Arian Khorasani
@arian-khorasani.bsky.social
AI Researcher at Mila-Quebec AI Institute! 🇨🇦
Always curious to learn!
Always curious to learn!
Reposted by Arian Khorasani
🚨 Excited to introduce PairBench! 🚨
💡 TL;DR: VLM-judges can fail at data comparison!
✅ PairBench helps you pick the right one by testing alignment, symmetry, smoothness & controllability—ensuring reliable auto-evaluation.
📄 Paper: arxiv.org/abs/2502.15210
🧵 Thread: 👇
💡 TL;DR: VLM-judges can fail at data comparison!
✅ PairBench helps you pick the right one by testing alignment, symmetry, smoothness & controllability—ensuring reliable auto-evaluation.
📄 Paper: arxiv.org/abs/2502.15210
🧵 Thread: 👇
February 27, 2025 at 7:50 PM
🚨 Excited to introduce PairBench! 🚨
💡 TL;DR: VLM-judges can fail at data comparison!
✅ PairBench helps you pick the right one by testing alignment, symmetry, smoothness & controllability—ensuring reliable auto-evaluation.
📄 Paper: arxiv.org/abs/2502.15210
🧵 Thread: 👇
💡 TL;DR: VLM-judges can fail at data comparison!
✅ PairBench helps you pick the right one by testing alignment, symmetry, smoothness & controllability—ensuring reliable auto-evaluation.
📄 Paper: arxiv.org/abs/2502.15210
🧵 Thread: 👇