How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing Paper • 2602.01851 • Published 3 days ago • 16
EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering Paper • 2509.25175 • Published Sep 29, 2025 • 31
GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts Paper • 2509.25160 • Published Sep 29, 2025 • 32