arXiv (All)
open access
Same Reward, Different Skills: When Multimodal RL Learns to Look
Reinforcement learning with verifiable rewards (RLVR) improves vision-language benchmark scores even without visual information during training. With images at test, blind-trained models recover roughly half of the real-image gain at 3B and nearly four fifths at 7B. Prolonged real-image training can
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- RLVR is a Kernel, Not a Function: Statistical Inference for pass@$k$ Crossovers#1037230
- AnyviewMeter: Adapting Robotic Reward Models with Camera Geometry and Multi-View Attention#1035652
- Where the Verifier Fails: A Category-Level Audit of Reward Signals in RLVR#821295
- Scaling Vision-Language Reward Learning for Robot Manipulation in Parallel Simulation#1036157
- Mechanism-Guided Selective Unlearning for RLVR-Induced Reasoning#287130
Record · ID 1157179
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive