Add links to paper and code

README.md

@@ -1,10 +1,9 @@
 ---
+base_model: Qwen/Qwen2.5-Omni-3B
+library_name: transformers
 license: other
 license_name: qwen-research
 license_link: LICENSE
-base_model: Qwen/Qwen2.5-Omni-3B
-base_model_relation: finetune
-library_name: transformers
 pipeline_tag: audio-text-to-text
 tags:
 - audio
@@ -13,12 +12,17 @@ tags:
 - candidate-scoring
 - qwen2_5_omni
 - safetensors
+base_model_relation: finetune
 ---
 
 # AudioJev
 
 **Direct audio decisions with order-calibrated candidate probabilities. Built with Qwen.**
 
+Paper: https://huggingface.co/papers/2610.01293
+
+Code: https://github.com/SihanLv/AudioJev-Inference
+
 AudioJev takes an audio waveform, a natural-language question, and a list of candidate descriptions. It returns a probability distribution over those candidates using the next-token logits of their position labels. This release contains the **random-derangement SKL (RD-SKL) model with lambda = 0.5 and training seed = 20261001**, fine-tuned from [Qwen2.5-Omni-3B](https://huggingface.co/Qwen/Qwen2.5-Omni-3B).
 
 ## Checkpoint
@@ -78,4 +82,4 @@ The released model is intended for audio-conditioned classification and question
 
 This model is derived from Qwen2.5-Omni-3B and carries the **Qwen Research License Agreement**, supplied in [LICENSE](LICENSE). The upstream agreement grants use for research or evaluation and requires a separate license from Alibaba Cloud for commercial use. See [Notice](Notice) for attribution and a description of modified files.
 
-**Built with Qwen.** The original pretrained weights were modified by AudioJev fine-tuning with RD-SKL, lambda 0.5, seed 20261001. This release does not grant rights beyond the applicable upstream terms.
+**Built with Qwen.** The original pretrained weights were modified by AudioJev fine-tuning with RD-SKL, lambda 0.5, seed 20261001. This release does not grant rights beyond the applicable upstream terms.