AI Paper Atlas

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

TRM-VLA: Temporal-Aware Chain-of-Thought Reasoning and Memorization for Vision-Language-Action Models

Xiang Li, Ya-Li Li, Yuan Wang, Shengjin Wang

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models

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 keyframe-triggered reasoning (KTR) (ablation)TRM-VLA (CogACT backbone) · SimplerEnv-Bridgeavg success rate: 0.54 -> 0.65Improved
add granularity-adaptable context memory (GCM) on top of KTR (ablation)TRM-VLA · SimplerEnv-Bridgeavg success rate: 0.65 -> 0.73Improved
add stage-wise temporal structuring within KTR (ablation)TRM-VLA · SimplerEnv-Bridgeavg success rate: 0.54 -> 0.60Improved
add keyframe-based annotation within KTR (with STS) (ablation)TRM-VLA · SimplerEnv-Bridgeavg success rate: 0.60 -> 0.65Improved
add temporal reasoning integration (cross-attention retrieval) to GCM (ablation)TRM-VLA · SimplerEnv-Bridgeavg success rate: 0.70 -> 0.73Improved
add dynamic reasoning context buffer to GCM (ablation)TRM-VLA · SimplerEnv-Bridgeavg success rate: 0.69 -> 0.73Improved
add KTR on real-world tasks (ablation)TRM-VLA · Real-world (4 tasks)avg success rate: 0.50 -> 0.59Improved
add GCM on real-world tasks (ablation)TRM-VLA · Real-world (4 tasks)avg success rate: 0.59 -> 0.69Improved
add GCM on Push Buttons in Order and Place Bear (ablation)TRM-VLA with KTR · Real-world Push Buttonsuccess rate: 0.45 -> 0.6Improved
trigger CoT only at keyframes instead of full CoT every stepTRM-VLA vs CogACT-ECoT · Real-world tasksCoT tokens per step: 26.3 -> 4.3Improved
add full per-step CoT (ECoT) to CogACT-BaseCogACT-Base · Real-world tasksavg success rate (%): 50.0 -> 44.0Hurt
add full per-step CoT (ECoT) to CogACT-BaseCogACT-Base · LIBERO-90success rate (%): 88.4 -> 92.1Improved

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