AI Paper Atlas

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

PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation

Yuanzhe Liu, Jingyuan Zhu, Yuchen Mo, Gen Li, Xu Cao, Jin Jin, Yifan Shen, Zhengyuan Li, Tianjiao Yu, Wenzhen Yuan, Fangqiang Ding, Ismini Lourentzou

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Multimodal prompt-driven manipulation · 38 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 progress prediction (ablation)PALM · CALVIN ABC->Daverage length: 4.02 -> 4.48Improved
add affordance foresight prediction (ablation)PALM (fine-tuning) · CALVIN ABC->Daverage length: 3.58 -> 4.48Improved
add progress prediction during pre-training (ablation)PALM (pre-training) · CALVIN ABC->Daverage length: 3.73 -> 4.48Improved
add inverse dynamics prediction (ablation)PALM · CALVIN ABC->Daverage length: 3.92 -> 4.48 (fine-tuning); 4.17 -> 4.48 (pre-training)Improved
add Global affordance to vanilla VLA (ablation)vanilla VLA · LIBERO-Longsuccess rate: 77.0 -> 84.0Improved
add Local affordance on top of Global (ablation)VLA + Global · CALVIN ABC->D / LIBERO-Longaverage length / success rate: CALVIN 3.96 -> 4.16; LIBERO-Long 84.0 -> 82.5Mixed
add Spatial affordance on top of Global and Local (ablation)VLA + Global + Local · LIBERO-Longsuccess rate: 82.5 -> 86.5Improved
add Dynamic affordance to complete set (ablation)VLA + G,L,S · LIBERO-Longsuccess rate: 86.5 -> 91.8Improved
include in-the-wild robot data (DROID, BridgeData V2) in pre-training (ablation)PALM · LIBERO-Longsuccess rate: 73.5 -> 91.8Improved
include long-horizon video data in pre-training (ablation)PALM · CALVIN ABC->Daverage length: 3.73 -> 4.48Improved
include human-annotated fine-tuning data (ablation)PALM · CALVIN ABC->Daverage length: 3.58 -> 4.48Improved
include simulation benchmark pre-training data (ablation)PALM · CALVIN ABC->Daverage length: 3.96 -> 4.48Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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