TMPO uses Softmax Trajectory Balance to match policy probabilities over multiple trajectories to a Boltzmann reward distribution, improving diversity by 9.1% in diffusion alignment tasks.
FLUX.https://github.com/black-forest-labs/flux
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
A sparse set of massive activation channels in DiTs carries semantic information, proven critical by disruption tests, spatially aligned with image subjects via clustering, and transferable for semantic interpolation between prompts.
BLK-Assist is a three-part framework (Conceptor for sketches, Stencil for transparent assets, Upscale for high-res outputs) that fine-tunes public diffusion models on one artist's proprietary corpus for style-faithful generative co-creation.
RLDX-1 outperforms frontier VLAs such as π0.5 and GR00T N1.6 on dexterous manipulation benchmarks, reaching 86.8% success on ALLEX humanoid tasks versus around 40% for the baselines.
citing papers explorer
-
TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment
TMPO uses Softmax Trajectory Balance to match policy probabilities over multiple trajectories to a Boltzmann reward distribution, improving diversity by 9.1% in diffusion alignment tasks.
-
Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers
A sparse set of massive activation channels in DiTs carries semantic information, proven critical by disruption tests, spatially aligned with image subjects via clustering, and transferable for semantic interpolation between prompts.
-
BLK-Assist: A Methodological Framework for Artist-Led Co-Creation with Generative AI Models
BLK-Assist is a three-part framework (Conceptor for sketches, Stencil for transparent assets, Upscale for high-res outputs) that fine-tunes public diffusion models on one artist's proprietary corpus for style-faithful generative co-creation.
-
RLDX-1 Technical Report
RLDX-1 outperforms frontier VLAs such as π0.5 and GR00T N1.6 on dexterous manipulation benchmarks, reaching 86.8% success on ALLEX humanoid tasks versus around 40% for the baselines.