Goto

Collaborating Authors

 Media



Rethinking Score Distillation as a Bridge Between Image Distributions David McAllister 1 Songwei Ge2 Jia-Bin Huang 2 David W. Jacobs 2

Neural Information Processing Systems

Score distillation sampling (SDS) has proven to be an important tool, enabling the use of large-scale diffusion priors for tasks operating in data-poor domains. Unfortunately, SDS has a number of characteristic artifacts that limit its usefulness in general-purpose applications. In this paper, we make progress toward understanding the behavior of SDS and its variants by viewing them as solving an optimal-cost transport path from a source distribution to a target distribution.






Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs

Neural Information Processing Systems

To address these issues, we introduced JailTrickBench to evaluate the impact of various attack settings on LLM performance and provide a baseline for jailbreak attacks, encouraging the adoption of a standardized evaluation framework.


Supplementary Materials: FiV A: Fine-grained Visual Attribute Dataset for T ext-to-Image Diffusion Models

Neural Information Processing Systems

Section A. We then introduce additional details on dataset construction in Section B. Further, we Finally, we discuss the limitations and future work of the project in Section D. Please also find the Details on attribute taxonomy and statistics. We visualize the rough distribution of visual attributes and subjects on the left. We also visualize the attribute alignment accuracy via human validation here. Due to space limitations, only 15 sub-subjects are listed for each major-subject. The result shows that Image 4 exhibits inconsistencies, with the reasons provided.