🏢 Nanjing University

AdaptiveStep: Divides reasoning steps automatically through model confidence, enhancing PRM training & performance.

STAR: A novel approach uses text-to-video models for realistic, temporally consistent real-world video super-resolution, improving image quality and detail.

TALE: A novel framework dynamically adjusts token budgets in LLM reasoning prompts, slashing costs by ~70% with minimal accuracy loss.

Create realistic 3D heads with specific hairstyles from text, no 3D hair data needed!

InstanceCap improves text-to-video generation through detailed, instance-aware captions.

This survey paper offers a comprehensive overview of Multimodal Large Language Model (MLLM) evaluation, systematically categorizing benchmarks and methods, and identifying gaps for future research, th…