The reviewed record of science sign in
Pith

arxiv: 2210.03094 · v2 · pith:FTLKW655 · submitted 2022-10-06 · cs.RO · cs.AI· cs.LG

VIMA: General Robot Manipulation with Multimodal Prompts

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:FTLKW655record.jsonopen to challenge →

classification cs.RO cs.AIcs.LG
keywords promptsvimadatalanguagemultimodalrobottasktasks
0
0 comments X
read the original abstract

Prompt-based learning has emerged as a successful paradigm in natural language processing, where a single general-purpose language model can be instructed to perform any task specified by input prompts. Yet task specification in robotics comes in various forms, such as imitating one-shot demonstrations, following language instructions, and reaching visual goals. They are often considered different tasks and tackled by specialized models. We show that a wide spectrum of robot manipulation tasks can be expressed with multimodal prompts, interleaving textual and visual tokens. Accordingly, we develop a new simulation benchmark that consists of thousands of procedurally-generated tabletop tasks with multimodal prompts, 600K+ expert trajectories for imitation learning, and a four-level evaluation protocol for systematic generalization. We design a transformer-based robot agent, VIMA, that processes these prompts and outputs motor actions autoregressively. VIMA features a recipe that achieves strong model scalability and data efficiency. It outperforms alternative designs in the hardest zero-shot generalization setting by up to $2.9\times$ task success rate given the same training data. With $10\times$ less training data, VIMA still performs $2.7\times$ better than the best competing variant. Code and video demos are available at https://vimalabs.github.io/

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 28 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Robotic Policy Adaptation via Weight-Space Meta-Learning

    cs.RO 2026-06 unverdicted novelty 7.0

    WIZARD meta-learns to map task evidence directly to LoRA updates for VLA policies, reporting up to 14x gains on unseen tasks in simulation and real-robot experiments without test-time optimization or action labels.

  2. Colosseum V2: Benchmarking Generalization for Vision Language Action Models

    cs.RO 2026-05 unverdicted novelty 7.0

    Introduces Colosseum V2 benchmark for evaluating VLA model generalization in robotic manipulation with 28 tasks, revealing limitations in current methods and sim-real correlations.

  3. OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation

    cs.RO 2026-05 unverdicted novelty 7.0

    OA-WAM uses persistent address vectors and dynamic content vectors in object slots to enable addressable world-action prediction, improving robustness on manipulation benchmarks under scene changes.

  4. Beyond Monotonic Progress: Retry-Supervised Value Learning for Robot Imitation

    cs.RO 2026-06 unverdicted novelty 6.0

    ReTVL uses retry events as sparse supervision to train mistake-sensitive value functions that reweight demonstration chunks for improved behavior cloning on real-robot manipulation tasks.

  5. Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation

    cs.CV 2026-06 unverdicted novelty 6.0

    Qwen-RobotWorld is a language-conditioned video world model using Double-Stream MMDiT, an 8.6M-frame embodied corpus, and progressive curriculum training that ranks first on EWMBench and DreamGen Bench.

  6. Efficient Skill Grounding via Code Refactoring with Small Language Models

    cs.AI 2026-06 unverdicted novelty 6.0

    RECENT decouples skill semantics from embodiment-specific bindings via code refactoring to let small language models achieve skill grounding performance matching large language model baselines.

  7. TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies

    cs.RO 2026-06 unverdicted novelty 6.0

    TempoVLA learns a single VLA policy with controllable execution speed via variable-speed trajectory augmentation and explicit speed conditioning.

  8. LLM-Guided Future Hypotheses for Horizon-Aware Exploration in Multi-Step Robot Manipulation

    cs.RO 2026-05 unverdicted novelty 6.0

    FEC conditions policies on LLM-guided short-horizon future videos via a three-stage pipeline, yielding performance gains for BC+RL over no-future baselines on RoboCasa and CALVIN while mismatched futures degrade results.

  9. PrimitiveVLA: Learning Reusable Motion Primitives for Efficient and Generalizable Robotic Manipulation

    cs.RO 2026-05 unverdicted novelty 6.0

    PrimitiveVLA introduces a primitive-centric framework that disassembles demonstrations into reusable motion primitives during fine-tuning and assembles them at inference via VLM planner and LLM switch for improved dat...

  10. How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning

    cs.RO 2026-05 unverdicted novelty 6.0

    DeMiAn re-annotates robot and egocentric videos with VLM-generated dense labels across motion, scene, pose, and reasoning aspects, then uses a learned instructor to boost policy success by 5 points on RoboCasa over ta...

  11. GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization

    cs.RO 2026-05 unverdicted novelty 6.0

    GuidedVLA improves VLA success rates by manually supervising separate attention heads in the action decoder with auxiliary signals for task-relevant factors.

  12. GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization

    cs.RO 2026-05 unverdicted novelty 6.0

    GuidedVLA improves VLA generalization by supervising individual attention heads with manually defined auxiliary signals for three task-relevant factors.

  13. StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception

    cs.RO 2026-05 unverdicted novelty 6.0

    StereoPolicy fuses stereo image pairs via a Stereo Transformer on pretrained 2D encoders to boost robotic manipulation policies, showing gains over monocular, RGB-D, point cloud, and multi-view methods in simulations ...

  14. DeepFleet: Multi-Agent Foundation Models for Mobile Robots

    cs.RO 2025-08 unverdicted novelty 6.0

    DeepFleet develops and compares four foundation model architectures for multi-agent robot fleet coordination using warehouse data, finding robot-centric and graph-floor models most promising for prediction and scaling.

  15. GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation

    cs.RO 2024-10 unverdicted novelty 6.0

    GR-2 pre-trains on web-scale videos then fine-tunes on robot data to reach 97.7% average success across over 100 manipulation tasks with strong generalization to new scenes and objects.

  16. A Survey on Vision-Language-Action Models for Embodied AI

    cs.RO 2024-05 unverdicted novelty 6.0

    This is the first survey on vision-language-action models, providing a taxonomy across three lines, plus summaries of datasets, simulators, benchmarks, challenges, and future directions in embodied AI.

  17. Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation

    cs.RO 2023-12 conditional novelty 6.0

    A GPT-style model pre-trained on large video datasets achieves 94.9% success on CALVIN multi-task manipulation and 85.4% zero-shot generalization, outperforming prior baselines.

  18. PaLM-E: An Embodied Multimodal Language Model

    cs.LG 2023-03 conditional novelty 6.0

    PaLM-E is a single 562B-parameter multimodal model that performs embodied reasoning tasks like robotic manipulation planning and visual question answering by interleaving vision, state, and text inputs with positive t...

  19. Scaling Robot Learning with Semantically Imagined Experience

    cs.RO 2023-02 unverdicted novelty 6.0

    Augmenting robot datasets via diffusion-based semantic inpainting enables manipulation policies to solve unseen tasks with new objects and improves robustness to novel distractors.

  20. Diagnosing Semantic Handoff Failures in Agent-Orchestrated Vision-Language-Action Skill Composition

    cs.RO 2026-07 conditional novelty 5.0

    Individual VLA robot skills achieving 77–100% success from clean starting states still stall in composed long-horizon rollouts due to semantic handoff failures where terminal states are not valid starting states for t...

  21. Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy

    cs.RO 2026-06 unverdicted novelty 5.0

    OmniAct framework integrates planning, memory, and verification to enable persistent autonomy in omnimodal embodied agents, showing improved success and stable context in 40 real-world tasks.

  22. MagicSim: A Unified Infrastructure for Executable Embodied Interaction

    cs.RO 2026-06 unverdicted novelty 5.0

    MagicSim is a unified embodied interaction infrastructure built on a deterministic batched runtime and shared MDP that supports diverse world construction, execution, task evaluation, automatic rollout generation, and...

  23. World Models for Robotic Manipulation: A Survey

    cs.RO 2026-05 accept novelty 5.0

    Survey organizing world models for robotic manipulation into representation families, a functional taxonomy, and infrastructure roles across pretraining, post-training, and inference, while reviewing 34 datasets and e...

  24. What Matters in Building Vision-Language-Action Models for Generalist Robots

    cs.RO 2024-12 unverdicted novelty 5.0

    Systematic tests of VLM backbones, policy architectures, and cross-embodiment data yield RoboVLMs that set new SOTA on robot manipulation benchmarks while requiring few manual designs.

  25. MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations

    cs.RO 2023-10 unverdicted novelty 5.0

    MimicGen creates over 50K robot demonstrations from roughly 200 human ones, allowing imitation learning to achieve strong performance on complex long-horizon tasks like assembly and coffee preparation.

  26. Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own

    cs.RO 2023-10 unverdicted novelty 5.0

    RLFP and the FAC algorithm combine foundation-model priors for policy, value, and rewards to produce sample-efficient robotic RL that reaches 86% real-robot success after one hour and 100% success on 7/8 Meta-world ta...

  27. World Action Models: The Next Frontier in Embodied AI

    cs.RO 2026-05 unverdicted novelty 4.0

    The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.

  28. StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception

    cs.RO 2026-05 unverdicted novelty 4.0

    StereoPolicy fuses left-right image features via cross-attention to deliver consistent gains over RGB, RGB-D, point cloud, and multi-view baselines in simulation and real-robot manipulation tasks.