Pith. sign in

REVIEW 8 cited by

Vision-Language Models as Success Detectors

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 2303.07280 v1 pith:5MQZFVEF submitted 2023-03-13 cs.CV cs.AIcs.LG

classification cs.CVcs.AIcs.LG
keywords successdetectionmodelsrewardagentshumanrealvideos
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Detecting successful behaviour is crucial for training intelligent agents. As such, generalisable reward models are a prerequisite for agents that can learn to generalise their behaviour. In this work we focus on developing robust success detectors that leverage large, pretrained vision-language models (Flamingo, Alayrac et al. (2022)) and human reward annotations. Concretely, we treat success detection as a visual question answering (VQA) problem, denoted SuccessVQA. We study success detection across three vastly different domains: (i) interactive language-conditioned agents in a simulated household, (ii) real world robotic manipulation, and (iii) "in-the-wild" human egocentric videos. We investigate the generalisation properties of a Flamingo-based success detection model across unseen language and visual changes in the first two domains, and find that the proposed method is able to outperform bespoke reward models in out-of-distribution test scenarios with either variation. In the last domain of "in-the-wild" human videos, we show that success detection on unseen real videos presents an even more challenging generalisation task warranting future work. We hope our initial results encourage further work in real world success detection and reward modelling.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 11 citations worldwide. Full citation record

  1. SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning

    cs.RO 2026-03 conditional novelty 6.5 of 10

    A video-language model with per-timestep spatiotemporal CoT and dense progress prediction can serve as the sole reward for zero-shot online robot RL on 24 unseen manipulation tasks.

  2. LabRobFail: A Benchmark for Robotic Failure Analysis in Chemical Self-driving Laboratory

    cs.RO 2026-07 conditional novelty 6.0 of 10

    A chemical-lab failure sim, 20K-trajectory dataset, six-axis benchmark, and specialized VLM raise failure detection to 90.8% on seen scenes and lift downstream policy success by 4–16 points.

  3. Tactile Modality Fusion for Vision-Language-Action Models

    cs.RO 2026-03 conditional novelty 6.0 of 10

    A FiLM-based tactile fusion method that conditions VLA visual features on frozen pretrained touch embeddings improves real-robot insertion success, speed, and force control relative to vision-only and concatenation baselines.

  4. RoboStream: Weaving Spatio-Temporal Reasoning with Memory in Vision-Language Models for Robotics

    cs.RO 2026-03 conditional novelty 6.0 of 10

    Training-free STF-Tokens plus a Causal Spatio-Temporal Graph let VLMs keep object permanence and action history, raising long-horizon robotic manipulation success far above reactive baselines.

  5. TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics

    cs.RO 2026-02 conditional novelty 6.0 of 10

    The log-probability a VLM assigns to 'True' for 'does this video prefix complete the task?' is used as a zero-shot dense progress reward that outperforms GVL on open-source models.

  6. Reward Evolution with Graph-of-Thoughts: A Bi-Level Language Model Framework for Reinforcement Learning

    cs.RO 2025-09 conditional novelty 5.0 of 10

    RE-GoT combines graph-of-thoughts planning in LLMs with VLM feedback from rollout videos to automatically write and refine RL reward functions, beating prior LLM-based reward design on RoboGen and ManiSkill2.

  7. RoboPearls: Editable Video Simulation for Robot Manipulation

    cs.CV 2025-06 conditional novelty 5.0 of 10

    RoboPearls is a 3D Gaussian Splatting based framework that edits demonstration videos into varied photorealistic simulations, and training on them improves robot manipulation success rates on RLBench and COLOSSEUM.

  8. Foundation Model Driven Robotics: A Comprehensive Review

    cs.RO 2025-07 conditional novelty 2.0 of 10

    A review of foundation-model-driven robotics that synthesizes recent work across perception, planning, control, HRI, simulation, and sim-to-real transfer, and highlights open challenges.

Pith tools