Gen-Searcher is the first trained search-augmented image generation agent using SFT followed by GRPO reinforcement learning with dual text-image rewards, delivering 15-16 point gains on knowledge-intensive benchmarks.
Lumina- image 2.0: A unified and efficient image generative framework
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
LingBot-Video is an open-source MoE video foundation model for embodied intelligence that scales to 120B parameters, integrates robot data, and uses multi-dimensional RL to improve physical plausibility.
citing papers explorer
-
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Gen-Searcher is the first trained search-augmented image generation agent using SFT followed by GRPO reinforcement learning with dual text-image rewards, delivering 15-16 point gains on knowledge-intensive benchmarks.
-
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
LingBot-Video is an open-source MoE video foundation model for embodied intelligence that scales to 120B parameters, integrates robot data, and uses multi-dimensional RL to improve physical plausibility.