Poster · Atlanta
PRISM-Bench: A Benchmark of Puzzle-Based Visual Tasks with CoT Error Detection
- When
- Fri 11 Dec 2026, 10:00–13:00 EST
- Where
- Hall C1, Georgia World Congress Center
- Session
- Atlanta Poster Session 5
- Authors
- Cheng Wan, Yusu Qian, Qingyu Zhao
- Organisations
- Cornell University, Apple
- QRS classification
- Language models, Computer vision