6 papers
Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation
Ku Onoda, Paavo Parmas, Hiroki Furuta +4
Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset of visually distinct modes. Th…
Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback
Hiroki Furuta, Heiga Zen, Dale Schuurmans +4
Large text-to-video models hold immense potential for a wide range of downstream applications. However, they struggle to accurately depict dynamic object interactions, often result…
MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation
Yuta Oshima, Daiki Miyake, Kohsei Matsutani +4
Recent text-to-image generation models have acquired the ability of multi-reference generation and editing; that is, to inherit the appearance of subjects from multiple reference i…
WorldPack: Dynamic Frame Compression for Long-context Video World Modeling
Yuta Oshima, Yusuke Iwasawa, Masahiro Suzuki +2
Video world models have attracted significant attention for their ability to produce high-fidelity future visual observations conditioned on past observations and navigation action…
Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search
Yuta Oshima, Masahiro Suzuki, Yutaka Matsuo +1
The remarkable progress in text-to-video diffusion models enables the generation of photorealistic videos, although the content of these generated videos often includes unnatural m…
Geometric-Averaged Preference Optimization for Soft Preference Labels
Hiroki Furuta, Kuang-Huei Lee, Shixiang Shane Gu +4
Many algorithms for aligning LLMs with human preferences assume that human preferences are binary and deterministic. However, human preferences can vary across individuals, and the…