AI Paper Atlas

Research map / 3D vision / 3D generation

LessMimic: Versatile Humanoid-Object Interaction with Unified Distance Field Representations

Yutang Lin, Jieming Cui, Yixuan Li, Wei Liang, Baoxiong Jia, Yixin Zhu, Siyuan Huang

NeurIPS 2026 · 3D vision › 3D generation · approach: Hand-object interaction generation · 17 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes LessMimic, a humanoid-object interaction approach using unified distance field representations to enable versatile whole-body interaction without motion references or task-specific rewards.

Problem

Existing humanoid-object interaction methods depend on motion-reference inputs or task-specific rewards, which couple policies to particular motion scripts, object geometries, and contact timings, limiting geometric generalization and flexible interaction control.

Approach

Uses unified distance field representations for humanoid-object interaction so that simple commands can specify motion intent, removing reliance on motion references and task-specific rewards.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add AIP interaction reward (ablation)LessMimic · Carry and sequential N=5success rate (%): 0.0 -> 82.9 (Carry); 5.2 -> 62.1 (N=5)Improved
add AIP interaction reward (ablation)LessMimic · Push contact / SitStandcontact rate / success: Push 1.0x: 72.5 -> 51.3; SitStand 1.0x: 98.3 -> 80.3Hurt
add synthetic command augmentation (ablation)LessMimic · Sequential multi-skill, N=5success rate (%): 22.1 -> 62.1Improved
add geometry randomization in RL post-training (ablation)LessMimic · PickUp, scale 1.0xsuccess rate (%): 0.0 -> 100.0Improved
add RL post-training after behavior cloning (ablation)LessMimic · PickUp, scale 1.0xsuccess rate (%): 31.7 -> 100.0Improved
use Transformer instead of MLP backbone (ablation)LessMimic · Sequential multi-skill, N=5success rate (%): 1.7 -> 62.1Improved
encode DF history with VAE latent instead of raw DF (ablation)LessMimic · PickUp overallsuccess rate (%): 81.2 -> 89.0Improved
use DF instead of bounding-box or voxel observations (ablation)LessMimic · PickUp overallsuccess rate (%): 52.5 / 66.5 -> 81.2 (raw DF)Improved
use DF-based policy vs motion-conditioned baselines at out-of-range scale 0.4xLessMimic · PickUp, scale 0.4xsuccess rate (%): 0.0 -> 63.0Improved
motion-conditioned baselines vs LessMimic at nominal scaleHDMI/ResMimic · SitStand and Push, scale 1.0xsuccess / contact rate: ResMimic SitStand 100.0; HDMI Push 97.3 vs ours 80.3 / 51.3Mixed
replace MoCap DF input with egocentric depth (vision distillation)LessMimic · Sequential multi-skill, N=5success rate (%): 62.1 -> 15.9Hurt
add rear depth camera to vision policy (ablation)LessMimic (Vision) · SitStandsuccess rate (%): 0 -> 31 overallImproved

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