Blink

BLINK: Multimodal Large Language Models Can See but Not Perceive 🌐 Homepage | 💻 Code | 📖 Paper | 📖 arXiv | 🔗 Eval AI This page contains the benchmark dataset for the paper "BLINK: Multimodal Large Language Models Can See but Not Perceive" Introduction We introduce BLINK, a new benchmark for multimodal language mod

Papers using Blink (7)

VisReflect: Latent Visual Reflection for Fine-Grained Perception in Long Visual Context2026Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual Reasoning2026Decoding the Pulse of Reasoning VLMs in Multi-Image Understanding Tasks2026LanteRn: Latent Visual Structured Reasoning2026SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL2025Scaling Spatial Intelligence With Multimodal Foundation Models2025Grounded Reinforcement Learning For Visual Reasoning2025