Paper

WinDOM: Self-Family Distillation for Small-Model GUI Grounding

Unreadunread

AI summary

arXiv:2606. 25964v1 Announce Type: new Abstract: Small ($\sim$2B) GUI-grounding agents are attractive for on-device deployment, accessibility tooling, and low-cost iteration, but at this scale they face two open recipe questions: how to obtain bounding-box training data without expensive human annotation, and how to combine supervised fine-tuning with reinforcement learning.

Reading status

Priority

About this paper

Authors: Chengheng Li-Chen, Zhiqian Zhou, Hao Chen, Nicolas Chauvin
Released: 2026-06-25 (14d ago)
Topic: Related to current project
Relation to my work: Read next because WinDOM: Self-Family Distillation for Small-Model GUI Grounding overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)", clean result "Training one persona to emit a [ZLT] marker without bystanders adopting it has a one-cell-wide LR x epochs window on Qwen2.5-7B-Instruct (LOW confidence)", clean result "A pretraining-data-poisoned Qwen3-4B backdoor only fires on the exact trigger tokens — paraphrases don't activate it, and base-model similarity to the trigger doesn't predict which inputs fire (MODERATE confidence)". Matching terms: rect, under, source, rate, recipe, implement, without, screen. Source: arxiv cs.AI (Artificial Intelligence).
arXiv: 2606.25964

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to WinDOM: Self-Family Distillation for Small-Model GUI Grounding. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.