Search papers, labs, and topics across Lattice.
This paper introduces the Tree-of-Thoughts (ToT) reasoning framework for text-to-image in-context learning (T2I-ICL), addressing the challenges posed by compositional reasoning and prompt sensitivity in multimodal large language models. By employing a multi-stage reasoning and selection layer, the framework generates and evaluates multiple hypotheses to construct a more coherent prompt for image synthesis. The results demonstrate that this structured approach significantly improves the consistency and semantic alignment of generated images compared to traditional methods, without requiring additional training or fine-tuning.
Structured multi-branch reasoning in T2I-ICL can dramatically enhance image generation consistency and semantic alignment, outperforming existing prompting strategies.
In text-to-image in-context learning (T2I-ICL), a model has to infer a latent compositional pattern from fewshot demonstrations for generating a query image. Recent studies show that state-of-the-art multimodal large language models struggle with this setting, particularly due to limited compositional reasoning and sensitivity to prompt construction. In this work, we propose a Tree-of-Thoughts (ToT) reasoning framework for T2I-ICL that introduces a multi-stage reasoning and selection layer that generates, evaluates, and selects among multiple candidate hypotheses before constructing the final prompt for image synthesis. By exploring alternative reasoning branches and selecting a coherent interpretation, the proposed approach mitigates prompt ambiguity and compositional errors. We implement the proposed approach in a complete ToT-T2IICL inference pipeline and evaluate it on the CoBSAT benchmark. Both qualitative and quantitative results show that structured multi-branch reasoning leads to more consistent and semantically aligned image generation compared to baseline and Chain-of-Thought prompting strategies, without any additional training or fine-tuning.
