AI Paper Atlas

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

Contrastive Representation Regularization for Vision-Language-Action Models

Taeyoung Kim, Jimin Lee, Myungkyu Koo, Dongyoung Kim, Kyungmin Lee, Changyeon Kim, Younggyo Seo, Jinwoo Shin

ICML 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 0 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
Add RS-CL regularization to GR00T N1.5GR00T N1.5 · RoboCasa-Kitchen (300 demos)success rate (%): 65.7 -> 69.7Improved
Add RS-CL to GR00T N1.5GR00T N1.5 · LIBERO averagesuccess rate (%): 95.7 -> 96.4Improved
Add RS-CL to GR00T N1.5GR00T N1.5 · LIBERO Objectsuccess rate (%): 99.4 -> 98.6Hurt
Add RS-CL to GR00T N1.5GR00T N1.5 · RoboCasa-Kitchen pick-and-place taskssuccess rate (%): 30.3% to 41.5% (+11.2%)Improved
Add RS-CL to GR00T N1.5GR00T N1.5 · RoboCasa-Kitchen open-and-close (30 demos)success rate (%): 71.3 -> 70.0No clear effect
Add RS-CL to GR00T N1.5GR00T N1.5 · Real-robot taskssuccess rate (%): 45.0% to 58.3% (+13.3%)Improved
Use RS-CL instead of single-view TCN auxiliary lossGR00T N1.5 · RoboCasa-Kitchen (30 demos)success rate (%): 50.3 -> 53.0Improved
Use RS-CL instead of TCN regarding computeGR00T N1.5 · RoboCasa-Kitchen (30 demos)FLOPs (x10^12): 7.53 -> 2.91Improved
Add contrastive regularization (InfoNCE) without soft labels (ablation)GR00T N1.5 · RoboCasa-Kitchen (300 demos)success rate (%): 65.7 -> 67.3Improved
Use current-state distance soft labels instead of InfoNCE (ablation)RS-CL · RoboCasa-Kitchen (300 demos)success rate (%): 67.3 -> 69.7Improved
Use next action sequence distance instead of state distance as soft-label target (ablation)RS-CL · RoboCasa-Kitchen (300 demos)success rate (%): 69.7 -> 66.7Hurt
Add view cutoff augmentation instead of no augmentation (ablation)RS-CL · RoboCasa-Kitchen (300 demos)success rate (%): 65.3 -> 69.7Improved

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