AI Paper Atlas

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

HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models

Minghui Lin, Pengxiang Ding, Shu Wang, Zifeng Zhuang, Yang Liu, Xinyang Tong, Wenxuan Song, Shangke Lyu, Siteng Huang, Donglin Wang

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 35 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 HiF-VLA motion hindsight/foresight to OpenVLA-OFT (third-view)OpenVLA-OFT · LIBERO-Long (third-view input)avg success rate (%): 91.0 -> 94.4Improved
add HiF-VLA to OpenVLA-OFT (multi-view)OpenVLA-OFT · LIBERO-Long (multi-view input)avg success rate (%): 94.0 -> 96.4Improved
HiF-VLA vs strongest third-view baseline on CALVINVLA · CALVIN ABC-D (third-view input)avg tasks completed (of 5): 3.80 -> 4.08Improved
add RGB subgoal prediction (ablation)OpenVLA-OFT · LIBERO-Long efficiency ablation (third-view, history length 4, batch size 4)latency (ms): 91.0 -> 91.8 SR; 72.9 -> 115.9 msMixed
add motion foresight head (ablation)OpenVLA-OFT · LIBERO-Long efficiency ablation (third-view, history length 4, batch size 4)avg success rate (%): 91.0 -> 92.2Improved
add raw history frames (ablation)OpenVLA-OFT · LIBERO-Long efficiency ablation (third-view, history length 4, batch size 4)avg success rate (%): 91.0 -> 90.4Hurt
add motion-vector hindsight instead of raw history frames (ablation)OpenVLA-OFT · LIBERO-Long efficiency ablation (third-view, history length 4, batch size 4)avg success rate (%): 90.4 -> 92.2Improved
combine hindsight and foresight (ablation)OpenVLA-OFT · LIBERO-Long efficiency ablation (third-view, history length 4, batch size 4)avg success rate (%): 92.2 -> 93.2Improved
condition hindsight in the expert instead of injecting into the VLM (ablation)HiF-VLA · LIBERO-Long (third-view), hindsight embedding positionsuccess rate (%): 92.8 -> 94.4Improved
increase hindsight length beyond 8 (ablation)HiF-VLA · LIBERO-Long (third-view), hindsight lengthsuccess rate (%): 94.4 -> 93.6 (len 16), 93.4 (len 32)No clear effect
use HiF-VLA vs OpenVLA-OFT on real cover & stackOpenVLA-OFT · Real-world cover & stacksuccess rate (%): 33.3 -> 57.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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