Add pipeline tag, link to paper and project page

README.md

@@ -1,10 +1,11 @@
 ---
-license: apache-2.0
 base_model:
 - Qwen/Qwen3.5-4B
 - Qwen/Qwen3.5-9B
 - Qwen/Qwen3.5-35B-A3B
 library_name: peft
+license: apache-2.0
+pipeline_tag: text-generation
 tags:
 - text-to-image
 - prompt-expansion
@@ -16,6 +17,8 @@ tags:
 
 LoRA adapters for the prompt-expansion policies of *T-DIG: Text-conditioned Diversity for Image Generation* (under review).
 
+Paper: [T-DIG on Hugging Face](https://huggingface.co/papers/2610.29003) · Project page: [image-study.org/t-dig](https://image-study.org/t-dig/)
+
 Given a prompt and a request for what should differ, a *generation* policy writes K prompts, one per image, that vary the requested axis and keep everything else in the prompt. An *editing* policy instead writes one edit instruction per image of an existing set. The text-to-image (T2I) model is not changed. Each policy is trained with GRPO against one T2I model; it works with others, but best with its own.
 
 ## Contents
@@ -83,4 +86,4 @@ out = llm.generate([chat], SamplingParams(temperature=1.0, max_tokens=1024),
 
 ## Citation
 
-Citation information will be added after review.
+Citation information will be added after review.