AI Paper Atlas

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

Saliency-Aware Quantized Imitation Learning for Efficient Robotic Control

Seongmin Park, Hyungmin Kim, Sangwoo Kim, Wonseok Jeon, Juyoung Yang, Byeongwook Jeon, Yoonseon Oh, Jungwook Choi

ICCV 2025 · Vision-language and multimodal › Robot action and navigation · approach: Multimodal prompt-driven manipulation · 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
replace SIS with vision-language keyframe detection for state weighting (ablation)SQIL on OpenVLA · LIBERO (OpenVLA INT4 avg)avg success rate (%): 72.6 ± 0.7 -> 73.2 ± 0.6Improved
add SIS-weighted QRD loss to QATOpenVLA INT4 (AWQ) · LIBERO-Spatialsuccess rate (%): 80.9 ± 0.7 -> 83.9 ± 0.5Improved
add SIS-weighted QRD loss to QATOpenVLA INT4 (AWQ) · LIBERO-Longsuccess rate (%): 47.3 ± 0.3 -> 49.2 ± 1.0Improved
add QAT to uniform QRD distillation (ablation)QRD only · LIBERO-Spatial (INT4 AWQ init)avg success rate (%): 69.5 -> 83.9Improved
add quantization-aware fine-tuning (QAT) over PTQOpenVLA INT4 (AWQ) · LIBERO-Spatialsuccess rate (%): 80.1 ± 0.5 -> 80.9 ± 0.7Improved
use calibrated AWQ instead of uncalibrated RTNOpenVLA INT4 · LIBERO-Spatial (INT4 AWQ init)avg success rate (%): 73.3 -> 80.1Improved
quantize ViT to INT4 only (ablation)OpenVLA PTQ · LIBEROsuccess rate (%): 74.0% -> 73.4%No clear effect
quantize LLM to INT4 only (ablation)OpenVLA PTQ · LIBEROsuccess rate (%): 74.0% -> 71.3%Hurt
use raw SIS values as loss weights instead of threshold weight alpha_t (ablation)SQIL · LIBEROavg success rate (%): 73.2 ± 0.6 -> 71.8 ± 1.0Hurt
change saliency noise distribution from Gaussian to Uniform (ablation)SQIL · LIBEROavg success rate (%): 73.2 ± 0.6 -> 73.0 ± 0.4No clear effect
compute SIS every 5th frame instead of every 4th (ablation)SQIL on OpenVLA · LIBERO-Longsuccess rate (%): 49.2% -> 48.2%Hurt
increase saliency weight beta from 2 to 5 (ablation)SQIL on OpenVLA · LIBERO-Longsuccess rate (%): 49.2% -> 47.8%Hurt

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