Copertina

Beyond World-Frame Action Heads: Motion-Centric Action Frames for Vision-Language-Action Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yang, Huoren, Zhao, Jianchao, Yusong, Hu, Ou, Qiguan, Gao, Yuyang, Ke, Wei, He, Yuhang, Dong, SongLin, Ma, Zhiheng, Gong, Yihong
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

Neural Implicit Action Fields: From Discrete Waypoints to Continuous Functions for Vision-Language-Action Models
di: Liu, Haoyun, et al.
Pubblicazione: (2026)

ActionPlan: Future-Aware Streaming Motion Synthesis via Frame-Level Action Planning
di: Nazarenus, Eric, et al.
Pubblicazione: (2026)

Unleashing the Potential of All Test Samples: Mean-Shift Guided Test-Time Adaptation
di: Han, Jizhou, et al.
Pubblicazione: (2025)

Unify Robot Actions in Camera Frame
di: Xie, Sicheng, et al.
Pubblicazione: (2025)

Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration
di: He, Haisen, et al.
Pubblicazione: (2026)

Trajectory-Diversity-Driven Robust Vision-and-Language Navigation
di: Li, Jiangyang, et al.
Pubblicazione: (2026)

ReMoT: Reinforcement Learning with Motion Contrast Triplets
di: Wan, Cong, et al.
Pubblicazione: (2026)

Recurrence-Complete Frame-based Action Models
di: Keiblinger, Michael
Pubblicazione: (2025)

VDC-Agent: When Video Detailed Captioners Evolve Themselves via Agentic Self-Reflection
di: Wang, Qiang, et al.
Pubblicazione: (2025)

ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context
di: Jang, Huiwon, et al.
Pubblicazione: (2025)

DAWM: Diffusion Action World Models for Offline Reinforcement Learning via Action-Inferred Transitions
di: Li, Zongyue, et al.
Pubblicazione: (2025)

Understanding Multimodal Complementarity for Single-Frame Action Anticipation
di: Benavent-Lledo, Manuel, et al.
Pubblicazione: (2026)

ReSpike: Residual Frames-based Hybrid Spiking Neural Networks for Efficient Action Recognition
di: Xiao, Shiting, et al.
Pubblicazione: (2024)

EventCrab: Harnessing Frame and Point Synergy for Event-based Action Recognition and Beyond
di: Cao, Meiqi, et al.
Pubblicazione: (2024)

DualCP: Rehearsal-Free Domain-Incremental Learning via Dual-Level Concept Prototype
di: Wang, Qiang, et al.
Pubblicazione: (2025)

Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy
di: Zhang, Tianyi, et al.
Pubblicazione: (2025)

GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery
di: Han, Jizhou, et al.
Pubblicazione: (2026)

Learning Like Humans: Analogical Concept Learning for Generalized Category Discovery
di: Han, Jizhou, et al.
Pubblicazione: (2026)

Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery
di: Han, Jizhou, et al.
Pubblicazione: (2025)

Permutation-Aware Action Segmentation via Unsupervised Frame-to-Segment Alignment
di: Tran, Quoc-Huy, et al.
Pubblicazione: (2023)

Training-Free Action Recognition and Goal Inference with Dynamic Frame Selection
di: Keat, Ee Yeo, et al.
Pubblicazione: (2024)

One-Frame Calibration with Siamese Network in Facial Action Unit Recognition
di: Feng, Shuangquan, et al.
Pubblicazione: (2024)

WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation
di: Zhao, Baining, et al.
Pubblicazione: (2026)

CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling
di: Li, Hao, et al.
Pubblicazione: (2025)

X-DiffVLA: X-Embodied Diffusion Action Heads for Vision-Language-Action Models
di: Li, Boyu, et al.
Pubblicazione: (2026)

EgoAction: Egocentric Action Composition with Reliability-Aware Temporal Fusion for the EPIC-KITCHENS Action Detection Challenge at CVPR 2026
di: Fu, Zhiheng, et al.
Pubblicazione: (2026)

Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristic
di: Tang, Jianwei, et al.
Pubblicazione: (2025)

From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction
di: Miao, Xingyu, et al.
Pubblicazione: (2026)

World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems
di: Li, Runze, et al.
Pubblicazione: (2026)

CASR: Refining Action Segmentation via Marginalizing Frame-levle Causal Relationships
di: Du, Keqing, et al.
Pubblicazione: (2023)

LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuning
di: Lai, Bolin, et al.
Pubblicazione: (2023)

Common Ground: Framing and the Potential to Mitigate Herbicide Resistance Using Collective Action
di: Ariel Singerman, et al.
Pubblicazione: (2025)

E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving
di: Tang, Yihong, et al.
Pubblicazione: (2025)

Beyond Prompt Learning: Continual Adapter for Efficient Rehearsal-Free Continual Learning
di: Gao, Xinyuan, et al.
Pubblicazione: (2024)

ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models
di: Tang, Zuojin, et al.
Pubblicazione: (2026)

Vision-Language Models Unlock Task-Centric Latent Actions
di: Nikulin, Alexander, et al.
Pubblicazione: (2026)

Full‐Scale Tests to Characterize the Effect of Framing Action and Slab Continuity on the Collapse Capacity of Composite Frames Under Cyclic Loading
di: Hammad El Jisr, et al.
Pubblicazione: (2024)

RotVLA: Rotational Latent Action for Vision-Language-Action Model
di: Li, Qiwei, et al.
Pubblicazione: (2026)

Light Future: Multimodal Action Frame Prediction via InstructPix2Pix
di: Zhong, Zesen, et al.
Pubblicazione: (2025)