We introduce a novel, training-free approach for enhancing alignment in Transformer-based Text-Guided Diffusion Models (TGDMs). Existing TGDMs often struggle to generate semantically aligned images, particularly when dealing with complex text prompts or multi-concept attribute binding challenges. Previous U-Net-based methods primarily optimized the latent space, but their direct application to Transformer-based architectures has shown limited effectiveness. Our method addresses these challenges by directly optimizing cross-attention maps during the generation process. Specifically, we introduce Self-Coherence Guidance, a method that dynamically refines attention maps using masks derived from previous denoising steps, ensuring precise alignment without additional training. To validate our approach, we constructed more challenging benchmarks for evaluating coarse-grained attribute binding, fine-grained attribute binding, and style binding. Experimental results demonstrate the superior performance of our method, significantly surpassing other state-of-the-art methods across all evaluated tasks. Our code is available at https://scg-diffusion.github.io/scg-diffusion.

Large Language Models (LLMs) have demonstrated great potential for assisting developers in their daily development.However, most research focuses on generating correct code, how to use LLMs to generate personalized code has seldom been investigated.To bridge this gap, we proposed MPCODER (Multi-user Personalized Code Generator) to generate personalized code for multiple users.To better learn coding style features, we utilize explicit coding style residual learning to capture the syntax code style standards and implicit style learning to capture the semantic code style conventions.We train a multi-user style adapter to better differentiate the implicit feature representations of different users through contrastive learning, ultimately enabling personalized code generation for multiple users.We further propose a novel evaluation metric for estimating similarities between codes of different coding styles.The experimental results show the effectiveness of our approach for this novel task.The code and dataset are available at https://github.com/455849940/MPCoder.CodeLlama output layer CodeLlama Decoder Block N Neural network Neural network (a) Multi-user Style Adapter Style output layer Tuned Frozen (b) MPCoder Style Information Style hidden state of user interaction record Style Hidden States Space CodeLlama Decoder Block 1 CodeLlama Decoder Block N CodeLlama Decoder Layer Implicit Style Features Question Code Explicit Style Features Training data in batch CodeLlama Decoder Block ......

Understanding human emotions is fundamental to enhancing human-computer interaction, especially for embodied agents that mimic human behavior. Traditional emotion analysis often takes a third-person perspective, limiting the ability of agents to interact naturally and empathetically. To address this gap, this paper presents $E^3$ for Exploring Embodied Emotion, the first massive first-person view video dataset. $E^3$ contains more than $50$ hours of video, capturing $8$ different emotion types in diverse scenarios and languages. The dataset features videos recorded by individuals in their daily lives, capturing a wide range of real-world emotions conveyed through visual, acoustic, and textual modalities. By leveraging this dataset, we define $4$ core benchmark tasks - emotion recognition, emotion classification, emotion localization, and emotion reasoning - supported by more than $80$k manually crafted annotations, providing a comprehensive resource for training and evaluating emotion analysis models. We further present Emotion-LlaMa, which complements visual modality with acoustic modality to enhance the understanding of emotion in first-person videos. The results of comparison experiments with a large number of baselines demonstrate the superiority of Emotion-LlaMa and set a new benchmark for embodied emotion analysis. We expect that $E^3$ can promote advances in multimodal understanding, robotics, and augmented reality, and provide a solid foundation for the development of more empathetic and context-aware embodied agents.