Related papers: WAM-Diff: A Masked Diffusion VLA Framework with Mo…

End-to-End (E2E) solutions have emerged as a mainstream approach for autonomous driving systems, with Vision-Language-Action (VLA) models representing a new paradigm that leverages pre-trained multimodal knowledge from Vision-Language…

Research interest in end-to-end autonomous driving has surged owing to its fully differentiable design integrating modular tasks, i.e. perception, prediction and planing, which enables optimization in pursuit of the ultimate goal. Despite…

Large Language Models (LLMs) and Vision-Language Models (VLMs) have emerged as promising candidates for end-to-end autonomous driving. However, these models typically face challenges in inference latency, action precision, and…

Vision-Language-Action (VLA) models for autonomous driving increasingly adopt generative planners trained with imitation learning followed by reinforcement learning. Diffusion-based planners suffer from modality alignment difficulties, low…

End-to-end autonomous driving systems built on Vision Language Models (VLMs) have shown significant promise, yet their reliance on autoregressive architectures introduces some limitations for real-world applications. The sequential,…

Vision-Language-Action (VLA) models aim to control robots for manipulation from visual observations and natural-language instructions. However, existing hierarchical and autoregressive paradigms often introduce architectural overhead,…

The autonomous driving community is increasingly focused on addressing the challenges posed by out-of-distribution (OOD) driving scenarios. A dominant research trend seeks to enhance end-to-end (E2E) driving systems by integrating…

Vision-Language-Action (VLA) models adapt large vision-language backbones to map images and instructions into robot actions. However, prevailing VLAs either generate actions auto-regressively in a fixed left-to-right order or attach…

End-to-end autonomous driving via Vision-Language-Action (VLA) models demands a precarious balance between high-fidelity trajectory planning and efficient inference. Existing paradigms typically fall short: autoregressive (AR) VLAs are…

We introduce WAM-Flow, a vision-language-action (VLA) model that casts ego-trajectory planning as discrete flow matching over a structured token space. In contrast to autoregressive decoders, WAM-Flow performs fully parallel, bidirectional…

The rapid progress of auto-regressive vision-language models (VLMs) has inspired growing interest in vision-language-action models (VLA) for robotic manipulation. Recently, masked diffusion models, a paradigm distinct from autoregressive…

In autonomous driving, dynamic environment and corner cases pose significant challenges to the robustness of ego vehicle's state understanding and decision making. We introduce VDRive, a novel pipeline for end-to-end autonomous driving that…

Current end-to-end autonomous driving systems are fundamentally limited by a mismatch between temporal causal reasoning and global trajectory consistency. Autoregressive (AR) models capture interaction-aware temporal dependencies via causal…

End-to-end autonomous driving models based on Vision-Language-Action (VLA) architectures have shown promising results by learning driving policies through behavior cloning on expert demonstrations. However, imitation learning inherently…

A fundamental objective of manipulation policy design is to endow robots to comprehend human instructions, reason about scene cues, and execute generalized actions in dynamic environments. Recent autoregressive vision-language-action (VLA)…

Multimodal generative models require a unified approach to handle both discrete data (e.g., text and code) and continuous data (e.g., image, audio, video). In this work, we propose Latent Language Modeling (LatentLM), which seamlessly…

In this work, we introduce LLaDA-V, a purely diffusion-based Multimodal Large Language Model (MLLM) that integrates visual instruction tuning with masked diffusion models, representing a departure from the autoregressive paradigms dominant…

Discrete diffusion models have recently shown great promise for modeling complex discrete data, with masked diffusion models (MDMs) offering a compelling trade-off between quality and generation speed. MDMs denoise by progressively…

Prior masked modeling motion generation methods predominantly study text-to-motion. We present DiMo, a discrete diffusion-style framework, which extends masked modeling to bidirectional text--motion understanding and generation. Unlike…

World models that forecast environmental changes from actions are vital for autonomous driving models with strong generalization. The prevailing driving world model mainly build on video prediction model. Although these models can produce…