mlsanityData to 14 Oct 2026

Igniting VLMs toward the Embodied Space

arXiv 2509.11766 ↗First posted 15 Sep 2025cs.ROcited by 53

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

Abstract (arXiv)

While foundation models show remarkable progress in language and vision, existing vision-language models (VLMs) still have limited spatial and embodiment understanding. Transferring VLMs to embodied domains reveals fundamental mismatches between modalities, pretraining distributions, and training objectives, leaving action comprehension and generation as a central bottleneck on the path to AGI. We introduce WALL-OSS, an end-to-end embodied foundation model that leverages large-scale multimodal pretraining to achieve (1) embodiment-aware vision-language understanding, (2) strong language-action association, and (3) robust manipulation capability. Our approach employs a tightly coupled architecture and multi-strategies training curriculum that enables Unified Cross-Level CoT-seamlessly unifying instruction reasoning, subgoal decomposition, and fine-grained action synthesis within a single differentiable framework. Our results show that WALL-OSS attains high success on complex long-horizon manipulations, demonstrates strong instruction-following capabilities, complex understanding and reasoning, and outperforms strong baselines, thereby providing a reliable and scalable path from VLMs to embodied foundation models.

Key facts. Cited by 53 papers in the map (data through 14 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. First posted on arXiv 15 Sep 2025.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 12; 2026: 41.

53 papers.

Sort:

By area:

  1. 2026Cosmos 3: Omnimodal World Models for Physical AIcited by 165
  2. 2026A Pragmatic VLA Foundation Modelcited by 103
  3. 2026Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalizationcited by 66
  4. 2025InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policycited by 50
  5. 2026InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulationcited by 50
  6. 2025GigaBrain-0: A World Model-Powered Vision-Language-Action Modelcited by 44
  7. 2026Native Video-Action Pretraining for Generalizable Robot Controlcited by 36
  8. 2026StarVLA-α: Reducing Complexity in Vision-Language-Action Systemscited by 31
  9. 2026From Foundation to Application: Improving VLA Models in Practicecited by 26
  10. 2026GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learningcited by 24
  11. 2025A Survey on Agentic Multimodal Large Language Modelscited by 23
  12. 2026A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulationcited by 22
38 more
  1. 2025Mixture of Horizons in Action Chunkingcited by 21
  2. 2026G0.5: One Autoregressive Stream for Robot Reasoning and Actioncited by 18
  3. 2025AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Modelscited by 17
  4. 2026FAVLA: A Force-Adaptive Fast-Slow VLA model for Contact-Rich Robotic Manipulationcited by 15
  5. 2026TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformerscited by 14
  6. 2025MM-ACT: Learn from Multimodal Parallel Generation to Actcited by 12
  7. 2026Wall-OSS-0.5 Technical Reportcited by 12
  8. 2026GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearchcited by 11
  9. 2025UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Drivingcited by 10
  10. 2026RoboStereo: Dual-Tower 4D Embodied World Models for Unified Policy Optimizationcited by 10
  11. 2025Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Compositioncited by 9
  12. 2025MIND-V: Hierarchical World Model for Long-Horizon Robotic Manipulation with RL-based Physical Alignmentcited by 9
  13. 2026PRTS: A Primitive Reasoning and Tasking System via Contrastive Representationscited by 9
  14. 2026DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulationcited by 9
  15. 2026ForeAct: Steering Your VLA with Efficient Visual Foresight Planningcited by 8
  16. 2026SpatialVAM:Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot Policycited by 8
  17. 2026Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervisioncited by 8
  18. 2025Asynchronous Fast-Slow Vision-Language-Action Policies for Whole-Body Robotic Manipulationcited by 7
  19. 2026X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretrainingcited by 7
  20. 2026VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesiscited by 6
  21. 2026NativeMEM: Native Memory Compression for Long-Horizon Robotic Manipulationcited by 6
  22. 2026The Great March 100: 100 Detail-oriented Tasks for Evaluating Embodied AI Agentscited by 5
  23. 2026IG-RFT: An Interaction-Guided RL Framework for VLA Models in Long-Horizon Robotic Manipulationcited by 5
  24. 2026OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelismcited by 4
  25. 2026Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Actioncited by 4
  26. 2025Dejavu: Towards Experience Feedback Learning for Embodied Intelligencecited by 3
  27. 2026Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoningcited by 3
  28. 2026OpenWorldLib: A Unified Codebase and Definition of Advanced World Modelscited by 3
  29. 2026LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratoriescited by 3
  30. 2025Metis-HOME: Hybrid Optimized Mixture-of-Experts for Multimodal Reasoningcited by 2
  31. 2026From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulationcited by 2
  32. 2026HarvestFlex: Strawberry Harvesting via Vision-Language-Action Policy Adaptation in the Wildcited by 1
  33. 2026E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulationcited by 1
  34. 2026AeroGround: A Comprehensive Benchmark for Aerial-Ground Collaborative Reasoningcited by 1
  35. 2026SUN: Agentic Robot Policy Learning with Persistent Task Programscited by 1
  36. 2026TRACER: Texture-Robust Affordance Chain-of-Thought for Deformable-Object Refinementcited by 0
  37. 2026PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulationcited by 0
  38. 2026Scaling by Diversified Experience for Vision-Language-Action Modelscited by 0

50 most cited of 53 All 53 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025BLM1: A Boundless Large Model for Cross-Space, Cross-Task, and Cross-Embodiment Learning
  2. 2025From Grounding to Manipulation: Case Studies of Foundation Model Integration in Embodied Robotic Systems
  3. 2026EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training
  4. 2025InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation
  5. 2026Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines
  6. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey
  7. 2026How Foundational Skills Influence VLM-based Embodied Agents:A Native Perspective
  8. 2026Guava: Distilling Frontier VLMs into a Compact Agent through a Robotic Manipulation Harness