← Search

Mingan Lin

2 accepted papers

2025

Beyond Sight: Towards Cognitive Alignment in LVLM via Enriched Visual Knowledge

CVPR 2025poster

Does seeing always mean knowing? Large Vision-Language Models (LVLMs) integrate separately pre-trained vision and language components, often using CLIP-ViT as vision backbone. However, these models frequently encounter a core issue of "cognitive misalignment" between the vision encoder (VE) and the…

2025

CFBench: A Comprehensive Constraints-Following Benchmark for LLMs

ACL 2025long

The adeptness of Large Language Models (LLMs) in comprehending and following natural language instructions is critical for their deployment in sophisticated real-world applications. Existing evaluations mainly focus on fragmented constraints or narrow scenarios, but they overlook the comprehensivene…