ENTITY
Diffusion Direct Preference Optimization
Diffusion Direct Preference Optimization
PulseAugur coverage of Diffusion Direct Preference Optimization — every cluster mentioning Diffusion Direct Preference Optimization across labs, papers, and developer communities, ranked by signal.
Total · 30d
2
2 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
2
2 over 90d
TIER MIX · 90D
TOPICS
SENTIMENT · 30D
1 day(s) with sentiment data
RECENT · PAGE 1/1 · 2 TOTAL
-
New DIGHT framework enhances humanoid interaction generation in simulations
Researchers have developed DIGHT, a new framework designed to improve the generation of interactions between digital humanoids. This co-adaptive system couples an interaction generator with a humanoid tracking policy. D…
-
New DDSPO method enhances diffusion model alignment with user intent
Researchers have introduced Direct Diffusion Score Preference Optimization (DDSPO), a novel method for training diffusion models to better align with user intent and aesthetic quality. Unlike previous approaches that re…