Trendoday

ViRA: Toward Ultra-High-Resolution Visual Agents via Cross-Input Relative Policy Optimization

Visual agents answer questions about ultra-high-resolution photos by zooming into the relevant regions. However, existing agents often answer from common sense instead of reading the evidence. Reinfor

  • Upvotes6
–Rank now
#28Peak rank
1Days on list
13Score · 7d
Nov 18, 2026First seen
Rank · 7 days

About this paper

Visual agents answer questions about ultra-high-resolution photos by zooming into the relevant regions. However, existing agents often answer from common sense instead of reading the evidence. Reinforcement learning (RL) on the final answer cannot correct this, because a guess earns the same reward as reading. We propose Cross-Input Relative Policy Optimization (CrossRPO), which trains agents on contrast sets. A contrast set asks one question about several versions of an image that differ only in a small region with the evidence and have different answers, so only reading the evidence solves the whole set. CrossRPO rewards solving the whole set, and we prove that it does not reinforce a…

Upvotes
6
Authors
12
Published
Nov 16, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

ViRA: Toward Ultra-High-Resolution Visual Agents via Cross-Input Relative Policy Optimization was first seen on Hugging Face · Daily papers on Nov 18, 2026. Since then it has appeared in 2 checks on 1 different day. Its best position was #28 of 30, reached on Nov 18, 07:28 UTC. It dropped off the list after Nov 18, 15:28 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 07:2809:2811:2813:2815:28 Nov 18, 07:28 UTC · #28Nov 18, 15:28 UTC · #29

Last 14 days

Best rank per day (UTC).

Nov 9today

Metric history

Platform metric as reported by Hugging Face.

0246 07:2809:2811:2813:2815:28 Nov 18, 07:28 UTC · 6Nov 18, 15:28 UTC · 4

Questions

Is ViRA: Toward Ultra-High-Resolution Visual Agents via Cross-Input Relative Policy Optimization trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 18, 15:28 UTC, after 1 day of trending.

What is the highest rank ViRA: Toward Ultra-High-Resolution Visual Agents via Cross-Input Relative Policy Optimization reached?

#28 on Hugging Face · Daily papers, on Nov 18, 07:28 UTC. Trendoday checks this list every 120 minutes.

How long has ViRA: Toward Ultra-High-Resolution Visual Agents via Cross-Input Relative Policy Optimization been trending?

It was first seen on Nov 18, 2026 and has been on the list on 1 day (2 checks) since.