AI Paper Atlas

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

Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models

Yurou Yang, Muyuan Lin, Roberto Martín-Martín, Labrie Martin, Shreekant Gayaka, Cheng-Hao Kuo, Luca Carlone

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 3 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
fine-tune GR00T-N1.5 with VGGT tokens via Early Fusion, Late Fusion or Spatial Forcing (task finetuning only)GR00T-N1.5 · RoboCasa (8 tasks, 3 cameras)success rate (avg): 71.7 -> 69.7 (EF), 71.0 (LF), 68.3 (SF)No clear effect
add Early Fusion VGGT tokensGR00T-N1.5 · Unitree G1 real robotoverall success rate: 22.22 -> 27.78 (p=0.511)No clear effect
add Early Fusion VGGT tokensGR00T-N1.5 · Unitree G1 real robot (approach stage)success rate: 57.78 -> 84.44 (p<0.001)Improved
add mid-training on all RoboCasa tasks to Early Fusion (ablation)Early Fusion · RoboCasa (8 tasks, 3 cameras)success rate (avg): 69.7 -> 75.2Improved
mid-train baseline too and compare with mid-trained Early Fusion (ablation)Early Fusion · RoboCasa (mid-trained baselines)success rate (avg): 72.2 -> 75.2 (p=0.168)Improved
mid-train Early Fusion (ablation)Early Fusion · LIBEROsuccess rate (avg): 86.6 -> 87.7 (baseline 87.9)No clear effect
use a single camera instead of three, comparing Early Fusion to baseline (ablation)Early Fusion · RoboCasa (single camera)success rate (avg): 17.2 -> 21.5 (p=0.030)Improved
add learned attention gate to Early Fusion (ablation)Early Fusion · RoboCasasuccess rate: 5-27% -> 64-89%Improved
make attention gate input-dependent (ablation)Early Fusion · RoboCasasuccess rateNo clear effect
add positional embeddings to Early Fusion (ablation)Early Fusion · RoboCasasuccess rateMixed
also finetune the LLM in Spatial Forcing (ablation)Spatial Forcing · RoboCasa (8 tasks, 3 cameras)success rate (avg): 68.3 -> 31.2Hurt
add VGGT tokens (Early or Late Fusion) to GR00T VLM for depth probingGR00T-N1.5 · NYU Depth V2 depth probedepth RMSEImproved

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