Tag
HiFOR proposes a hierarchical foresight framework with action-guided world retrieval for vision-language-action models, jointly predicting short-term states, semantic milestones, and goal states to better guide robotic manipulation action generation.
VLDA提出用紧凑的Delta变量将机器人控制重构为可操作的转变建模，作为视觉语言理解与动作生成之间的接口，相比直接观测-动作映射和完整未来状态预测，提升了长程一致性、鲁棒性和泛化能力。
PINT 提出了一种统一模型，通过可学习的预测意图令牌（Predictive Intent Tokens）协调视觉语言推理、视频世界建模与动作生成，在无需具身预训练的情况下显著提升了机器人操作的分布外泛化能力，在 RoboTwin 2.0-Hard 和 LIBERO-Plus 等基准上大幅超越 Fast-WAM 和 StarVLA。
Dynin-Robotics is an omnimodal unified diffusion model that integrates vision, language, and action for language-conditioned robot control, improving adaptation and success through joint denoising and test-time scaling.
The paper proposes Latent Interface Training (LIT), a two-stage strategy to enhance generalization in robotics foundation models by mitigating vision-action shortcuts through pose-supervised latent interfaces.
WorldDiT is a unified diffusion transformer architecture that couples action generation with visual world modeling, achieving strong performance on LIBERO simulation suites without relying on large pretrained vision-language models.
Proposes AR-VLA, an autoregressive action expert that generates continuous action sequences with long-term memory for context-aware robotic policy training, improving trajectory smoothness and task success rates over reactive VLA models.