Can LLMs Debug Robots by Editing Their Weights?
cs.RO, cs.AI
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
- LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
- LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization
- LIBERO-RECOVER: Beyond Task Success Towards Failure Recovery in Robotic Manipulation Models
- Sigmoid Loss for Language Image Pre-Training
- PaliGemma: A versatile 3B VLM for transfer
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- OpenVLA: An Open-Source Vision-Language-Action Model
- Octo: An Open-Source Generalist Robot Policy
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
- Flow Matching for Generative Modeling
- World Action Models are Zero-shot Policies
- E0.5: From Reconstructive to Future-Predictive 3D Foundations for Robotic World-Action Modeling
- Locating and Editing Factual Associations in GPT
- Mass-Editing Memory in a Transformer
- Fast Model Editing at Scale
- LEACE: Perfect linear concept erasure in closed form
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation