Text-to-image inpainting models often exhibit an unpredictable balance among image coherence and prompt adherence. This rigidity limits their adaptability across diverse scenarios, including coarse masks, non-object, and interaction prompts. Recognizing this instability as an indicator of learned generation diversity, we aim to control model behavior for given objective. We propose Empirical Feature Intervention (EFI), a metric-agnostic framework that precomputes how feature interventions influence evaluation metrics—such as CLIP, Human Preference Score (HPS), and Image Reward (IR). Building on EFI, we introduce FreeCond, a free-of-cost framework that applies two simple input interventions (Image Frequency and Mask Value Modulation), these interventions can be further optimized via Surrogate Intervention Optimization (SIO) based on a surrogate model regressed with precomputed EFI data. FreeCond enables real-time, user-interactive control of pretrained models without retraining or architectural modifications. Also, to benchmark performance on challenging settings, we present FCIBench. Experiments on EditBench, BrushBench, and FCIBench demonstrate that FreeCond substantially improves CLIP, HPS, and IR metrics by up to 22%, 8%, and 54%, respectively.

Text-and-Image-To-Image (TI2I), an extension of Text-To-Image (T2I), integrates image inputs with textual instructions to enhance image generation. Existing methods often partially utilize image inputs, focusing on specific elements like objects or styles, or they experience a decline in generation quality with complex, multi-image instructions. To overcome these challenges, we introduce Training-Free Text-and-Image-to-Image (TF-TI2I), which adapts cutting-edge T2I models such as SD3 without the need for additional training. Our method capitalizes on the MM-DiT architecture, in which we point out that textual tokens can implicitly learn visual information from vision tokens. We enhance this interaction by extracting a condensed visual representation from reference images, facilitating selective information sharing through Reference Contextual Masking -- this technique confines the usage of contextual tokens to instruction-relevant visual information. Additionally, our Winner-Takes-All module mitigates distribution shifts by prioritizing the most pertinent references for each vision token. Addressing the gap in TI2I evaluation, we also introduce the FG-TI2I Bench, a comprehensive benchmark tailored for TI2I and compatible with existing T2I methods. Our approach shows robust performance across various benchmarks, confirming its effectiveness in handling complex image-generation tasks.

Direct preference optimization (DPO) methods have shown strong potential in aligning text-to-image diffusion models with human preferences by training on paired comparisons. These methods improve training stability by avoiding the REINFORCE algorithm but still struggle with challenges such as accurately estimating image probabilities due to the non-linear nature of the sigmoid function and the limited diversity of offline datasets. In this paper, we introduce Diffusion Denoising Ranking Optimization (Diffusion-DRO), a new preference learning framework grounded in inverse reinforcement learning. Diffusion-DRO removes the dependency on a reward model by casting preference learning as a ranking problem, thereby simplifying the training objective into a denoising formulation and overcoming the non-linear estimation issues found in prior methods. Moreover, Diffusion-DRO uniquely integrates offline expert demonstrations with online policy-generated negative samples, enabling it to effectively capture human preferences while addressing the limitations of offline data. Comprehensive experiments show that Diffusion-DRO delivers improved generation quality across a range of challenging and unseen prompts, outperforming state-of-the-art baselines in both both quantitative metrics and user studies. Our source code and pre-trained models are available at https://github.com/basiclab/DiffusionDRO.

Synthetic Aperture Radar (SAR) has emerged as an indispensable tool for maritime surveillance, providing reliable all-weather, day-and-night imaging capabilities. However, automated ship recognition in SAR imagery presents significant challenges, particularly due to variations in patch sizes, with small-size SAR image patches posing the greatest difficulties. To address this challenge, we propose Radiometric Resolution and Scale-aware Masked Autoencoder (RSMAE), a novel framework designed for SAR ship recognition. Our method incorporates three key innovations: (1) a scale-aware augmentation that adapts to images of varying image sizes for masked image modeling, enabling the model to learn multi-scale features and reconstruct fine-grained details lost during upscaling; (2) a foreground-background balanced masking strategy that independently handles the ship region and its surrounding region, ensuring the ship area is neither over-masked nor under-masked; and (3) a radiometric resolution-aware (RadRe-aware) reweighting mechanism that leverages SAR-specific radiometric characteristics to enhance reconstruction of challenging samples. Experimental results on the OpenSARShip dataset demonstrate that the proposed RSMAE consistently outperforms state-of-the-art methods by at least 2.07% in terms of recognition accuracy. These findings highlight the robustness and efficiency of the proposed RSMAE, making it a compelling solution for SAR ship recognition tasks.

Given an untrimmed video and a natural language query, video moment retrieval (VMR) aims to retrieve video moments described by the query. However, most existing VMR methods assume a one-to-one mapping between the input query and the target video moment (single-target VMR), disregarding the possibility that a video may contain multiple target moments that match the query description (multi-target VMR). Previous methods tackle multi-target VMR by incorporating false negative moments with the original target moment for multi-target training. However, existing methods cannot properly work when no false negative moments exist in the video, or when the identified false negative moments are noisy but are still being utilized as pseudo-labels. In this paper, we propose to tackle multi-target VMR by Semantic Fusion Augmentation and Semantic Boundary Detection (SFABD). Specifically, we use feature-level augmentation to generate augmented target moments, along with an intra-video contrastive loss to ensure feature consistency. Meanwhile, we perform semantic boundary detection to adaptively remove all false negatives from the negative set of contrastive loss to avoid semantic confusion. Extensive experiments conducted on Charades-STA, ActivityNet Captions, and QVHighlights show that our method achieves state-of-the-art performance on multi-target metrics and single-target metrics. The source code is available at https://github.com/basiclab/SFABD.

In this paper, we propose a novel normalization method called gradient normalization (GN) to tackle the training instability of Generative Adversarial Networks (GANs) caused by the sharp gradient space. Unlike existing work such as gradient penalty and spectral normalization, the proposed GN only imposes a hard 1-Lipschitz constraint on the discriminator function, which increases the capacity of the discriminator. Moreover, the proposed gradient normalization can be applied to different GAN architectures with little modification. Extensive experiments on four datasets show that GANs trained with gradient normalization outperform existing methods in terms of both Frechet Inception Distance and Inception Score.

With the rapid proliferation of online media sources and published news, headlines have become increasingly important for attracting readers to news articles, since users may be overwhelmed with the massive information. In this paper, we generate inspired headlines that preserve the nature of news articles and catch the eye of the reader simultaneously. The task of inspired headline generation can be viewed as a specific form of Headline Generation (HG) task, with the emphasis on creating an attractive headline from a given news article. To generate inspired headlines, we propose a novel framework called POpularity-Reinforced Learning for inspired Headline Generation (PORL-HG). PORL-HG exploits the extractive-abstractive architecture with 1) Popular Topic Attention (PTA) for guiding the extractor to select the attractive sentence from the article and 2) a popularity predictor for guiding the abstractor to rewrite the attractive sentence. Moreover, since the sentence selection of the extractor is not differentiable, techniques of reinforcement learning (RL) are utilized to bridge the gap with rewards obtained from a popularity score predictor. Through quantitative and qualitative experiments, we show that the proposed PORL-HG significantly outperforms the state-of-the-art headline generation models in terms of attractiveness evaluated by both human (71.03%) and the predictor (at least 27.60%), while the faithfulness of PORL-HG is also comparable to the state-of-the-art generation model.

In this demonstration, we present a real-time system that addresses three essential issues of large-scale image object retrieval: 1) image object retrieval-facilitating pseudo-objects in inverted indexing and novel object-level pseudo-relevance feedback for retrieval accuracy; 2) time efficiency-boosting the time efficiency and memory usage of object-level image retrieval by a novel inverted indexing structure and efficient query evaluation; 3) recall rate improvement--mining semantically relevant auxiliary visual features through visual and textual clusters in an unsupervised and scalable (i.e., MapReduce) manner. We are able to search over one-million image collection in respond to a user query in 121ms, with significantly better accuracy (+99%) than the traditional bag-of-words model.