Contact-rich manipulation requires adapting to contact states that can evolve substantially within an action horizon. However, chunk-based vision-language-action models predict complete action chunks from observations collected before execution, leaving tactile conditioning stale during execution. Existing tactile-reactive approaches typically rely on separate high-frequency controllers, which increase both architectural and training complexity. In this paper, we introduce TacForcing, a streaming action-generation framework that effectively incorporates execution-time tactile feedback. Instead of employing a separate reactive controller, TacForcing replaces the standard action expert with a streaming action expert to generate actions conditioned on the evolving tactile observations acquired during execution. TacForcing also introduces Execution-Aware Tactile Attention (EATA), which restricts tactile conditioning to actions nearing execution, thereby reducing the temporal mismatch between tactile acquisition and action execution. Across six simulated UniVTAC tasks and three real-world contact-rich manipulation tasks, TacForcing achieves average success rates of 65% and 69%, respectively, outperforming strong baselines in both settings.
Modern video games combine first-person perception, rapid visual changes, persistent world state, and heterogeneous native controls. Existing game agents map visual and task context directly to actions but lack explicit world dynamics modeling, whereas interactive game world models predict visual futures from supplied actions but do not serve as task policies. World-Action Models (WAMs) unify these objectives, but remain largely unexplored under the dynamics and open-ended interaction of video games. We introduce GameWAM, to our knowledge the first WAM for native closed-loop gameplay and GUI control. GameWAM jointly generates future visual observations and executable keyboard-mouse trajectories through parallel visual and action generative processes with block-causal conditioning and flow matching. To support joint world-action learning, we construct synchronized gameplay and GUI trajectories. To handle heterogeneous native control, GameWAM predicts a gameplay/GUI mode at each action step and generates actions with mode-specific prediction distributions and continuous-action normalization. For long-horizon interaction, block-cycle control predicts beyond the committed horizon, executes only a short action prefix, and replans from new observations, while fine-grained within-cycle context and hierarchical cross-cycle history preserve temporal continuity. Experiments demonstrate competitive task success with fewer executed native actions than the compared agents. We further uncover Low-Frequency Action Source Imprinting (LASI), in which low-frequency components of the sampled action source systematically steer coarse generated camera motion under fixed conditioning, revealing a source-sensitivity failure mode in generative control. Project page is available at https://yunncheng.github.io/GameWAM/.
Vision-Language-Action models (VLAs) integrate visual perception, language instruction, and action generation into end-to-end policies across heterogeneous architectures. However, enabling VLAs to self-evaluate their action generation reliability without external supervision remains a major challenge. Existing methods either rely on expert annotations or estimate uncertainty only from output statistics, largely ignoring internal signals. In this work, we observe that internal visual modality entropy exhibits consistent distinctions between successful and failed tasks across heterogeneous VLAs. Although VLAs' architectures differ in their action generation, we show that they share a common latent action generation abstraction evolving under visual perception, language instruction, and state input, which we formulate as a Conditional Generative Markov Chain. Based on this formulation, we propose MAE (Markov Attention Entropy), a self-evaluation framework that directly converts internal attention signals into architecture-aware reliability scores, and introduce LIBERO-Reflect, a 4,000-episode benchmark combining 2,000 standard episodes and 2,000 challenging episodes across four subsets. Extensive experiments across heterogeneous VLA architectures and diverse scenarios show that MAE consistently outperforms state-of-the-art baselines on AUPR, AUROC, and FPR@95. We further instantiate FabriMAE for verifier-free test-time action selection, showing that MAE-guided multiple sampling improves PI-family robustness on LIBERO-Plus with small observed runtime overhead.
World Action Models (WAMs) couple future visual prediction with robot action generation, enabling policies to model how the physical world evolves during interaction. Existing WAMs differ in how predictive dynamics are exposed to the action pathway. Explicit-future WAMs provide direct access to predicted scene evolution, but incur substantial inference costs from iterative video denoising. In contrast, direct-policy WAMs efficiently predict actions from the current observation but lack an explicit inference-time interface for exposing predictive dynamics to the Action DiT. To bridge this gap, we propose ForeWAM, a dynamics-conditioned direct-policy WAM that provides predictive context for action generation without decoding future videos. At its core, Future-KV performs a single Video DiT prefill over the current visual latent and stochastic future slots, and reuses the resulting layer-wise key-value states throughout action denoising. We further introduce dynamics registers supervised by a frozen latent action teacher, encouraging the implicit future states to capture interaction-induced transitions such as object motion, contact changes, and task progress. Ground-truth future observations and the teacher are used only during training; deployment requires neither and performs no future video generation. Without embodied robot data pretraining, the standard and accelerated variants of ForeWAM achieve average success rates of 96.7% and 96.9% on LIBERO, respectively. The standard variant further achieves 61.6% success on LIBERO-Plus. These results demonstrate that direct-policy WAMs can retain efficient action prediction while exposing predictive dynamics to the action pathway without explicitly generating future observations.
Flow matching (FM) has become a popular action head paradigm for modern embodied models. However, as a conditional generative model, it does not explicitly expose its inherent uncertainty, producing faulty action chunks even when it misinterprets the scene or encounters out-of-distribution (OOD) inputs. Therefore, determining when an FM-generated action can be trusted is essential for safe deployment, yet existing uncertainty estimation methods on real-time control suffer from several issues: extra training budget, high computational overhead, and low generalization ability. In this work, we provide a geometric interpretation of FM uncertainty in the velocity field, showing that uncertainty manifests as deviation from an ideal affine-isotropic contraction field. Building on this observation, we introduce denoising acceleration ($\mathrm{accel}$), a highly-generalizable and cost-free uncertainty proxy that measures the bending of the denoising trajectory from a single forward pass, without additional model evaluations, training, or resampling. We theoretically and empirically demonstrate that $\mathrm{accel}$ is a faithful proxy for FM uncertainty and further test its utility in online failure detection. Results show that $\mathrm{accel}$ identifies failing rollouts well before termination, matching or even outperforming costly resampling- and training-based baselines across settings under realistic deployment budget. Code and demos available at: https://github.com/rrrrrrzy/fm-geometry.
Sen Wang, R. Gnana Praveen, Bidhan Roy +1cs.LG cs.RO
Many recent robot policies pursue stronger control by using large pretrained vision-language models (VLMs) as the action backbone. We introduce WorldDiT, a unified diffusion transformer architecture that couples action generation with visual world modeling and achieves strong performance without a large pretrained VLM action backbone. During training, a single diffusion transformer generates continuous action chunks and predicts normalized RGB patch targets from future camera frames. Across four LIBERO simulation suites, WorldDiT lies on the reported Pareto frontier for total model parameters and mean success among methods reporting all four suites. These results provide a strong sub-billion-parameter baseline for future scaling studies.
Vision-language-action (VLA) models aim to understand natural-language instructions and visual observations, and to generate and execute corresponding actions as embodied agents. Recently, autoregressive token-based action generation has driven the development of many representative VLA models. However, this paradigm often reduces action generation to next-token prediction, thereby lacking explicit modeling of the spatiotemporal structure of action sequences and the disentanglement between vision-language representations and actions, which can limit performance in long-horizon and complex scenarios. In this paper, we propose TS-Mask VLA, a vision-language-action framework for robot manipulation. TS-Mask VLA is built upon two key designs: (1) a Discrete Diffusion Action Expert equipped with a Bridge Attention conditioning bridge, which enables multi-layer conditioning from the VLM and facilitates more accurate and stable action generation; and (2) a temporal-spatial 2D masking strategy for discrete action tokens that strengthens the model's understanding of cross-time dependencies and inter-dimensional coupling, leading to more structurally consistent action sequences. We conduct extensive experiments on simulation benchmarks and real-world tasks. On LIBERO, TS-Mask VLA achieves a 95.7 percent average success rate with only 0.5B parameters, outperforming significantly larger models. On CALVIN, it attains the best average sequence length of 4.19 and strong long-horizon performance. Comprehensive analyses and ablations further validate the effectiveness of our design.
Jiaming Liu, Qingpo Wuwu, Nuowei Han +8cs.RO cs.CV
Recently, Vision-Language-Action (VLA) models have demonstrated strong generalization across diverse tasks. However, effective robotic manipulation in physical environments fundamentally requires geometric understanding and spatial reasoning. While some VLA approaches attempt to incorporate 3D information, they are constrained by limited data availability and geometric information loss in current 3D encoding pipelines, and fail to jointly capture 3D geometry and temporally structured actions in dynamic environments. To address these limitations, we introduce Lift3D-VLA, a unified VLA framework that equips models with explicit 3D point cloud reasoning and enables temporally coherent action generation. First, building upon our previous work Lift3D, an enhanced 2D model-lifting strategy is proposed to geometrically align 3D points with pretrained 2D positional embeddings. This design enables direct point-cloud encoding within the VLA vision encoder while minimizing spatial information loss. Based on explicit 3D inputs, we propose Geometry-Centric Masked Autoencoding (GC-MAE), a dual-objective self-supervised framework that reconstructs the current point cloud while predicting its future geometric evolution. This formulation allows the 2D vision encoder to internalize both 3D structure and physical dynamics. To fully exploit 3D representations, we further design layer-wise temporal action modeling, which leverages multiple layers of the LLM to collaboratively predict action chunks, enabling temporally consistent predictions. Across 22 simulated tasks and 8 real-world manipulation tasks, Lift3D-VLA achieves 10.8% and 11.1% higher mean success rates on MetaWorld and RLBench than the best-performing prior VLA methods, and outperforms the strongest real-world baseline by 4 percentage points, while exhibiting stronger generalization to out-of-distribution perturbations.
Existing world model-based planners for visual navigation typically follow a verification-centric paradigm, decoupling goal intent from trajectory synthesis. This approach suffers from candidate dependence, heavy computational overhead, and inconsistencies between sampled actions and predicted visuals. To address these issues, we propose SWAM (Spatial-perceiving World Action Model), a task-centric joint observation-action generation framework. Given start and goal RGB observations, SWAM performs single-pass inference to simultaneously generate intermediate RGB-D sequences and corresponding action trajectories, promoting goal-consistent trajectory generation and improved spatial feasibility. While SWAM leverages depth pseudo-labels during training to internalize spatial priors, it requires only monocular RGB input at inference time. We further introduce a visual-guided action refinement module and a trajectory-scale regularization loss to enforce fine-grained alignment between motion and visual cues while stabilizing predictions across varying distances. Extensive experiments show that SWAM significantly outperforms state-of-the-art two-stage planners in success rate, trajectory accuracy, and inference efficiency, while demonstrating robust zero-shot generalization to unseen environments.
World Action Models (WAMs) unify future environment prediction with action generation for autonomous driving, yet existing approaches optimize only the final outputs, leaving intermediate representations as incidental byproducts. We present ReWorld, the first representation learning framework specifically designed for autonomous-driving WAMs. ReWorld explicitly optimizes the latent world-to-action pathway through three complementary mechanisms. First, it imposes future-predictive supervision on intermediate Video DiT states to encode temporal scene dynamics, enabling self-guided sampling and a roughly twofold convergence speedup. Second, it aligns Action DiT states with their attended video readouts so that the retrieved world information is retained in the representations used for planning. Third, it shapes the action space using geometrically close yet low-scoring hard negatives to separate the expert trajectory from nearby unsafe alternatives. ReWorld constructs supervision entirely from the WAM's own generation targets and attended features, requiring no external encoders or teacher models and introducing only 0.3% additional per-step training cost. Experiments show that ReWorld reduces FVD from 81.3 to 61.9 on nuScenes, improves closed-loop PDMS from 89.1 to 90.4 on NAVSIM without reinforcement learning or test-time scoring, and increases frozen linear-probe accuracy from 68.3% to 80.2% on UCF-101 action recognition. These results indicate that explicitly optimized representations are central to translating world knowledge into planning capability in WAMs.
Yuan Zhang, Jingfei Ni, Guanchen Lu +12cs.AI cs.CV
General-purpose embodied agents must understand multimodal instructions, anticipate how their environment will evolve, and produce precise control actions over extended horizons. Existing approaches typically specialize in visual-language reasoning, video-based world modeling, or action generation, while cascaded pipelines that first synthesize future observations and then infer actions can introduce interface bottlenecks and compound prediction errors. We present iFLYTEK-Embodied-Omni, a unified multimodal foundation model that jointly models vision(videos and images), language, and action within a single Omni framework. Its modality-specific visual-language, video-generation, and action-generation components communicate through shared multimodal self-attention. This design establishes brain-cerebellum collaboration: the vision-language modeland video generation model form a high-level brain for instruction understanding, task planning, progress tracking, and future visual-state prediction, whereas the action generation modelserves as a low-level cerebellum that directly converts planned subgoals and shared multimodal context into executable action chunks. To develop these capabilities, we combine action-annotated and action-free embodied videos from human demonstrations and robot interactions with embodied reasoning, embodied perception, and general-purpose image-text data to construct a comprehensive dataset. We further adopt a four-stage strategy that progressively trains the VLM, VGM, and AGM before jointly fine-tuning the complete model.
Jianing Guo, Fangzheng Chen, Zihao Mao +12cs.RO cs.AI
Flow matching has emerged as a standard paradigm for robotic manipulation owing to its strong expressive power for modelling complex, multimodal action distributions, alongside similar approaches like diffusion policy. However, existing methods rely on discretized action chunks, making them brittle to demonstrations collected at heterogeneous control frequencies and prone to temporally inconsistent actions that degrade control stability. In this paper, we propose Frequency-Aware Flow Matching (FAFM), which outputs continuous, temporally consistent actions. To handle heterogeneous frequency input, we transform discrete action sequences into the frequency domain with the discrete cosine transform (DCT), perform flow matching over the resulting coefficients, and reconstruct continuous actions via cosine basis expansion. To generate temporally consistent actions, we regularize the first-order temporal derivative to promote smooth actions. This corresponds to a Sobolev-type constraint that suppresses high-frequency errors and discourages abrupt action changes. Our FAFM is simple, introduces no additional network parameters and applies to standalone flow-matching policies and vision-language action models. Across synthetic toy benchmark, obstacle avoidance, LapGym, and LIBERO, FAFM improves success rates, multimodal expressivity, motion smoothness, convergence speed, robustness to mechanical bias and mixed-frequency input. These gains are consistent when deployed on a real-world Franka robot. Code available at https://anonymous.4open.science/r/FAFM.
Discrete Vision-Language-Action (VLA) models typically formulate action generation as next-token prediction over discretized action spaces, conditioning each token autoregressively on prior context. While effective, this paradigm incurs high inference latency and largely ignores the temporal structure inherent in action trajectories. Recent efforts introduce parallel decoding to improve efficiency, enabling faster inference, but lack explicit mechanisms for modeling token dependencies. We introduce TBD-VLA, a discrete token-based VLA framework that incorporates block diffusion to enable temporal action generation. We partition action sequences into temporal blocks and perform masked discrete diffusion within each block, while maintaining autoregressive generation across blocks. This design unifies temporal autoregression and parallel action decoding, achieving both strong temporal coherence and improved inference speed. In addition, the explicit temporal modeling enables asynchronous execution of action chunks (e.g., Real-Time Chunking) via temporal in-painting. TBD-VLA significantly outperforms prior VLA approaches in both simulation and real-world manipulation tasks, offering a scalable path toward fast, temporally aware, discrete VLA models. Project webpage: https://tbd-vla.github.io/
Yitong Chen, Shiduo Zhang, Jingjing Gong +1cs.CV cs.AI cs.LG cs.RO
Generating diverse images from sparse text is hard; generating compact actions from rich observations is easier. From the condition-target view, Vision-Language-Action (VLA) thus aligns with image-to-text, not text-to-image. We formalize this view through the irreducible velocity loss $R_v(t,c)$ of standard flow matching and validate it with a controlled 8-mode toy experiment and image-to-text MNIST task. We then show that high-noise training boosts one-step VLA decoding on standard LIBERO, achieving 95.6% on LIBERO-Long, and remains competitive across LIBERO-Plus, LIBERO-Pro, and real-world robot tasks, while ablations that weaken the condition or expand the horizon predictably erase the one-step gain. These results suggest that whether one-step action generation works in VLA depends not on specialized training, but on the condition-target structure.
Recent world action models leverage video foundation models by aligning broad visual-dynamics priors with executable robot actions. We revisit this alignment from a distributional perspective. Existing formulations typically narrow the aligned prior into an observation-conditioned policy distribution over future actions. In contrast, we keep the distribution broader by modeling the joint space of interaction videos and executable hand trajectories under multiple conditioning regimes. We propose Donk, a unified video-action denoising model for dexterous hands. With language, an initial image, and the initial hand state, Donk samples future videos and bimanual MANO trajectories as an action policy. Without the image condition, the same denoising architecture samples paired video-action rollouts from a text-conditioned distribution, turning the aligned video prior into a data engine. Across action, video, and text-only generation evaluations, Donk improves dexterous trajectory accuracy, preserves strong video fidelity, and produces smooth text-conditioned action rollouts under the same unified training recipe.
Flow-based vision-language-action (VLA) policies offer strong expressivity for action generation, but suffer from a fundamental inefficiency: multi-step inference is required to recover action structure from uninformative Gaussian noise, leading to a poor efficiency-quality trade-off under real-time constraints. We address this issue by rethinking the role of the starting point in generative action modeling. Instead of shortening the sampling trajectory, we propose CF-VLA, a coarse-to-fine two-stage formulation that restructures action generation into a coarse initialization step that constructs an action-aware starting point, followed by a single-step local refinement that corrects residual errors. Concretely, the coarse stage learns a conditional posterior over endpoint velocity to transform Gaussian noise into a structured initialization, while the fine stage performs a fixed-time refinement from this initialization. To stabilize training, we introduce a stepwise strategy that first learns a controlled coarse predictor and then performs joint optimization. Experiments on CALVIN and LIBERO show that our method establishes a strong efficiency-performance frontier under low-NFE (Number of Function Evaluations) regimes: it consistently outperforms existing NFE=2 methods, matches or surpasses the NFE=10 $π_{0.5}$ baseline on several metrics, reduces action sampling latency by 75.4\%, and achieves the best average real-robot success rate of 83.0\%, outperforming MIP by 19.5 points and $π_{0.5}$ by 4.0 points. These results suggest that structured, coarse-to-fine generation enables both strong performance and efficient inference. Our code is available at https://github.com/EmbodiedAI-RoboTron/CF-VLA.