Pith. sign in

REVIEW 19 cited by

Yell At Your Robot: Improving On-the-Fly from Language Corrections

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.12910 v1 pith:ELOZOK6E submitted 2024-03-19 cs.RO cs.AIcs.LG

Yell At Your Robot: Improving On-the-Fly from Language Corrections

classification cs.RO cs.AIcs.LG
keywords feedbackhigh-levellanguagecorrectionslong-horizonlow-levelpoliciesrobot
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Hierarchical policies that combine language and low-level control have been shown to perform impressively long-horizon robotic tasks, by leveraging either zero-shot high-level planners like pretrained language and vision-language models (LLMs/VLMs) or models trained on annotated robotic demonstrations. However, for complex and dexterous skills, attaining high success rates on long-horizon tasks still represents a major challenge -- the longer the task is, the more likely it is that some stage will fail. Can humans help the robot to continuously improve its long-horizon task performance through intuitive and natural feedback? In this paper, we make the following observation: high-level policies that index into sufficiently rich and expressive low-level language-conditioned skills can be readily supervised with human feedback in the form of language corrections. We show that even fine-grained corrections, such as small movements ("move a bit to the left"), can be effectively incorporated into high-level policies, and that such corrections can be readily obtained from humans observing the robot and making occasional suggestions. This framework enables robots not only to rapidly adapt to real-time language feedback, but also incorporate this feedback into an iterative training scheme that improves the high-level policy's ability to correct errors in both low-level execution and high-level decision-making purely from verbal feedback. Our evaluation on real hardware shows that this leads to significant performance improvement in long-horizon, dexterous manipulation tasks without the need for any additional teleoperation. Videos and code are available at https://yay-robot.github.io/.

discussion (0)

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

Forward citations

Cited by 19 Pith papers

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

  1. Adapting Generalist Robot Policies with Semantic Reinforcement Learning

    cs.RO 2026-06 unverdicted novelty 7.0

    SARL optimizes language prompt inputs to generalist vision-language-action policies through online RL to solve complex long-horizon tasks by composing existing skills.

  2. Zero2Skill: Bootstrapping Robot Skills through Autonomous Data Collection, Training, and Deployment

    cs.RO 2026-07 conditional novelty 6.0

    Corrective Memory lets a robot data collector reuse natural-language corrections across rounds, cutting human time to 16% of teleoperation while matching its success rate and downstream policy performance.

  3. Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering

    cs.RO 2026-06 unverdicted novelty 6.0

    A search-and-distill framework with conformalized improvement head produces a language feedback policy that boosts frozen VLA performance by 24.7% in simulation and 65% on hardware while guaranteeing harmlessness on p...

  4. Learning to Assist: Collaborative VLAs for Implicit Human-Robot Collaboration

    cs.RO 2026-06 conditional novelty 6.0

    VLA models with inference-time steering mitigate action leakage in implicit human-robot collaboration, supporting longer horizons and yielding faster, more reliable assembly than shorter-horizon baselines in a 16-pers...

  5. EgoPriMo: Egocentric Motion Generation for Interactive Humanoid Control

    cs.RO 2026-06 unverdicted novelty 6.0

    EgoPriMo learns a unified egocentric motion prior with a Triple-stream DiT model that supports reconstruction, generation, and forecasting of SMPL motions from egocentric views and text, outperforming prior methods an...

  6. Flow-based Policy Adaptation without Policy Updates

    cs.RO 2026-06 unverdicted novelty 6.0

    GLOVES learns flow models from limited expert demonstrations to selectively correct actions from non-expert policies or operators toward expert distributions using reverse-flow OOD detection as an intervention gate.

  7. Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning

    cs.AI 2026-05 unverdicted novelty 6.0

    MAVIC corrects Bellman backups at instruction boundaries by adjusting the incoming objective and restoring continuation value, enabling consistent estimation under stochastic instruction switching in a unified policy.

  8. Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning

    cs.AI 2026-05 unverdicted novelty 6.0

    MAVIC corrects Bellman backups at instruction boundaries by adjusting the incoming objective and restoring continuation value, enabling consistent estimation under stochastic instruction switching in cooperative MARL.

  9. RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models

    cs.RO 2026-05 unverdicted novelty 6.0

    RePO-VLA raises average adversarial success rates in VLA manipulation from 20% to 75% by using recovery-aware initialization, a progress-aware semantic value function, and value-conditioned refinement on success and c...

  10. Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models

    cs.RO 2026-05 unverdicted novelty 6.0

    AFIL improves VLA policy robustness by jointly training success and failure generators on online-generated failure trajectories and using adaptive guidance to avoid failure modes during action sampling.

  11. $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization

    cs.LG 2025-04 unverdicted novelty 6.0

    π_{0.5} is a VLA model that achieves long-horizon dexterous manipulation in entirely new homes through co-training on heterogeneous tasks and multi-source data including web and semantic predictions.

  12. Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

    cs.RO 2025-02 accept novelty 6.0

    OpenVLA-OFT fine-tuning boosts LIBERO success rate from 76.5% to 97.1%, speeds action generation 26x, and outperforms baselines on real bimanual dexterous tasks.

  13. Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models

    cs.RO 2025-02 unverdicted novelty 6.0

    A hierarchical VLA architecture lets robots follow complex instructions and situated feedback by separating high-level reasoning from low-level control.

  14. DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control

    cs.RO 2025-02 unverdicted novelty 6.0

    DexVLA combines a scaled diffusion action expert with embodiment curriculum learning to achieve better generalization and performance than prior VLA models on diverse robot hardware and long-horizon tasks.

  15. A Few Words Go a Long Way: Language Guided Robot Policy Synthesis

    cs.RO 2026-07 conditional novelty 5.0

    Interactive LLM program synthesis plus a persistent skill library from natural-language corrections outperforms zero-shot VLAs and one-shot code policies on complex real-robot manipulation.

  16. DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization

    cs.RO 2026-05 unverdicted novelty 5.0

    DyGRO-VLA is a two-stage optimization framework for cross-task scaling of Vision-Language-Action models via dynamic grouped residual optimization in RL.

  17. Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models

    cs.RO 2026-05 unverdicted novelty 5.0

    AFIL trains dual action generators on success and failure rollouts from a pretrained VLA to steer diffusion policies away from failure modes during inference.

  18. A Survey on Vision-Language-Action Models: An Action Tokenization Perspective

    cs.RO 2025-07 unverdicted novelty 5.0

    The survey frames VLA models as pipelines that generate progressively grounded action tokens and classifies those tokens into eight types to guide future development.

  19. TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation

    cs.RO 2024-09 unverdicted novelty 4.0

    TinyVLA achieves faster inference and higher data efficiency than OpenVLA on robotic manipulation tasks by initializing from high-speed multimodal models and adding a diffusion policy decoder, without any pre-training phase.