AI Paper Atlas

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

Rethinking Intermediate Representation for VLM-based Robot Manipulation

Weiliang Tang, Jialin Gao, Jia-Hui Pan, Gang Wang, Li Erran Li, Yun-Hui Liu, Mingyu Ding, Pheng-Ann Heng, Chi-Wing Fu

CVPR 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
use SEAM semantic-assembly representation instead of OmniManip's keypoint/axis representationVLM-based manipulation with Qwen3-VL · Real-world UR5 8 tasks (closed-loop)total success rate: 68.8% -> 83.8%Improved
use SEAM instead of OmniManip in open-loop executionVLM-based manipulation with Qwen3-VL · Real-world UR5 8 tasks (open-loop)total success rate: 52.5% -> 63.8%Improved
use SEAM instead of OmniManip on pick up cup/bowl onto dish (open-loop)VLM-based manipulation with Qwen3-VL · Pick up cup/bowl onto the dish (open-loop)success rate: 7/10 -> 5/10Hurt
add RAG-based few-shot part segmentation to localize the teapot openingSEAM · Fit the lid onto the teapotqualitative executionImproved
use RAG few-shot segmentation instead of LISA, OV-seg or Grounded SAMSEAM · Part segmentation inference time (A6000)time (sec.): 0.88 -> 0.6 vs Grounded SAMImproved
use high-level skill vocabulary (Instruct2Act) instead of low-level primitivesintermediate representation · 33 generated tasks, Qwen3-VLaction-generalizability vs VLM-comprehensibilityMixed
use low-level keypoint representation (ReKep, OmniManip) instead of SEAMintermediate representation · 33 generated tasks, Qwen3-VLaction-generalizability vs VLM-comprehensibilityMixed

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