3 papers
cs.CV2026
MemeMind: Reference-Guided Trace Construction for Offline Context Optimization
Run Yang, Weihang Wang, Boheng Sheng +7
Offline context optimization improves an agent by revising its instructions and examples while keeping the model frozen. This approach learns from rollouts on an adaptation set, bu…
cs.AI2026
MemeBench: What LVLMs Miss When Interpreting Culture-Dependent Memes
Weihang Wang, Kainan Tu, Jielei Zhang +9
Large vision-language models have improved at describing visual content, but accurate descriptions do not ensure interpretation when meaning depends on knowledge beyond the pixels.…
cs.CL2025
Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in Large Language Models
Boheng Sheng, Jiacheng Yao, Meicong Zhang +1
Large language models (LLMs) often struggle to accurately read and comprehend extremely long texts. Current methods for improvement typically rely on splitting long contexts into f…