proomt

Search

Search posts, papers, and topics

All posts

Hugging Face Daily PapersHangyu Ran, Yuhao Zheng, Yingying Zhang1 min readpaperadvanced

RULER: Instance-aware Rubric Rewards for SVG Generation

Summary

RULER introduces an instance-aware rubric reward system for generating SVG code from natural language, addressing the lack of faithful evaluation signals. It uses a VLM to score rendered SVGs against a text-derived rubric, achieving significant performance improvements over existing methods without needing ground truth or human preference data.

  • Scalar metrics like CLIP and Aesthetic scores are poor evaluation signals for stylized vector graphics and lead to reward hacking in RL.
  • A multi-axis, instance-aware rubric, scored by a VLM, correlates much better with human judgment for SVG generation.
  • RULER uses this VLM-scored rubric as a fine-grained reward signal for reinforcement learning, optimizing via Group Relative Policy Optimization.
  • The method requires no paired SVG ground truth or human preference labels, as rubrics are generated solely from text instructions.

Engineers working on generative AI for design tools or vector graphics will find this valuable for improving model evaluation and training efficiency in open-ended generation tasks.

8/10

Related reading

  1. ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals

    ImpossibleRubrics introduces a 169‑task benchmark of “impossible” prompts, each with a formal oracle certificate defining what an honest answer can claim. The authors generate rubrics downstream and test them adversarially, finding that many rubric generators are exploitable (8‑36% of the time) and that a single generic rubric (“be decisive, penalize hedging”) is exploited 64% of the time, while…

    Hugging Face Daily Papersarxiv.org1 minpaper
  2. Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design

    The paper introduces Designer‑RSI, a continual‑adaptation system that couples a frozen design‑software‑controlling LLM with an external procedural memory of natural‑language design skills. Over five adaptation rounds on real user briefs, the memory grows from 76 to 139 procedures and lifts execution success from 72.7% to 99.3%, showing that skill accumulation and selective replay can dramatically…

    Hugging Face Daily Papersarxiv.org1 minpaper
  3. Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

    Code2Skill is an automated pipeline that mines popular GitHub repositories to extract verifiable, implementation‑anchored procedural “skills”. It builds a bank of ~1 M skill records (atomic ops, workflows, patterns) with provenance metadata, verifies each via blind reconstruction, and shows that augmenting LLM‑based agents with these skills yields an average 11.7% performance lift across 72 proto…

    Hugging Face Daily Papersarxiv.org1 minpaper
  4. EDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation

    EdgeGen automatically extracts compliance rules from a tool‑calling LLM agent’s specification and generates database‑grounded edge‑case tasks that violate those rules. Using these synthetic edge cases for finetuning and harness optimization improves benchmark performance by up to 42 % and 30 % respectively, without any human labeling.

    Hugging Face Daily Papersarxiv.org1 minpaper