AI Paper Atlas

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

Scaling up Memory for Robotic Control via Experience Retrieval

Ajay Sridhar, Jennifer Pan, Satvik Sharma, Chelsea Finn

ICLR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Multimodal prompt-driven manipulation

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 keyframe memory (MemER) vs no historyhigh-level policy · Countingwrong scoops: 61 -> 1Improved
add keyframe memory (MemER) vs 32-frame long historyhigh-level policy · Object Search optimal pathcount of 60: 41 -> 57Improved
extend history from 8 to 32 frameshigh-level policy · Countingwrong scoops: 26 -> 12Improved
use MemER high-level policy vs Human HL oraclehigh-level policy · Object Search / Countingobjects retrieved: 59 vs 58; 1 vs 0 wrong scoopsNo clear effect
fine-tuned Qwen2.5-VL high-level policy instead of GPT-5high-level policy · Object Search offlinetrajectory accuracy: 0.15 -> 0.80Improved
fine-tuned Qwen2.5-VL instead of Gemini Robotics-ER 1.5high-level policy · Counting offlinetrajectory accuracy: 0.13 -> 0.67Improved
replace visual keyframes with text subtasks (ablation)MemER · Object Searchoptimal path used: 57 -> 28Hurt
add text subtasks to visual keyframe memory (ablation)MemER · Countingwrong scoops: 1 -> 13Hurt
multi-task instead of single-task training (ablation)MemER · Object Search and Dust & Replace, original taskssuccessNo clear effect
multi-task instead of single-task training (ablation)MemER · Cross-task object generalizationsuccessImproved
merge fine-tuned high-level weights with pretrained Qwen2.5-VL (ablation)MemER · three taskssuccessImproved

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