This is your work, valued
https://www.yanhongli.com/
text_or_pixels. Codebase for EMNLP 2025 Findings paper "Text or Pixels? Evaluating Efficiency and Understanding of LLMs with Visual Text Inputs"
18rep_dispersion. Python
5LLM-SelfReflection-Eval. The codebase for the NACCL 2024 paper titled 'When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language Models.'
5annotated_deep_learning_paper_implementations. notes for annotated_deep_learning_paper_implementations by labml.ai
4cd-lm. Code and resources for our ICLR 2025 paper, Chunk-Distilled Language Modeling
4Awesome-Retrieval-Augmented-Multimodal-Generation. A curated list of papers on Retrieval-Augmented Generation (RAG) applied to multimodal tasks (images, text, video, and beyond).
2ConvRE.
1