AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

Diagnose, Correct, and Learn from Manipulation Failures via Visual Symbols

Xianchao Zeng, Xinyu Zhou, Youcheng Li, Jiayou Shi, Tianle Li, Liangming Chen, Lei Ren, Yong-Lu Li

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune on ViFailback dataset (LoRA, 1 epoch) (ablation)Qwen3-VL-8B · ViFailback-Bench Liteaccuracy (%): 38.33 -> 93.70Improved
fine-tune on ViFailback dataset (ablation)Qwen3-VL-8B · ViFailback-Bench Hardscore (%): 33.04 -> 72.64Improved
increase training trajectories from 1,200 to 4,702 (ablation)Qwen3-VL-8B · ViFailback-Benchaccuracy (%)Improved
increase training data on visual symbol code generation (ablation)Qwen3-VL-8B · Generating Visual Symbols' Codesaccuracy (%): up to 38.73Improved
scale model size within Qwen2.5-VL (3B to 72B)Qwen2.5-VL · ViFailback-Bench Liteaccuracy (%): 38.10 -> 50.61Improved
scale Qwen3-VL from 8B to 32BQwen3-VL · ViFailback-Bench Liteaccuracy (%): 38.33 -> 47.79Improved
add ViFailback-8B correction with visual symbols following data (VSF)pi0.5 (base & symbol) · real-world manipulationsuccess rate (%): 52.4% -> 73.0%Improved
add ViFailback-8B correction with point-based motion control (PMC)pi0.5 (base) · real-world manipulationsuccess rate (%): 50.8% -> 74.6%Improved
add visual symbol-following data to pi0.5 fine-tuning without correction (ablation)pi0.5 · real-world manipulationsuccess rate (%): 50.8% -> 52.4%No clear effect
PMC instead of VSF for executing guidance (ablation)ViFailback-8B system · real-world manipulationsuccess rate (%): 73.0% -> 74.6%Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy