Imagen de Portada

Offline Semantic Guidance for Efficient Vision-Language-Action Policy Distillation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shi, Jin, Zhang, Brady, Lu, Yishun
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies
por: Du, Fan, et al.
Publicado: (2026)

Second-Order Multi-Level Variance Correction for Modality Competition in Multimodal Models
por: Lu, Yishun, et al.
Publicado: (2026)

TernaryCLIP: Efficiently Compressing Vision-Language Models with Ternary Weights and Distilled Knowledge
por: Zhang, Shu-Hao, et al.
Publicado: (2025)

Multimodal Distribution Matching for Vision-Language Dataset Distillation
por: Jeong, Jongoh, et al.
Publicado: (2026)

VGAS: Value-Guided Action-Chunk Selection for Few-Shot Vision-Language-Action Adaptation
por: Xu, Changhua, et al.
Publicado: (2026)

Remodeling Semantic Relationships in Vision-Language Fine-Tuning
por: Wu, Xiangyang, et al.
Publicado: (2025)

When Alignment Fails: Multimodal Adversarial Attacks on Vision-Language-Action Models
por: Yan, Yuping, et al.
Publicado: (2025)

VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies
por: Gao, Mingjian, et al.
Publicado: (2026)

INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling
por: Dong, Xin, et al.
Publicado: (2025)

VITA: Vision-to-Action Flow Matching Policy
por: Gao, Dechen, et al.
Publicado: (2025)

ARFlow: Human Action-Reaction Flow Matching with Physical Guidance
por: Jiang, Wentao, et al.
Publicado: (2025)

VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models
por: Zhang, Jianke, et al.
Publicado: (2026)

InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
por: Chen, Xinyi, et al.
Publicado: (2025)

UniCMs: A Unified Consistency Model For Efficient Multimodal Generation and Understanding
por: Xu, Chenkai, et al.
Publicado: (2025)

Adversarial Prompt Distillation for Vision-Language Models
por: Luo, Lin, et al.
Publicado: (2024)

CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games
por: Chen, Peng, et al.
Publicado: (2025)

MAGIC: Meta-Ability Guided Interactive Chain-of-Distillation for Effective-and-Efficient Vision-and-Language Navigation
por: Wang, Liuyi, et al.
Publicado: (2024)

DMGD: Train-Free Dataset Distillation with Semantic-Distribution Matching in Diffusion Models
por: Wang, Qichao, et al.
Publicado: (2026)

Representation Calibration and Uncertainty Guidance for Class-Incremental Learning based on Vision Language Model
por: Tan, Jiantao, et al.
Publicado: (2025)

Continuous Vision-Language-Action Co-Learning with Semantic-Physical Alignment for Behavioral Cloning
por: Qi, Xiuxiu, et al.
Publicado: (2025)

Information-Theoretic Constraints for Continual Vision-Language-Action Alignment
por: Zhao, Libang, et al.
Publicado: (2026)

X-Distill: Cross-Architecture Vision Distillation for Visuomotor Learning
por: Shao, Maanping, et al.
Publicado: (2026)

IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model
por: Jiang, Anqing, et al.
Publicado: (2025)

NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning
por: Rawal, Ishaan, et al.
Publicado: (2026)

Dual-Model Distillation for Efficient Action Classification with Hybrid Edge-Cloud Solution
por: Wei, Timothy, et al.
Publicado: (2024)

When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models
por: Lu, Hui, et al.
Publicado: (2025)

A Survey on Efficient Vision-Language-Action Models
por: Yu, Zhaoshu, et al.
Publicado: (2025)

Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight
por: Yang, Yi, et al.
Publicado: (2025)

Single-Sample Black-Box Membership Inference Attack against Vision-Language Models via Cross-modal Semantic Alignment
por: Li, Jiaqing, et al.
Publicado: (2026)

SARVLM: A Vision Language Foundation Model for Semantic Understanding in SAR Imagery
por: Ma, Qiwei, et al.
Publicado: (2025)

Rebalanced Vision-Language Retrieval Considering Structure-Aware Distillation
por: Yang, Yang, et al.
Publicado: (2024)

InkSight: Offline-to-Online Handwriting Conversion by Teaching Vision-Language Models to Read and Write
por: Mitrevski, Blagoj, et al.
Publicado: (2024)

Active Multimodal Distillation for Few-shot Action Recognition
por: Feng, Weijia, et al.
Publicado: (2025)

Does Visual Information Play a Decisive Role in Vision-Language-Action Model Driving Behavior?
por: He, Jingtao, et al.
Publicado: (2026)

D3S2: Diffusion-Guided Dataset Distillation for Semantic Segmentation
por: Zheng, Wenjie, et al.
Publicado: (2026)

Survey on Vision-Language-Action Models
por: Adilkhanov, Adilzhan, et al.
Publicado: (2025)

Enhancing Medical Large Vision-Language Models via Alignment Distillation
por: Chang, Aofei, et al.
Publicado: (2025)

AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors
por: Yuan, Kaishen, et al.
Publicado: (2024)

Attention-Guided Patch-Wise Sparse Adversarial Attacks on Vision-Language-Action Models
por: Zhang, Naifu, et al.
Publicado: (2025)

Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance
por: Chen, Xinrong, et al.
Publicado: (2026)