Understanding the performance gap between online and offline alignment algorithms Paper • 2405.08448 • Published May 14 • 14
DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation Paper • 2406.16855 • Published Jun 24 • 54
DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling Paper • 2406.11617 • Published Jun 17 • 8
Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming Paper • 2406.11654 • Published Jun 17 • 6
Reward Steering with Evolutionary Heuristics for Decoding-time Alignment Paper • 2406.15193 • Published Jun 21 • 12
Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations Paper • 2406.11801 • Published Jun 17 • 15
Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization Paper • 2404.09956 • Published Apr 15 • 11