Update README.md

README.md

@@ -225,4 +225,8 @@ Interestingly, 33 million param `answerai-colbert-small-v1` is winning. Also, co
 * [**ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction**](https://arxiv.org/abs/2112.01488) (NAACL'22).
 * [**PLAID: An Efficient Engine for Late Interaction Retrieval**](https://arxiv.org/abs/2205.09707) (CIKM'22).
 
-TODO : Add Jina Papers, Answer AI papers 
+## Future Work 
+- Push a clean codebase to replicate re-ranker benchmarks on MIRAGE (current one is a disaster).
+- Train on : https://huggingface.co/datasets/sebastian-hofstaetter/tripclick-training
+- Train with Knowledge-Distillation with in ColBERTv2 style
+- Add relavant Jina Papers, Answer AI papers in refernces