LAION-C supplies six novel corruptions that stay OOD for web-scale training sets and demonstrates that leading models now rival or exceed human robustness on them.
The role of imagenet classes in fr \’echet inception distance
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
representative citing papers
A diffusion-trained maximum entropy model uses 512 learned statistics to synthesize visual textures at quality matching or exceeding prior models that rely on ~177k statistics.
SatSplatDiff combines depth supervision and shadow-guided generative refinement with 2DGS to reduce geometric MAE by up to 18% and improve visual fidelity by 28-45% on satellite datasets while enabling 5x resolution enhancement.
A diffusion-based hairstyle transfer method that uses a region-specific training loss to make cross-attention produce a source-aligned hair mask for pose-robust inpainting.
Dash2Sim recovers metric geo-referenced 4D scenes from in-the-wild monocular dashcam videos to enable the ROADWork4D benchmark, revealing that current closed-loop planners fail on work zone lane changes.
BadRDM is a backdoor attack on retrieval-augmented diffusion models that poisons the retrieval database with toxicity surrogates and uses multimodal contrastive learning to force toxic generations from text triggers while preserving benign performance.
FID improves with better samples only on concentrated reference datasets but can worsen on dispersed ones, as shown by density and effective rank in a controlled study across six datasets.
Automatic metrics such as FID are misaligned with human perception and downstream segmentation performance for Earth observation datasets and synthetic counterparts.
LLM safety evaluations are hindered by noise in dataset curation, automated red-teaming, response generation, and LLM-judge evaluation, making fair comparisons difficult and slowing progress.
citing papers explorer
-
LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models
LAION-C supplies six novel corruptions that stay OOD for web-scale training sets and demonstrates that leading models now rival or exceed human robustness on them.
-
Learning a Maximum Entropy Model for Visual Textures using Diffusion
A diffusion-trained maximum entropy model uses 512 learned statistics to synthesize visual textures at quality matching or exceeding prior models that rely on ~177k statistics.
-
SatSplatDiff: Geometry-preserving generative refinement for high-fidelity satellite Gaussian Splatting
SatSplatDiff combines depth supervision and shadow-guided generative refinement with 2DGS to reduce geometric MAE by up to 18% and improve visual fidelity by 28-45% on satellite datasets while enabling 5x resolution enhancement.
-
H-Adapter: Pose-Robust Hairstyle Transfer via Attention-Derived, Source-Aligned Hair Masks
A diffusion-based hairstyle transfer method that uses a region-specific training loss to make cross-attention produce a source-aligned hair mask for pose-robust inpainting.
-
Dash2Sim: Closed-Loop Driving Simulation from in-the-wild Dashcam Videos
Dash2Sim recovers metric geo-referenced 4D scenes from in-the-wild monocular dashcam videos to enable the ROADWork4D benchmark, revealing that current closed-loop planners fail on work zone lane changes.
-
Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models
BadRDM is a backdoor attack on retrieval-augmented diffusion models that poisons the retrieval database with toxicity surrogates and uses multimodal contrastive learning to force toxic generations from text triggers while preserving benign performance.
-
Rethinking FID Through the Geometry of the Reference Dataset
FID improves with better samples only on concentrated reference datasets but can worsen on dispersed ones, as shown by density and effective rank in a controlled study across six datasets.
-
Benchmarking the Alignment of Data-Quality Metrics, Human Judgment and Land-Cover Segmentation Performance for Earth Observation
Automatic metrics such as FID are misaligned with human perception and downstream segmentation performance for Earth observation datasets and synthetic counterparts.
-
LLM-Safety Evaluations Lack Robustness
LLM safety evaluations are hindered by noise in dataset curation, automated red-teaming, response generation, and LLM-judge evaluation, making fair comparisons difficult and slowing progress.