RULER: Instance-aware Rubric Rewards for SVG Generation

Hugging Face Daily Papers Papers
svg-generation reinforcement-learning rubric-scoring vision-language-model ai-research

Summary

RULER introduces instance-aware rubric rewards for SVG generation, using a vision-language judge to optimize reinforcement learning and significantly improve performance over previous methods.

Generating Scalable Vector Graphics (SVG) code from natural-language instructions is an open-ended task without absolute visual ground truth, leaving both evaluation and policy optimization without a faithful signal. Scalar metrics (CLIP, Aesthetic) calibrated on natural images transfer poorly to stylized vector content, and reusing them as RL rewards triggers reward hacking. We address both limitations with rubric-based scoring. We first establish empirically that prompting a vision-language judge with a multi-axis rubric correlates with human judgments far better than scalar metrics, both across samples and within instructions. Building on this finding, we introduce RULER (Instance-aware Rubric Rewards for Reinforcement Learning), which converts each instruction into an instance-aware rubric of six items spanning semantic, visual, and stylistic axes; a judge VLM scores rendered rollouts item-by-item, and the weighted satisfactions form a fine-grained reward optimized via Group Relative Policy Optimization. Because the rubric is derived from text alone, RULER requires neither paired SVG ground truth nor human preference labels. On MMSVG-Illustration and MMSVG-Icon, RULER lifts the rubric score from 0.432/0.395 to 0.693/0.683, surpassing dedicated SVG specialists and matching the substantially larger DeepSeek-V3, with ablations identifying rubric design as the active lever for RL on open-ended SVG generation. The project page is available at https://hangyuran.github.io/RULER/.
Original Article
View Cached Full Text

Cached at: 09/23/26, 03:32 AM

Paper page - RULER: Instance-aware Rubric Rewards for SVG Generation

Source: https://huggingface.co/papers/2609.25270

Abstract

GeneratingScalableVectorGraphics(SVG)codefromnatural-languageinstructionsisanopen-endedtaskwithoutabsolutevisualgroundtruth,leavingbothevaluationandpolicyoptimizationwithoutafaithfulsignal.Scalarmetrics(CLIP,Aesthetic)calibratedonnaturalimagestransferpoorlytostylizedvectorcontent,andreusingthemasRLrewardstriggersrewardhacking.Weaddressbothlimitationswithrubric-basedscoring.Wefirstestablishempiricallythatpromptingavision-languagejudgewithamulti-axisrubriccorrelateswithhumanjudgmentsfarbetterthanscalarmetrics,bothacrosssamplesandwithininstructions.Buildingonthisfinding,weintroduceRULER(Instance-awareRubricRewardsforReinforcementLearning),whichconvertseachinstructionintoaninstance-awarerubricofsixitemsspanningsemantic,visual,andstylisticaxes;ajudgeVLMscoresrenderedrolloutsitem-by-item,andtheweightedsatisfactionsformafine-grainedrewardoptimizedviaGroupRelativePolicyOptimization.Becausetherubricisderivedfromtextalone,RULERrequiresneitherpairedSVGgroundtruthnorhumanpreferencelabels.OnMMSVG-IllustrationandMMSVG-Icon,RULERliftstherubricscorefrom0.432/0.395to0.693/0.683,surpassingdedicatedSVGspecialistsandmatchingthesubstantiallylargerDeepSeek-V3,withablationsidentifyingrubricdesignastheactiveleverforRLonopen-endedSVGgeneration.Theprojectpageisavailableathttps://hangyuran.github.io/RULER/.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2609\.25270

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.25270 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.25270 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.25270 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR

Hugging Face Daily Papers

This paper introduces POW3R, a policy-aware rubric reward framework for reinforcement learning with verifiable rewards (RLVR). It shows that static rubric aggregation misallocates learning signal, and POW3R achieves faster convergence and better performance across multiple settings.

V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning

Hugging Face Daily Papers

Introduces a rubric-based reinforcement learning method to improve visual faithfulness in vision-language models by decomposing responses into atomic propositions and scoring them on visual faithfulness, reasoning consistency, and instruction following.