AI Paper Atlas

Research map / Large language models / Agents, code and math

Goal-Driven Sequential Data Abstraction

Umar Riaz Muhammad, Yongxin Yang, Timothy M. Hospedales, Tao Xiang, Yi-Zhe Song

ICCV 2019 · Large language models › Agents, code and math · approach: LLM-guided program synthesis · 21 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
select strokes holistically with GDSA instead of keep/remove decisions in original order (DSA)GDSA · QuickDraw, budget 25%, RNNcategory recognition accuracy (%): 38.36 -> 50.50Improved
select strokes holistically with GDSA instead of DSAGDSA · QuickDraw, budget 25%, Sketch-a-Netcategory recognition accuracy (%): 65.05 -> 71.92Improved
select strokes holistically with GDSA instead of DSAGDSA · QuickDraw, budget 50%, RNNcategory recognition accuracy (%): 67.89 -> 71.75Improved
select strokes with GDSA instead of first strokes in human orderGDSA · QuickDraw, budget 25%, RNNcategory recognition accuracy (%): 36.66 -> 50.50Improved
select segments with GDSA instead of DSAGDSA · TVSum, budget 1 segmentcategory recognition accuracy (%): 42.0 -> 68.0Improved
select segments with GDSA instead of DQSNGDSA · TVSum, budget 25%category recognition accuracy (%): 64.0 -> 74.0Improved
select segments with GDSA instead of DQSNGDSA · TVSum, budget 50%category recognition accuracy (%): 72.0 -> 76.0Improved
select sentences with GDSA instead of DSA (HAN classifier)GDSA · Amazon reviews, budget 1 sentencesentiment accuracy (%): 72.42 -> 83.77Improved
select sentences with GDSA instead of DQSN (HAN classifier)GDSA · Amazon reviews, budget 25%sentiment accuracy (%): 80.25 -> 86.08Improved
select sentences with GDSA instead of random sentences (RNN classifier)GDSA · Amazon reviews, budget 25%sentiment accuracy (%): 66.44 -> 73.39Improved
select sentences randomly instead of in original orderGDSA · Amazon reviews, budget 25%, HANsentiment accuracy (%): 76.06 -> 77.14No clear effect
replace the 2-state keep/remove action space with a pool-based picking policy trained by RL on a synthetic taskGDSA · synthetic 3x3 images, budget 2recognition accuracy: 50%-70% -> ~90%Improved

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