88%Must read
?Must readVote to see the score
Evidence-RL: Towards Evidence-intensive Visual Reasoning
Counterfactual Evidence Disentanglement (CED) audits vision-language model grounding by comparing evidence-region and non-evidence-region support drops inside GRPO, improving visual reasoning across benchmarks without inference overhead or evidence annotations.
Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 16 on Hugging Face · Code ★ 4
– ReadersNo votes yet
15/20 AI panelreviewers recommend it
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
AI panel: 15 of 20 reviewers recommend it
lenient 4/5
medium 8/10
strict 3/5