LARC：在连续空间做潜在推理，统一多模态模型图像生成新框架
Latent Reasoning in Continuous Space for Unified Multimodal Models
一篇解决图像生成不会"思考"的论文，LARC 把推理搬进连续隐空间，GenEval 上比 BAGEL 高 7 个点，还能测试时扩展。
论文 LARC 针对统一多模态模型（UMMs）中语言链式推理难以迁移到图像生成的问题，将原因归结为离散 token 推理与连续图像生成空间的模态错配。该方法先通过课程式 SFT 把 token 级推理逐步转为连续隐空间推理，再用信息增益 RL 在无真值监督下自我演化。在 GenEval 基准上，LARC 超过 BAGEL 7 个百分点，创下当时最优成绩，并在并行与串行两种测试时扩展策略下均优于 token 式生成。
Latent Reasoning in Continuous Space for Unified Multimodal Models
Unified Multimodal Models (UMMs) achieve remarkable success on diverse multimodal understanding and generation tasks, yet they still struggle to effectively leverage language-based chain-of-thought reasoning for image generation. As a result, existing reasoning-augmented UMMs often fail to inherit the test-time scaling and fine-grained controllability observed in large language models. We attribute this failure to a fundamental modality mismatch: reasoning is performed in a discrete token space, whereas image generation operates in a continuous space. To bridge this gap, we introduce a Latent Reasoning framework in Continuous space (LARC), which alleviates the token-level bottleneck by reasoning over continuous hidden states. Specifically, the training framework consists of two stages: (i) curriculum supervised fine-tuning (SFT), and (ii) information-gain reinforcement learning (RL). First, the curriculum SFT stage gradually converts token-level reasoning into latent reasoning. Subsequently, the information-gain RL stage self-evolves latent reasoning without ground truth supervision. Experiments across diverse text-to-image generation benchmarks show that LARC consistently improves generation quality, prompt following, and compositional fidelity. Notably, LARC achieves state-of-the-art performance on GenEval with a 7%p gain over BAGEL and demonstrates clear test-time scaling behavior, outperforming token-based generation under both parallel and sequential test-time scaling strategies.