Copertina

HELM: Harness-Enhanced Long-horizon Memory for Vision-Language-Action Manipulation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zeng, Zijian, Ding, Fei, Yang, Huiming, Li, Xianwei
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

DexSim2Real: Foundation Model-Guided Sim-to-Real Transfer for Generalizable Dexterous Manipulation
di: Zeng, Zijian, et al.
Pubblicazione: (2026)

HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts
di: He, Neil, et al.
Pubblicazione: (2025)

Rethinking the Comparison Unit in Sequence-Level Reinforcement Learning: An Equal-Length Paired Training Framework from Loss Correction to Sample Construction
di: Ding, Fei, et al.
Pubblicazione: (2026)

Internalizing Outcome Supervision into Process Supervision: A New Paradigm for Reinforcement Learning for Reasoning
di: Ding, Fei, et al.
Pubblicazione: (2026)

Design Conditions for Intra-Group Learning of Sequence-Level Rewards: Token Gradient Cancellation
di: Ding, Fei, et al.
Pubblicazione: (2026)

villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models
di: Chen, Xiaoyu, et al.
Pubblicazione: (2025)

DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
di: Yin, Cheng, et al.
Pubblicazione: (2025)

Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation
di: Feng, Yunhai, et al.
Pubblicazione: (2025)

$\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
di: Chen, Xianwei, et al.
Pubblicazione: (2026)

CRL-VLA: Continual Vision-Language-Action Learning
di: Zeng, Qixin, et al.
Pubblicazione: (2026)

Reducing Credit Assignment Variance via Counterfactual Reasoning Paths
di: Ding, Fei, et al.
Pubblicazione: (2026)

SOLAR-RL: Semi-Online Long-horizon Assignment Reinforcement Learning
di: Wang, Jichao, et al.
Pubblicazione: (2026)

StateLinFormer: Stateful Training Enhancing Long-term Memory in Navigation
di: Chen, Zhiyuan, et al.
Pubblicazione: (2026)

Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection
di: Suo, Yucheng, et al.
Pubblicazione: (2025)

Toward Accurate Long-Horizon Robotic Manipulation: Language-to-Action with Foundation Models via Scene Graphs
di: Dinesh, Sushil Samuel, et al.
Pubblicazione: (2025)

AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models
di: Jiang, Yuhua, et al.
Pubblicazione: (2025)

Continuous Reasoning for Vision-Language-Action
di: Wu, Yueh-Hua, et al.
Pubblicazione: (2026)

Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos
di: Li, Qixiu, et al.
Pubblicazione: (2025)

Distilling and Retrieving Generalizable Knowledge for Robot Manipulation via Language Corrections
di: Zha, Lihan, et al.
Pubblicazione: (2023)

Enhancing Robotic Manipulation with AI Feedback from Multimodal Large Language Models
di: Liu, Jinyi, et al.
Pubblicazione: (2024)

ES-dLLM: Efficient Inference for Diffusion Large Language Models by Early-Skipping
di: Zhu, Zijian, et al.
Pubblicazione: (2026)

Towards General Continuous Memory for Vision-Language Models
di: Wu, Wenyi, et al.
Pubblicazione: (2025)

Recurrent Action Transformer with Memory
di: Cherepanov, Egor, et al.
Pubblicazione: (2023)

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning
di: Luo, Zhi, et al.
Pubblicazione: (2024)

TimeCapsule: Solving the Jigsaw Puzzle of Long-Term Time Series Forecasting with Compressed Predictive Representations
di: Lu, Yihang, et al.
Pubblicazione: (2025)

Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance
di: Wang, Songsheng, et al.
Pubblicazione: (2025)

CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
di: Li, Qixiu, et al.
Pubblicazione: (2024)

HyperVLA: Efficient Inference in Vision-Language-Action Models via Hypernetworks
di: Xiong, Zheng, et al.
Pubblicazione: (2025)

Chain-of-Modality: Learning Manipulation Programs from Multimodal Human Videos with Vision-Language-Models
di: Wang, Chen, et al.
Pubblicazione: (2025)

Understanding Asynchronous Inference Methods for Vision-Language-Action Models
di: Agouzoul, Ayoub
Pubblicazione: (2026)

Jump-Start Reinforcement Learning with Vision-Language-Action Regularization
di: Moroncelli, Angelo, et al.
Pubblicazione: (2026)

Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification
di: Wu, Yilin, et al.
Pubblicazione: (2025)

Offline Policy Learning via Skill-step Abstraction for Long-horizon Goal-Conditioned Tasks
di: Kim, Donghoon, et al.
Pubblicazione: (2024)

Enhancing Generalization in Vision-Language-Action Models by Preserving Pretrained Representations
di: Grover, Shresth, et al.
Pubblicazione: (2025)

Autoregressive Action Sequence Learning for Robotic Manipulation
di: Zhang, Xinyu, et al.
Pubblicazione: (2024)

Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks
di: Liu, Yang, et al.
Pubblicazione: (2025)

Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action Memory
di: He, Shiqi, et al.
Pubblicazione: (2025)

Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models
di: Jin, Ruofan, et al.
Pubblicazione: (2026)

PolarMem: A Training-Free Polarized Latent Graph Memory for Verifiable Vision-Language Models
di: Chen, Zhisheng, et al.
Pubblicazione: (2026)

Verifier-free Test-Time Sampling for Vision Language Action Models
di: Jang, Suhyeok, et al.
Pubblicazione: (2025)