arXiv subjects

Wenxuan Song

Publications and source records attributed to Wenxuan Song.

At least 37 records · Page 2Linked to original sources

arXiv2026

MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation

Vision-Language-Action (VLA) models map visual observations and natural-language instructions to robot actions; however, hierarchical and autoregressive paradigms often incur architectural overhead, accumulate long-horizon errors, and require auxiliary modules to capture environment dynamics. To this end, we present MMaDA-VLA, a fully native, pretrained discrete diffusion VLA that unifies multi-modal understanding and generation. Specifically, MMaDA-VLA uses a shared discrete token space to jointly denoise a future goal observation and an action chunk, grounding actions in predicted visual outcomes without an auxiliary world model. In this way, parallel, order-free refinement improves long-horizon consistency. Extensive experiments and comprehensive analyses demonstrate that MMaDA-VLA achieves an average success rate of 98.0\% on LIBERO and an average successful sequence length of 4.78 on CALVIN, while performing strongly in real-world settings. The project page is available at https://yliu-cs.github.io/MMaDA-VLA.

cs.RO↗

arXiv2026

DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching

Vision-Language-Action (VLA) models that encode actions using a discrete tokenization scheme have been widely adopted for robotic manipulation, but existing decoding paradigms remain fundamentally limited. Whether actions are decoded sequentially by autoregressive VLAs or in parallel by discrete diffusion VLAs, once a token is generated, it is typically fixed and cannot be revised in subsequent iterations. Consequently, early token errors cannot be effectively corrected later. We propose DFM-VLA, a discrete flow matching VLA that iteratively refines action tokens. DFM-VLA models a token-level probability velocity field that dynamically updates the full action sequence across refinement iterations. We investigate two approaches to constructing the velocity field: an auxiliary velocity-head formulation and an embedding-guided formulation. To further improve prediction accuracy, we introduce a metric-aligned action tokenizer (MAAT) tailored to the coarse-to-fine nature of DFM, together with a two-stage decoding strategy. Extensive experiments on CALVIN, LIBERO, LIBERO-Plus, and real-world manipulation tasks demonstrate the effectiveness of our approach. Our project is available at https://chris1220313648.github.io/DFM-VLA/.

cs.RO↗

arXiv2026

MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight

World action models (WAMs) built on video generation backbones are a rising recipe for robot learning, yet remain confined to tabletop manipulation. Mobile manipulation demands simultaneous locomotion and whole-body manipulation amid scene-scale dynamics, yet is still dominated by dynamics-blind visual encoders with hand-crafted coordination. We bridge this gap with MobileWAM, a mixture-of-transformers architecture that fuses a pretrained video diffusion transformer with a lightweight action expert through layerwise joint attention, translating internet-scale motion priors into whole-body control. To reconcile the heterogeneous dynamics of moving and manipulating, each feed-forward layer of the action expert becomes a three-expert mixture of shared, locomotion, and manipulation experts, softly routed by the motion intent in the action tokens. To densify supervision, we further propose Chain-of-Foresight (CoF): intermediate representations sequentially predict a chain of future latent chunks, each step conditioned on its predecessor. CoF pairs naturally with our decoupled video--action denoising scheme. At deployment, the WAM serves as a pure current-frame encoder; foresight acts only through gradients, so at inference the foresight chain and video generation are discarded, leaving only policy-level cost. MobileWAM surpasses state-of-the-art mobile manipulation policies on ManiSkill-HAB and fine-tunes to a real ARX Lift2 mobile manipulator across diverse tasks with strong generalization. Code will be released soon.

cs.CV↗

arXiv2026

MoWorld: A Flash World Model

The future of World Models depends not only on scaling model capability, but also on scaling practicality and inference efficiency. High-frame-rate inference enables responsive perception, planning, and control in real-world autonomous systems. To this end, we present MoWorld, a cost-effective yet high-performance Flash World Model with an end-to-end framework spanning data generation, pre-training, distillation, and efficient inference, enabling up to 50 FPS real-time interaction with cinematic visual quality without the need of high-end GPUs. To enable large-scale real-world deployment, MoWorld jointly optimizes model capability and cost throughout the entire development pipeline. Specifically, unlike existing approaches that primarily rely on large-scale video corpora, MoWorld is built upon a scalable 3D-native data engine accumulated from our large-scale 3D vision and generative modeling pipeline, enabling the efficient construction of geometrically consistent training data across diverse real-world and synthetic environments. Based on this foundation, a curriculum cross-frame pre-training strategy for stable and scalable World Model learning, an efficient denoising-step distillation algorithm to reduce diffusion training cost, and a mixed-precision parallel inference framework for low-cost real-time deployment. MoWorld is the first real-time interactive World Model built on the Neural Processing Unit (NPU) and can achieves up to 50 FPS in such the devices, enabling practical and efficient deployment at scale. Comprehensive evaluations demonstrate that MoWorld achieves leading performance; notably, its average inference cost is only 30\%-50\% of that of existing World Models, providing a practical foundation for large-scale real-world applications of World Models. We also demonstrate diverse applications of MoWorld.

cs.CV↗

arXiv2026

Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories

We present Xiaomi-Robotics-1, a foundational vision-language-action (VLA) model capable of (1) following diverse language instructions to perform a wide range of mobile manipulation tasks in unseen environments out-of-the-box, and (2) efficiently adapting to novel downstream tasks with minimal fine-tuning data. We propose a two-stage training recipe consisting of pre-training and post-training. During pre-training, we imbue the model with broad and generalizable action-generation capabilities by training on over 100k hours of real-world manipulation trajectories collected via UMI devices. Crucially, we develop a scalable auto-labeling pipeline that annotates trajectory clips with natural languages describing scene state transitions, providing rich and precise conditioning for action learning. During post-training, we aim to align these capabilities with robot embodiments and imperative instructions that humans naturally use to prompt robots. Extensive experiments demonstrate strong scaling behavior. Xiaomi-Robotics-1 consistently improves with increased data scales and model sizes during pre-training. This scaling behavior directly transfers to post-training, where a stronger pre-training model yields better out-of-the-box real-robot performance in unseen environments. Furthermore, Xiaomi-Robotics-1 serves as a strong robot foundation policy that can be efficiently fine-tuned on complex, dexterous tasks with high data efficiency. Across multiple simulation benchmarks, Xiaomi-Robotics-1 outperforms state-of-the-art methods. Notably, it establishes a new state-of-the-art with a 57.4% success rate on RoboCasa365, surpassing the previous best of 46.6%. Furthermore, it achieves an average score of 20.07 on RoboDojo, significantly outperforming the prior state-of-the-art (13.07). Code and model checkpoints will be released. Project page: https://robotics.xiaomi.com/xiaomi-robotics-1.html

cs.RO↗

arXiv2026

IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams

Recent multimodal large language models (MLLMs) achieve strong performance on reactive question answering, but real-world streaming assistants require proactive reasoning over continuous visual inputs. Existing benchmarks mainly study reactive or proactive interactions in isolated single-turn settings, overlooking dynamic multi-turn scenarios where users may add, modify, or cancel proactive requests alongside interleaved reactive queries. To address this gap, we introduce IPIBench, the first benchmark for evaluating Interactive Proactive Intelligence of MLLMs under streaming video settings. IPIBench covers proactive monitoring, proactive task management, and interleaved reactive-proactive requests. Evaluations on representative MLLMs reveal two major limitations: unstable proactive triggering and weak coordination between reactive and proactive behaviors. We further propose IPI-Agent, a training-free agentic framework with an interaction-control policy and a temporal-gating mechanism for stabilizing proactive triggering and coordinating multi-turn interactions. Experiments show that IPI-Agent consistently improves existing MLLMs across all benchmark settings.

cs.CV↗

arXiv2026

CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models

This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT). Some advanced finetuning methods with auxiliary training objectives can improve performance and reduce the number of convergence steps. However, they typically incur significant computational overhead due to the additional losses from auxiliary objectives. To simultaneously achieve the enhanced capabilities of auxiliary training with the simplicity of standard SFT, we decouple the two objectives of auxiliary-objective SFT within the parameter space, namely, enhancing general capabilities and fitting task-specific action distributions. To deliver the goal, we only need to train the model to converge on a small-scale task set using two distinct training strategies, resulting in two finetuned models. The parameters' difference between the two models can then be interpreted as capability vectors provided by auxiliary objectives. These vectors are then merged with pretrained parameters to form a capability-enhanced meta model. Moreover, when standard SFT is augmented with a lightweight orthogonal regularization loss, the merged model attains performance comparable to auxiliary finetuned baselines with reduced computational overhead. Internal and external experiments demonstrate that our capability vectors (1) are effective and versatile across diverse models, (2) can generalize to novel environments and embodiments out of the box.

cs.CV↗

arXiv2026

RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark

Memory is a critical component of robotic intelligence, as robots must rely on past observations and actions to accomplish long-horizon tasks in partially observable environments. However, existing robotic memory benchmarks still lack multimodal annotations for memory formation, provide limited task coverage and structural complexity, and remain restricted to simulation without real-world evaluation. We address this gap with RoboMemArena, a large-scale benchmark of 26 tasks, with average trajectory lengths exceeding 1,000 steps per task and 68.9% of subtasks being memory-dependent. The generation pipeline leverages a vision-language model (VLM) to design and compose subtasks, generates full trajectories through atomic functions, and provides memory-related annotations, including subtask instructions and native keyframe annotations, while paired real-world memory tasks support physical evaluation. We further design PrediMem, a dual-system VLA in which a high-level VLM planner manages a memory bank with recent and keyframe buffers and uses a predictive coding head to improve sensitivity to task dynamics. Extensive experiments on RoboMemArena show that PrediMem outperforms all baselines and provides insights into memory management, model architecture, and scaling laws for complex memory systems.

cs.RO↗

arXiv2026

HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models

Vision-Language-Action (VLA) models have recently enabled robotic manipulation by grounding visual and linguistic cues into actions. However, most VLAs assume the Markov property, relying only on the current observation and thus suffering from temporal myopia that degrades long-horizon coherence. In this work, we view motion as a more compact and informative representation of temporal context and world dynamics, capturing inter-state changes while filtering static pixel-level noise. From this perspective, HiF-VLA equips a motion-centric world model for the VLA, enabling agents to reason about temporal dynamics for future evolution during action generation. Building on this idea, we propose HiF-VLA (Hindsight, Insight, and Foresight for VLAs), a unified framework that leverages motion for bidirectional temporal reasoning. HiF-VLA encodes past dynamics through hindsight priors, anticipates future motion via foresight reasoning, and integrates both through a hindsight-modulated joint expert to enable a ''think-while-acting'' paradigm for long-horizon manipulation. As a result, HiF-VLA surpasses strong baselines on LIBERO-Long and CALVIN ABC-D benchmarks, while incurring negligible additional inference latency. Furthermore, HiF-VLA achieves substantial improvements in real-world long-horizon manipulation tasks, demonstrating its broad effectiveness in practical robotic settings.

cs.RO↗

arXiv2026

Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance

This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT). Some advanced finetuning methods with auxiliary training objectives can improve performance and reduce the number of convergence steps. However, they typically incur significant computational overhead due to the additional losses from auxiliary tasks. To simultaneously achieve the enhanced capabilities of auxiliary training with the simplicity of standard SFT, we decouple the two objectives of auxiliary task training within the parameter space, namely, enhancing general capabilities and fitting task-specific action distributions. To deliver this goal, we only need to train the model to converge on a small-scale task set using two distinct training strategies. The difference between the resulting model parameters can then be interpreted as capability vectors provided by auxiliary tasks. These vectors are then merged with pretrained parameters to form a capability-enhanced meta model. Moreover, when standard SFT is augmented with a lightweight orthogonal regularization loss, the merged model attains performance comparable to auxiliary finetuned baselines with reduced computational overhead. Experimental results demonstrate that this approach is highly effective across diverse robot tasks. Project page: https://chris1220313648.github.io/Fast-dVLA/

cs.RO↗

arXiv2026

Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process

Vision-language-action (VLA) models aim to understand natural language instructions and visual observations and to execute corresponding actions as an embodied agent. Recent work integrates future images into the understanding-acting loop, yielding unified VLAs that jointly understand, generate, and act -- reading text and images and producing future images and actions. However, these models either rely on external experts for modality unification or treat image generation and action prediction as separate processes, limiting the benefits of direct synergy between these tasks. Our core philosophy is to optimize generation and action jointly through a synchronous denoising process, where the iterative refinement enables actions to evolve from initialization, under constant and sufficient visual guidance. We ground this philosophy in our proposed Unified Diffusion VLA and Joint Discrete Denoising Diffusion Process (JD3P), which is a joint diffusion process that integrates multiple modalities into a single denoising trajectory to serve as the key mechanism enabling understanding, generation, and acting to be intrinsically synergistic. Our model and theory are built on a unified tokenized space of all modalities and a hybrid attention mechanism. We further propose a two-stage training pipeline and several inference-time techniques that optimize performance and efficiency. Our approach achieves state-of-the-art performance on benchmarks such as CALVIN, LIBERO, and SimplerEnv with 4$\times$ faster inference than autoregressive methods, and we demonstrate its effectiveness through in-depth analysis and real-world evaluations. Our project page is available at https://irpn-eai.github.io/UD-VLA.github.io/.

cs.RO↗

arXiv2026

VAMPO: Policy Optimization for Improving Visual Dynamics in Video Action Models

Video action models are an appealing foundation for Vision--Language--Action systems because they can learn visual dynamics from large-scale video data and transfer this knowledge to downstream robot control. Yet current diffusion-based video predictors are trained with likelihood-surrogate objectives, which encourage globally plausible predictions without explicitly optimizing the precision-critical visual dynamics needed for manipulation. This objective mismatch often leads to subtle errors in object pose, spatial relations, and contact timing that can be amplified by downstream policies. We propose VAMPO, a post-training framework that directly improves visual dynamics in video action models through policy optimization. Our key idea is to formulate multi-step denoising as a sequential decision process and optimize the denoising policy with rewards defined over expert visual dynamics in latent space. To make this optimization practical, we introduce an Euler Hybrid sampler that injects stochasticity only at the first denoising step, enabling tractable low-variance policy-gradient estimation while preserving the coherence of the remaining denoising trajectory. We further combine this design with GRPO and a verifiable non-adversarial reward. Across diverse simulated and real-world manipulation tasks, VAMPO improves task-relevant visual dynamics, leading to better downstream action generation and stronger generalization. The homepage is https://vampo-robot.github.io/VAMPO/.

cs.RO↗

arXiv2026

S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresight

Video action models (VAMs) have emerged as a promising paradigm for robot learning, owing to their powerful visual foresight for complex manipulation tasks. However, current VAMs, typically relying on either slow multi-step video generation or noisy one-step feature extraction, cannot simultaneously guarantee real-time inference and high-fidelity foresight. To address this limitation, we propose S-VAM, a shortcut video-action model that foresees coherent geometric and semantic representations via a single forward pass. Serving as a stable blueprint, these foreseen representations significantly simplify the action prediction. To enable this efficient shortcut, we introduce a novel self-distillation strategy that condenses structured generative priors of multi-step denoising into one-step inference. Specifically, vision foundation model (VFM) representations extracted from the diffusion model's own multi-step generated videos provide teacher targets. Lightweight decouplers, as students, learn to directly map noisy one-step features to these targets. Extensive experiments in simulation and the real world demonstrate that our S-VAM outperforms state-of-the-art methods, enabling efficient and precise manipulation in complex environments. Our project page is https://haodong-yan.github.io/S-VAM/

cs.CV↗

arXiv2026

PROSPECT: Unified Streaming Vision-Language Navigation via Semantic--Spatial Fusion and Latent Predictive Representation

Multimodal large language models (MLLMs) have advanced zero-shot end-to-end Vision-Language Navigation (VLN), yet robust navigation requires not only semantic understanding but also predictive modeling of environment dynamics and spatial structure. We propose PROSPECT, a unified streaming navigation agent that couples a streaming Vision-Language-Action (VLA) policy with latent predictive representation learning. PROSPECT uses CUT3R as a streaming 3D foundation spatial encoder to produce long-context, absolute-scale spatial features, and fuses them with SigLIP semantic features via cross-attention. During training, we introduce learnable stream query tokens that query the streaming context and predict next-step 2D and 3D latent features (rather than pixels or explicit modalities), supervised in the latent spaces of frozen SigLIP and CUT3R teachers. The predictive branch shapes internal representations without inference overhead. Experiments on VLN-CE benchmarks and real-robot deployment demonstrate state-of-the-art performance and improved long-horizon robustness under diverse lighting. We will release code for the community soon.

cs.CV↗

arXiv2026

Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline

Vision-Language-Action (VLA) models have emerged as a generalist robotic agent. However, existing VLAs are hindered by excessive parameter scales, prohibitive pre-training requirements, and limited applicability to diverse embodiments. To improve the practicality of VLAs, we propose a comprehensive benchmark and an improved baseline. First, we propose CEBench, a new benchmark spanning diverse embodiments in both simulation and the real world with consideration of domain randomization. We collect 14.4k simulated trajectories and 1.6k real-world expert-curated trajectories to support training on CEBench. Second, using CEBench as our testbed, we study three critical aspects of VLAs' practicality and offer several key findings. Informed by these findings, we introduce LLaVA-VLA, a lightweight yet powerful VLA designed for practical deployment on consumer-grade GPUs. Architecturally, it integrates a compact VLM backbone with multi-view perception, proprioceptive tokenization, and action chunking. To eliminate reliance on costly pre-training, LLaVA-VLA adopts a two-stage training paradigm including post-training and fine-tuning. Furthermore, LLaVA-VLA extends the action space to unify navigation and manipulation. Experiments across embodiments demonstrate the capabilities of generalization and versatility of LLaVA-VLA , while real-world mobile manipulation experiments establish it as the first end-to-end VLA model for mobile manipulation. We will open-source all datasets, codes, and checkpoints upon acceptance to foster reproducibility and future research.

cs.RO↗

arXiv2026

PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding

Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation. The performance of VLA models can be improved by integrating with action chunking, a critical technique for effective control. However, action chunking linearly scales up action dimensions in VLA models with increased chunking sizes. This reduces the inference efficiency. To tackle this problem, we propose PD-VLA, the first parallel decoding framework for VLA models integrated with action chunking. Our framework reformulates autoregressive decoding as a nonlinear system solved by parallel fixed-point iterations. This approach preserves model performance with mathematical guarantees while significantly improving decoding speed. In addition, it enables training-free acceleration without architectural changes, as well as seamless synergy with existing acceleration techniques. Extensive simulations validate that our PD-VLA maintains competitive success rates while achieving 2.52 times execution frequency on manipulators (with 7 degrees of freedom) compared with the fundamental VLA model. Furthermore, we experimentally identify the most effective settings for acceleration. Finally, real-world experiments validate its high applicability across different tasks.

cs.RO↗

arXiv2026

FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignment

Enabling VLA models to predict environmental dynamics, known as world modeling, has been recognized as essential for improving robotic reasoning and generalization. However, current approaches face two main issues: 1. The training objective forces models to over-emphasize pixel-level reconstruction, which constrains semantic learning and generalization 2. Reliance on predicted future observations during inference often leads to error accumulation. To address these challenges, we introduce Future Representation Alignment via Parallel Progressive Expansion (FRAPPE). Our method adopts a two-stage fine-tuning strategy: In the mid-training phase, the model learns to predict the latent representations of future observations; In the post-training phase, we expand the computational workload in parallel and align the representation simultaneously with multiple different visual foundation models. By significantly improving fine-tuning efficiency and reducing dependence on action-annotated data, FRAPPE provides a scalable and data-efficient pathway to enhance world-awareness in generalist robotic policies. Experiments on the RoboTwin benchmark and real-world tasks demonstrate that FRAPPE outperforms state-of-the-art approaches and shows strong generalization in long-horizon and unseen scenarios.

cs.RO↗

arXiv2026

"In my defense, only three hours on Instagram": Designing Toward Digital Self-Awareness and Wellbeing

Screen use pervades daily life, shaping work, leisure, and social connections while raising concerns for digital wellbeing. Yet, reducing screen time alone risks oversimplifying technology's role and neglecting its potential for meaningful engagement. We posit self-awareness -- reflecting on one's digital behavior -- as a critical pathway to digital wellbeing. We developed WellScreen, a lightweight probe that scaffolds daily reflection by asking people to estimate and report smartphone use. In a two-week deployment with college students (N=25) focused on generating formative insights, we examined how discrepancies between estimated and actual usage shaped digital awareness and wellbeing. Participants often underestimated productivity and social media while overestimating entertainment app use. They showed a 10% improvement in positive affect, rating WellScreen as moderately useful. Interviews revealed that structured reflection supported recognition of patterns, adjustment of expectations, and more intentional engagement with technology. Our findings highlight the promise of lightweight reflective interventions for supporting self-awareness and intentional digital engagement, offering implications for designing digital wellbeing tools.

cs.HC↗