Exploring the frontier of AI data, evaluation, benchmarks, and open-source infrastructure.
Title
Category
Venue
ScalingAR: Scaling Confidence for Autoregressive Image Generation
ZODA-contributed work ScalingAR was accepted to ICML 2026. It proposes a test-time scaling framework for autoregressive image generation that leverages the model’s own confidence signals to improve generation quality and efficiency.
Multimodal, Image Generation
2026AlignVid: Taming Visual Dominance via Training-Free Attention Modulation in Text-guided Image-to-Video Generation
ZODA-contributed work AlignVid was accepted to ICML 2026. It introduces a training-free, inference-time attention modulation method that enables image-to-video models to follow text-based editing instructions more accurately.
Multimodal, Video Generation, Evaluation and Alignment
2026Show, Don't Tell: Morphing Latent Reasoning into Image Generation
ZODA-contributed work LatentMorph was accepted to ICML 2026. It integrates implicit latent-space reasoning into text-to-image generation, allowing models to dynamically refine their outputs during the generation process.
Multimodal, Image Generation, Reasoning
2026