Paper

SDR: Set-Distance Rewards for Radiology Report Generation

Unreadunread

AI summary

arXiv:2606. 00440v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has rapidly advanced reasoning in vision--language models.

Reading status

Priority

About this paper

Authors: Halil Ibrahim Gulluk, Max Van Puyvelde, Wim Van Criekinge, Olivier Gevaert
Released: 2026-06-02 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because SDR: Set-Distance Rewards for Radiology Report Generation overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", 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)". Matching terms: code, source, token, line, rate, full, chain, trained. Source: arxiv cs.AI (Artificial Intelligence).
arXiv: 2606.00440

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to SDR: Set-Distance Rewards for Radiology Report Generation. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.