, Cynthia Matuszek, Mitch Pryor

Challenge:	Language is a key modality in Vision-Language-Action (VLA) models, yet its linguistic characteristics are poorly documented.
Approach:	They propose to audit VLA corpora to characterize what kinds of instructions they contain . they quantify instruction language along complementary dimensions including lexical variety, duplication and overlap, semantic similarity, and syntactic complexity.
Outcome:	The proposed dataset audit of several widely used VLA datasets shows that many datasets rely on highly repetitive, template-like commands with limited structural variation yielding a narrow distribution of instruction forms.

Do What? Teaching Vision-Language-Action Models to Reject the Impossible (2025.findings-emnlp)

Copied to clipboard

Wen-Han Hsieh, Elvis Hsieh, Dantong Niu, Trevor Darrell, Roei Herzig, David M. Chan

Responsible & Trustworthy NLP

Challenge:	Recent studies show that VLAs can recognize, interpret, and respond to false-premise instructions.
Approach:	They propose a framework that detects when an instruction cannot be executed due to a false premise and engages in language-based clarification or correction.
Outcome:	The proposed framework detects when an instruction cannot be executed due to a false premise and engages in language-based clarification or correction.

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning (2025.acl-long)

Copied to clipboard

Qi Sun, Pengfei Hong, Tej Deep Pala, Vernon Toh, U-Xuan Tan, Deepanway Ghosal, Soujanya Poria

Multimodality

Challenge:	Visual-Language-Action models lack the ability to generate actionable policies tailored to specific robotic embodiments.
Approach:	They propose an embodied multimodal action model with Grounded Chain of Thought and Look-ahead Spatial Reasoning that enhances spatial reasoning and task planning.
Outcome:	The proposed model improves on existing baselines in tasks requiring spatial reasoning and grounding reasoning.

JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse (2025.findings-acl)

Copied to clipboard

Muyao Li, Zihao Wang, Kaichen He, Xiaojian Ma, Yitao Liang

Multimodality

Challenge:	Visual Language Action models have shown promise in decision-making tasks, but have been neglected in previous work .
Approach:	They propose a new paradigm for visual language action models that enhances the foundation model prior to action-specific tuning by first post-training it on a curated set of visual and linguistic tasks using self-supervised learning.
Outcome:	The proposed model outperforms the best agent baseline on a diverse set of atomic tasks and surpasses imitation learning-based policies in Minecraft.

MIRTH: Mutual-Information Reasoning with Temporal Hubs for Vision-Language-Action Agents (2026.acl-long)

Copied to clipboard

Hao Sun, Yu Song, Teng Shiyu, Ziwei Niu, Yen-wei Chen

Multimodality

Challenge:	a recent study shows that VLA models suffer from temporal myopia that discards historical dynamics and reasoning gaps between high-level instructions and low-level motor commands.
Approach:	They propose a framework to address temporal myopia and autoregressive scalar decoding in VLAs . they propose two memory hubs that compress long-term scene evolution and short-term motion trends .
Outcome:	The proposed framework achieves state-of-the-art performance and exhibiting emergent error recovery capabilities.

ATAAT: Adaptive Threat-Aware Adversarial Tuning Framework against Backdoor Attacks on Vision-Language-Action Models (2026.findings-acl)

Copied to clipboard

Kewei Chen, Yayu Long, Shuai Li, Mingsheng Shang

Robustness in NLP

Challenge:	Existing backdoor models rely on visual inputs for instruction parsing, rendering the perception pathway a critical attack surface.
Approach:	They propose an Adaptive Threat-Aware Adversarial Tuning framework that detects and decouples the optimal gradient decoupling strategy based on the adversary's capabilities.
Outcome:	The proposed framework achieves a highly robust targeted attack success rate while maintaining extreme stealthiness with a 5% poisoning rate.

Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance (2025.emnlp-main)

Copied to clipboard

Songsheng Wang, Rucheng Yu, Zhihang Yuan, Chao Yu, Feng Gao, Yu Wang, Derek F. Wong

Language Models

Challenge:	Visual Language Models (VLMs) have significant parameter size and autoregressive (AR) decoding nature impose considerable computational demands on VLA models.
Approach:	They propose a framework to relax acceptance utilizing the relative distances represented by the action tokens of the VLA model.
Outcome:	Empirical results show that the proposed framework improves the speed of the prediction task by 44%.

SilentDrift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models (2026.findings-acl)

Copied to clipboard

Bingxin Xu, Yuzhang Shang, Binghui Wang, Emilio Ferrara

Chunking

Challenge:	Existing backdoor attacks introduce kinematic discontinuities and distributional anomalies that can be flagged by standard trajectory detection.
Approach:	They propose a backdoor attack exploiting an intra-chunk visual open-loop vulnerability . they propose 93.2% Attack Success Rate and a poisoning rate under 2% .
Outcome:	The proposed attack achieves a 93.2% Attack Success Rate with a poisoning rate under 2% while maintaining a 95.3% Clean Task Success Rate.

Libra-VLA: Achieving Learning Equilibrium via Asynchronous Coarse-to-Fine Dual-System (2026.acl-long)

Copied to clipboard

Yifei Wei, Linqing Zhong, Yi Liu, Yuxiang Lu, Xindong He, Maoqing Yao, Guanghui Ren

Challenge:	Vision-Language-Action models ground high-level semantic instructions into executable physical actions.
Approach:	They propose a Coarse-to-Fine Dual-System VLA architecture that decouples learning complexity into a coarse-to fine hierarchy while leveraging structural modularity to implement an asynchronous execution strategy.
Outcome:	The proposed architecture decouples learning complexity into a coarse-to-fine hierarchy while leveraging structural modularity to implement an asynchronous execution strategy.

When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action Models (2026.acl-long)

Copied to clipboard

Xuan Dong, Zhe Han, Tianhao Niu, Qingfu Zhu, Wanxiang Che

Robustness in NLP

Challenge:	Vision-Language-Action models have shown strong performance in language-conditioned robotic manipulation, yet their robustness to linguistic variation remains poorly understood.
Approach:	They propose a step-wise inference-time intervention that aligns representations according to step language sensitivity, significantly improving performance under linguistic variation.
Outcome:	The proposed model significantly improves performance under linguistic variation under non-English instructions under language-agnostic steps.