⚖️ Alignment & RLHF

🎞️ ECCV2026 · 1 paper notes

📌 Same area in other venues: 📷 CVPR2026 (12) · 🔬 ICLR2026 (102) · 💬 ACL2026 (38) · 🧪 ICML2026 (37) · 🤖 AAAI2026 (17) · 🧠 NeurIPS2025 (36)

Omni-RRM: Advancing Omni Reward Modeling via Automatic Rubric-Grounded Preference Synthesis

Omni-RRM synthesizes preference data with five-criterion justifications through dual-teacher consensus, then uses SFT→GRPO to learn pairwise response discrimination across images, video, and audio, raising the 7B backbone's five-benchmark average accuracy from 60.2% to 70.4% and improving response selection without updating the generator's parameters.