Update README.md

README.md

@@ -157,6 +157,24 @@ On LMEB-Dialogue, a compact embedding model paired with our Nano reranker, which
 ![lmeb](./assets/lmeb.jpg)
 ![lmeb_emb](./assets/lmeb_emb.jpg)
 
+#### Ablation on multi-stage training
+
+Across all three model sizes and all seven compression ratios, performance on BEIR and MIRACL improves consistently from Stage 1 to Stage 3, demonstrating the effectiveness of our multi-stage training pipeline. Concretely, Stage 1 establishes a robust foundation for document reranking, distillation in Stage 2 substantially improves performance, and Stage 3 yields further modest gains. More importantly, robustness to compression generally improves across the three training stages. For example, from Stage 1 to Stage 3, the performance retention of KaLM-Reranker-V1-Nano at r = 128 relative to r = 2 increases from 92.88% to 93.80% on BEIR and from 90.93% to 92.15% on MIRACL.
+
+![lmeb_emb](./assets/ablation.jpg)
+
+![kalm-reranker-v1-r2 training](./assets/training.jpg)
+
+#### Potential of test-time compute scaling 
+Results show that this multi-stage strategy largely preserves reranking effectiveness while reducing the estimated online
+computation cost by a factor of several. For example, on BEIR, KaLM-Reranker-V1-Small
+achieves an average nDCG@10 of 61.11 under setting (c), compared with 61.17 under setting (a),
+while reducing the estimated relative serving cost from 8.65x to 2.75x. Interestingly, settings (c)
+and (d) outperform setting (a) on some tasks, suggesting that reranking more candidates at a low
+compression ratio does not necessarily improve reranking quality.
+
+![test-time-compute](./assets/test-time-compute.jpg)
+
 ## Usage
 ### Using Sentence Transformers
 
@@ -447,24 +465,6 @@ T5Gemma2 semantic forward still runs through Transformers. It is not vLLM's
 native HTTP `/score` implementation or a complete vLLM-native kernel port.
 See [the complete installation, API and troubleshooting guide](./vllm_support/README.md).
 
-#### Ablation on multi-stage training
-
-Across all three model sizes and all seven compression ratios, performance on BEIR and MIRACL improves consistently from Stage 1 to Stage 3, demonstrating the effectiveness of our multi-stage training pipeline. Concretely, Stage 1 establishes a robust foundation for document reranking, distillation in Stage 2 substantially improves performance, and Stage 3 yields further modest gains. More importantly, robustness to compression generally improves across the three training stages. For example, from Stage 1 to Stage 3, the performance retention of KaLM-Reranker-V1-Nano at r = 128 relative to r = 2 increases from 92.88% to 93.80% on BEIR and from 90.93% to 92.15% on MIRACL.
-
-![lmeb_emb](./assets/ablation.jpg)
-
-![kalm-reranker-v1-r2 training](./assets/training.jpg)
-
-#### Potential of test-time compute scaling 
-Results show that this multi-stage strategy largely preserves reranking effectiveness while reducing the estimated online
-computation cost by a factor of several. For example, on BEIR, KaLM-Reranker-V1-Small
-achieves an average nDCG@10 of 61.11 under setting (c), compared with 61.17 under setting (a),
-while reducing the estimated relative serving cost from 8.65x to 2.75x. Interestingly, settings (c)
-and (d) outperform setting (a) on some tasks, suggesting that reranking more candidates at a low
-compression ratio does not necessarily improve reranking quality.
-
-![test-time-compute](./assets/test-time-compute.jpg)
-
 
 ### Acknowledgements
 We sincerely thank `jina-reranker-v3` and `Qwen3-Reranker` for their valuable inspiration and contributions to the reranking community, from which we have learned a lot.