Automated report

current/2024-02-23 Consolidating Attention Features for Multi-view Image Editing.yaml

@@ -1,11 +1,17 @@
-date: "2024-02-23"
 author: Or Patashnik
-title: Consolidating Attention Features for Multi-view Image Editing
-thumbnail: https://cdn-uploads.huggingface.co/production/uploads/60f1abe7544c2adfd699860c/-4na-GRPXDJonefyY3jmQ.mp4
+date: '2024-02-23'
 link: https://huggingface.co/papers/2402.14792
-summary: 'Large-scale text-to-image models enable a wide range of image editing techniques, using text prompts or even spatial controls. However, applying these editing methods to multi-view images depicting a single scene leads to 3D-inconsistent results. In this work, we focus on spatial control-based geometric manipulations and introduce a method to consolidate the editing process across various views. We build on two insights: (1) maintaining consistent features throughout the generative process helps...'
 opinion: placeholder
+summary: 'Large-scale text-to-image models enable a wide range of image editing techniques,
+  using text prompts or even spatial controls. However, applying these editing methods
+  to multi-view images depicting a single scene leads to 3D-inconsistent results.
+  In this work, we focus on spatial control-based geometric manipulations and introduce
+  a method to consolidate the editing process across various views. We build on two
+  insights: (1) maintaining consistent features throughout the generative process
+  helps...'
 tags:
-    - Computer Vision
-    - Deep Learning
-    - Explainable AI and Interpretability
+- Computer Vision
+- Deep Learning
+- Explainable AI and Interpretability
+thumbnail: https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/assets/2402.14792.gif?raw=true
+title: Consolidating Attention Features for Multi-view Image Editing

current/2024-02-23 GaussianPro: 3D Gaussian Splatting with Progressive Propagation.yaml

@@ -1,10 +1,13 @@
-date: "2024-02-23"
 author: Kai Cheng
-title: 'GaussianPro: 3D Gaussian Splatting with Progressive Propagation'
-thumbnail: https://cdn-uploads.huggingface.co/production/uploads/60f1abe7544c2adfd699860c/DoTO-vmhmEZ46b1NEJMX7.mp4
+date: '2024-02-23'
 link: https://huggingface.co/papers/2402.14650
-summary: This paper proposes a method called GaussianPro which improves the quality of 3D Gaussian splatting, a technique used for real-time rendering, by using a progressive propagation strategy to guide the creation of new 3D Gaussians from the existing reconstructed geometry of the scene....
 opinion: placeholder
+summary: This paper proposes a method called GaussianPro which improves the quality
+  of 3D Gaussian splatting, a technique used for real-time rendering, by using a progressive
+  propagation strategy to guide the creation of new 3D Gaussians from the existing
+  reconstructed geometry of the scene....
 tags:
-    - Computer Vision
-    - Deep Learning
+- Computer Vision
+- Deep Learning
+thumbnail: https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/assets/2402.14650.gif?raw=true
+title: 'GaussianPro: 3D Gaussian Splatting with Progressive Propagation'

current/2024-02-23 GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusion.yaml

@@ -1,9 +1,13 @@
-date: "2024-02-23"
 author: Xueyi Liu
-title: 'GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusion'
-thumbnail: https://cdn-uploads.huggingface.co/production/uploads/60f1abe7544c2adfd699860c/wwLwrz8tXVgFmPhnk5Sde.mp4
+date: '2024-02-23'
 link: https://huggingface.co/papers/2402.14810
-summary: This paper proposes a novel method called GeneOH Diffusion to denoise hand-object interactions by using a contact-centric representation called GeneOH and a domain-generalizable denoising scheme. The method shows effectiveness on four benchmarks with significant domain variations and has potential for various downstream applications....
 opinion: placeholder
+summary: This paper proposes a novel method called GeneOH Diffusion to denoise hand-object
+  interactions by using a contact-centric representation called GeneOH and a domain-generalizable
+  denoising scheme. The method shows effectiveness on four benchmarks with significant
+  domain variations and has potential for various downstream applications....
 tags:
-    - Computer Vision
+- Computer Vision
+thumbnail: https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/assets/2402.14810.gif?raw=true
+title: 'GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising
+  via Denoising Diffusion'

current/2024-02-23 OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement.yaml

@@ -1,11 +1,14 @@
-date: "2024-02-23"
 author: Tianyu Zheng
-title: 'OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement'
-thumbnail: https://cdn-uploads.huggingface.co/production/uploads/60f1abe7544c2adfd699860c/J9Z7fBm_fC6eQV8-yjdmk.mp4
+date: '2024-02-23'
 link: https://huggingface.co/papers/2402.14658
-summary: This paper introduces OpenCodeInterpreter, an open-source code system that can generate, execute, and refine code. It integrates execution and human feedback for dynamic code refinement and outperforms GPT-4 in key benchmarks with the help of synthesized human feedback....
 opinion: placeholder
+summary: This paper introduces OpenCodeInterpreter, an open-source code system that
+  can generate, execute, and refine code. It integrates execution and human feedback
+  for dynamic code refinement and outperforms GPT-4 in key benchmarks with the help
+  of synthesized human feedback....
 tags:
-    - Deep Learning
-    - Natural Language Processing
-    - Human-Computer Interaction (HCI) and User Interfaces
+- Deep Learning
+- Natural Language Processing
+- Human-Computer Interaction (HCI) and User Interfaces
+thumbnail: https://github.com/deep-diver/hf-daily-paper-newsletter/blob/main/assets/2402.14658.gif?raw=true
+title: 'OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement'