Updates for arXiv release

README.md

@@ -17,10 +17,15 @@ license_link: LICENSE.md
 
 # ReSWD: ReSTIR‘d, not shaken. Combining Reservoir Sampling and Sliced Wasserstein Distance for Variance Reduction.
 
-<a href="https://reservoirswd.github.io/"><img src="https://img.shields.io/badge/Project%20Page-5CE1BC.svg"></a> <a href="https://reservoirswd.github.io/static/paper.pdf"><img src="https://img.shields.io/badge/Arxiv-2408.00653-B31B1B.svg"></a> <a href="https://huggingface.co/spaces/stabilityai/reswd"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Gradio%20Demo-Huggingface-orange"></a>
-
 This is the official codebase for **ReSWD**, a state-of-the-art algorithm for distribution matching with reduced variance. It has several applications (such as diffusion guidance or color matching).
 
+
+* **Repository**: [https://github.com/Stability-AI/ReSWD](https://github.com/Stability-AI/ReSWD)
+* **Tech report**: [https://arxiv.org/pdf/2510.01061](https://arxiv.org/pdf/2510.01061)
+* **Video summary**: [https://youtu.be/ckcSgf0s-jI](https://youtu.be/ckcSgf0s-jI)
+* **Project page**: [https://reservoirswd.github.io/](https://reservoirswd.github.io/)
+* **arXiv page**: [https://arxiv.org/abs/2510.01061](https://arxiv.org/abs/2510.01061)
+
 ## Citation
 
 ```BibTeX

app.py

@@ -10,7 +10,7 @@ with gr.Blocks() as demo:
         # ReSWD
 
         **[Project Page](https://reservoirswd.github.io/)** | 
-        **[Paper](https://reservoirswd.github.io/static/paper.pdf)** |
+        **[Paper](https://arxiv.org/abs/2510.01061)** |
         **[GitHub](https://github.com/Stability-AI/ReSWD)**
 
         ReSTIR‘d, not shaken. Combining Reservoir Sampling and Sliced Wasserstein

src/gradio_demo/sw_guidance.py

@@ -32,7 +32,7 @@ models = {
     "stabilityai/stable-diffusion-3.5-large-turbo": {
         "num_inference_steps": 4,
         "guidance_scale": 1.0,
-        "sw_u_lr": np.log10(4e-3),
+        "sw_u_lr": np.log10(5e-3),
         "sw_steps": 6,
         "cfg_rescale_phi": 0.65,
     },