Jul 2026· International Conference on Generative Artificial Intelligence and Image Processing· Vol 14292, pp. 1429203 - 1429203-5· 0 citations· 20 references
Engineering
TL;DR
This work presents a streamlined Attentive Fusion Network that employs text embeddings as queries to actively harvest pertinent cues from OpenCLIP-encoded visual data, and implements a zero-initialized, learnable Context Gating module that autonomously regulates the blending of both modalities.
Abstract
In the domain of text-to-image generation, diffusion models have demonstrated remarkable creativity. However, they continue to face challenges such as "semantic misalignment" and "detail loss" when tasked with generating images that require specific, fine-grained visual characteristics. Current approaches frequently resort to basic feature stacking or tuning within a single modality; however, these techniques often fail to achieve a delicate balance between embedding intricate reference textures and maintaining the original text-driven semantics. To address this, we propose AttnFusion, a visual feature injection framework based on gated cross-attention. We present a streamlined Attentive Fusion Network that employs text embeddings as queries to actively harvest pertinent cues from OpenCLIP-encoded visual data. To prevent the visual signal from overshadowing the text, we implement a zero-initialized, learnable Context Gating module that autonomously regulates the blending of both modalities. Empirical evaluations on the challenging Food-101 benchmark demonstrate that AttnFusion markedly surpasses leading baselines, including DisenBooth, DreamBooth, and LoRA. It achieves an FID of 48.44, while maintaining superior text-image alignment (CLIP-T score of 29.15), demonstrating its robustness in both visual fidelity and semantic consistency.
This work proposes **VisReflect**, a simple yet effective framework that improves fine-grained perception in long visual contexts through latent visual reflection, which generates continuous visual reflection that represents question-relevant visual features in the latent space.
Chimera, a hybrid visual diffusion backbone with a principled scaling recipe that combines Kimi Delta Attention for long-context state tracking with O(N) complexity, interleaved Multi-head Latent Attention (MLA) for direct global interaction, and modality-aware short convolutions for local spatiotemporal context is introduced.
Chongjian Ge, Hanwen Jiang, Tianyu Wang et al.· 1 citation
Vision-language models (VLMs), such as contrastive language-image pre-training (CLIP), exhibit powerful zero-shot generalization capabilities. Parameter-efficient fine-tuning (PEFT) techniques, notably prompt learning, have been extensively explored to adapt these models to downstream tasks. However, their efficacy remains constrained when transferred to specialized domains like remote sensing. We argue that the bottleneck stems not merely from the limited parameters of prompts, but essentially from the disruption of the input’s original image–text features and the lack of deep cross-modal alignment. In particular, existing methods typically rely on global attention or coarse-grained feature mapping. This inadvertently corrupts the original input representations, thereby impairing the model’s inherent generalization. Furthermore, their isolated unimodal gradient updates fail to bridge the semantic gap inherent in complex remote sensing scenes. To address these challenges, we propose tokenwise prompt-free learning (Tiper), shifting the optimization paradigm from introducing external prompts to precisely recalibrating the critical tokens that govern classification outputs. In particular, Tiper employs a hierarchical learner to supersede global prompts. Crucially, this learner intervenes exclusively on the specific core tokens (i.e., the CLS token in the visual branch and the EOT token in the textual branch), leaving other original input representations unperturbed. This fine-grained strategy effectively balances domain adaptation with the preservation of inherent generalization. Finally, we design the learner as a cross-modal coupled bridge with shared weights, enabling it to synchronously receive gradient feedback from both modalities and fostering profound multimodal collaboration. Extensive experiments validate our method on eight public remote sensing datasets covering diverse scenes and resolutions. In the base-to-new generalization task, Tiper outperforms the strong baseline MaPLe with a significant 3.7% improvement in the harmonic mean (HM). Notably, without relying on any external large-scale domain models, Tiper surpasses the latest domain-specific prompt learning methods (e.g., domain-controlled prompt learning (DCPL), domain prompt learning with quaternion networks (DPLQ)), demonstrating its superior adaptability for remote sensing image scene classification.
Tengfei Gong, Junlin Wu, Yaxioong Chen et al.· IEEE Transactions on Geoscie...· 0 citations
A novel training-free tri-branch denoising framework that effectively decouples structure from style via attention manipulation is proposed that outperforms existing state-of-the-art approaches and achieves consistent improvements in structural consistency and stylistic coherence for image composition.
Xiang Chen, Qingyi Si, Bo Wang et al.· Neural Networks· 1 citation
VLTok is a novel 1D hybrid tokenizer that unifies V isual and L anguage representations in a shared Tok en space through a self-prompted training paradigm, and achieves state-of-the-art performance in both image reconstruction and image generation.
Hualiang Wang, Siming Fu, Wei-Nan Jia et al.· 0 citations