Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+figure/before_after_train_lcb_02.png filter=lfs diff=lfs merge=lfs -text
+figure/benchmark_accuracy_1130.png filter=lfs diff=lfs merge=lfs -text
+figure/inference_pipeline_teaser_02.png filter=lfs diff=lfs merge=lfs -text
+figure/teaser_draft_02.png filter=lfs diff=lfs merge=lfs -text
+figure/train_reward_response_length_1130.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -22,7 +22,7 @@ We open-source model checkpoints, training data, and the full inference pipeline
 
 <p align="center">
   <img src="figure/teaser_draft_02.png" width="48%" />
-  <img src="[figure/before_after_train_lcb_02.png](https://github.com/stepfun-ai/PaCoRe/blob/main/figure/before_after_train_lcb_02.png)" width="48%" />
+  <img src="figure/before_after_train_lcb_02.png" width="48%" />
 </p>
 
 *Figure 1 | Parallel Coordinated Reasoning (PaCoRe) performance.  Left: On HMMT 2025, PaCoRe-8B demonstrates remarkable test-time scaling, yielding steady gains and ultimately surpassing GPT-5. Right: On LiveCodeBench, the RLVR-8B model fails to leverage increased test-time compute, while PaCoRe-8B model effectively unlocks substantial gains as the test-time compute increases.*
@@ -184,4 +184,4 @@ If you are interested in our project and would like to contribute to the reasone
   year={2025},
   url={[https://github.com/stepfun-ai/PaCoRe/blob/main/pacore_report.pdf](https://github.com/stepfun-ai/PaCoRe/blob/main/pacore_report.pdf)},
 }
-```
+```