AI Paper Atlas

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

Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation

Fengnian Zhang, Tao Huang, Siyu Xu, Zhong Jin, Chang Xu

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 4 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
prune highest-diff instead of lowest-diff Llama2 FFN channels (20%, no recovery) (ablation)OpenVLA · LIBERO-Spatialsuccess rate (%): 1.5 -> 76.3Improved
add LoRA fine-tuning after lowest-diff pruning (ablation)OpenVLA · LIBERO-Spatialsuccess rate (%): 1.5 -> 86.5Improved
prune highest-diff instead of lowest-diff DINOv2 FFN channels (ablation)OpenVLA · LIBERO-Spatialsuccess rate (%): 0.0 -> 82.0Improved
prune lowest-diff instead of highest-diff DINOv2 attention heads (ablation)OpenVLA · LIBERO-Spatialsuccess rate (%): 1.6 -> 76.7Improved
prune highest-diff instead of lowest-diff Llama2 attention heads (ablation)OpenVLA · LIBERO-Spatialsuccess rate (%): 0.0 -> 84.3Improved
prune highest-diff instead of lowest-diff Llama2 FFN channels (ablation)OpenVLA · LIBERO-Spatialsuccess rate (%): 2.7 -> 72.0Improved
prune highest-diff instead of lowest-diff Gemma attention heads (ablation)pi0.5 · LIBERO-Spatialsuccess rate (%): 0.0 -> 85.0Improved
prune highest-diff instead of lowest-diff Gemma FFN channels (ablation)pi0.5 · LIBERO-Spatialsuccess rate (%): 5.0 -> 95.0Improved
choose highest-diff vs lowest-diff pruning for the projector FFN (30%) (ablation)OpenVLA · LIBERO-Spatialsuccess rate (%): 0.0 -> 54.0Mixed
remove SigLIP FFN entirely (ratio 1.0) (ablation)OpenVLA · LIBERO-Spatialsuccess rate (%): 84.7 -> 70.0Hurt
use the multi-module joint pruning scheme instead of LLM-Pruner at matched 12.4GBOpenVLA · LIBERO (Long, Moderate config)success rate (%): 1.0 -> 62.3Improved
apply Moderate joint pruning (7.3GB to 5.6GB)pi0.5 · LIBERO (avg of 4 suites)success rate (%): 96.9 -> 89.0Hurt

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