The paper argues that diffusion-based action policies can use a frozen, observation‑free backbone as a reusable trajectory prior, with task adaptation handled entirely by the conditioning pathway. By pretraining a general action head on forward‑kinematics data and then freezing it, the authors show that a single backbone can match or outperform normally trained models on MimicGen and LIBERO. Their experiments reveal that a small 5 M‑parameter MLP backbone can rival large U‑Net and transformer backbones, indicating that action backbones are often over‑parameterized and that image‑style architectures may not be the best fit for low‑dimensional action generation.
Diffusion-based vision-language-action (VLA) models often inherit the image-generation view: actions are generated by iterative denoising. We argue that VLA action generation has a different condition-target structure: the policy is conditioned on rich observations, language, and state, but predicts only a compact, low-dimensional action chunk.
arXiv:2606. 05737v1 Announce Type: cross Abstract: Diffusion-based vision-language-action (VLA) models often inherit the image-generation view: actions are generated by iterative denoising.
UniWALM is a unified world-action-language model that jointly learns video, action, and language in a single shared representation, using a mixture-of-transformers backbone with diffusion heads that co-denoise across modalities. By generating language as part of the same pass as action, the model closes a language‑as‑memory loop without an external planner, and introduces Flow Matching with Correction to maintain reliable action streams. Experiments show UniWALM outperforms baselines on compositional pick‑and‑place tasks and memory‑dependent benchmarks, and dramatically improves success on a real‑world Find‑the‑Item task when using generated textual memory.
TAPESTRY repurposes a pretrained video diffusion transformer into a robotic policy by treating robot actions as single-patch tokens in the model’s latent space, eliminating the need for video generation at inference. The lightweight linear projection maps each action timestep to the VAE patch dimensions, and the shared backbone is trained with three diffusion objectives—video diffusion, joint video+action diffusion, and action-only diffusion—to learn dynamics priors and action denoising. At test time, the model produces smooth action chunks in a single DDIM step, achieving strong performance on simulation and real‑robot benchmarks with significantly lower inference cost than comparable joint video–action policies.
MT‑WAM enhances the Fast‑WAM framework by adding complementary supervision for future 2‑D point trajectories and visual features while keeping the original training objectives. A lightweight dual‑stream branch and structured attention mask isolate motion‑specific processing, and motion‑stream tokens provide additional dynamics cues to the action expert. During inference, MT‑WAM skips future‑video prediction, using cached video and motion information to achieve higher success rates on LIBERO, LIBERO‑Plus, RoboTwin 2.0 Clean2Rand, and several real‑world tasks.
The paper introduces the Just Action Model (JAM), a framework that decouples backbone initialization, future observation objectives, and inference machinery to unify vision-language-action (VLA) and world-action model (WAM) approaches. JAM employs a pretrained visual backbone, an action expert, an action loss, and a foresight loss that predicts future encodings without visual generation, discarding the prediction head after training. Experiments show JAM outperforms FastWAM and ImageWAM on LIBERO, LIBERO-Plus, and RoboTwin, while reducing online training FLOPs by 73%.
arXiv:2609.27455v1 Announce Type: new Abstract: World Action Models (WAMs) jointly model action generation and environment dynamics and are mostly built on pretrained Video Diffusion Models (VDMs). I...
Dynin‑Robotics introduces an omnimodal masked‑diffusion backbone, Dynin‑Omni, that jointly represents language, visual observations, goals, and actions as discrete tokens. By conditioning on different spans, the same model learns action prediction, next‑observation prediction, goal‑state prediction, and trajectory‑to‑instruction reconstruction, enabling test‑time scaling through goal prediction and action‑candidate evaluation. The system, pretrained on 1.33 million trajectories from 48 Open X‑Embodiment datasets, achieves competitive performance on LIBERO, zero‑shot LIBERO‑Plus, and a 78.4 % success rate on a Franka Research 3 robot, while a block‑parallel implementation speeds up action decoding by up to 29.2×.
arXiv:2610.08183v1 Announce Type: cross Abstract: Multi-task manipulation policies differ in architecture, scale, and pretrained priors all at once, so published comparisons cannot attribute performa...
arXiv:2607. 27138v1 Announce Type: cross Abstract: Vision-language-action (VLA) models remain constrained by scarce action-labeled robot data, whereas action-free videos offer abundant observations of physical change.
arXiv:2609.37250v1 Announce Type: cross Abstract: World-action models (WAMs) couple future visual-state prediction with action generation. By adapting video generators or image-editing models pretrai...
arXiv:2610.02323v1 Announce Type: cross Abstract: Flow-based Vision-Language-Action (VLA) policies generate action chunks by transporting samples from a task-agnostic isotropic Gaussian source. As th...