AI Paper Atlas

Research map / 3D vision / 3D generation

Human-Object Interaction via Automatically Designed VLM-Guided Motion Policy

Zekai Deng, Ye Shi, Kaiyang Ji, Lan Xu, Shaoli Huang, Jingya Wang

ICLR 2026 · 3D vision › 3D generation · approach: Hand-object interaction generation · 9 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 VLM-guided RMD multi-task formulation vs InterPhysInterPhys · InterPlay HybridCompletion Rate (%): 27.5 -> 53.8Improved
add top-view image input for VLM planner instead of text-only LLM (ablation)Ours · InterPlay StaticCompletion Rate (%): 62.8 -> 75.1Improved
add top-view image input for VLM planner instead of text-only LLM (ablation)Ours · InterPlay HybridCompletion Rate (%): 39.9 -> 53.8Improved
add part-level object decomposition (vs single entity) (ablation)Ours · Single-task CarryCompletion Rate (%): 75.1 -> 88.3Improved
add multi-part human-object RMD (vs one human part, one object part) (ablation)Ours · Single-task CarryCompletion Rate (%): 11.7 -> 88.3Improved
add multi-part human-object RMD (vs one-one) (ablation)Ours · Single-task LieCompletion Rate (%): 28.1 -> 62.0Improved
add relative position encoding (ablation)Ours · Single-task LieCompletion Rate (%): 36.8 -> 62.0Improved
add relative velocity encoding (ablation)Ours · Single-task SitCompletion Rate (%): 76.1 -> 92.6Improved
add dynamic encoding w'_ij (ablation)Ours · Single-task OpenCompletion Rate (%): 62.1 -> 91.2Improved
use GPT-4V instead of LLaVA-1.6 as planner (ablation)Ours · InterPlay-HybridCompletion Rate (%): 43.3 -> 53.8Improved
use GPT-4V instead of Qwen-VL-Max as planner (ablation)Ours · InterPlay-HybridCompletion Rate (%): 47.7 -> 53.8Improved
use full prompt instead of simplified prompt (ablation)Ours · InterPlay-HybridCompletion Rate (%): 45.3 -> 53.8Improved

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