Related papers: Test-Time Conditioning with Representation-Aligned…

Test-time alignment (TTA) aims to adapt models to specific rewards during inference. However, existing methods tend to either under-optimise or over-optimise (reward hack) the target reward function. We propose Null-Text Test-Time Alignment…

Diffusion model alignment aims to bridge the gap between generated outputs and human preferences by enhancing both semantic consistency with textual prompts and overall visual quality. Existing alignment methods face a challenging…

We introduce a novel method for conditioning diffusion-based image synthesis models with heterogeneous graph data. Existing approaches typically incorporate conditioning variables directly into model architectures, either through…

We propose selective debiasing -- an inference-time safety mechanism designed to enhance the overall model quality in terms of prediction performance and fairness, especially in scenarios where retraining the model is impractical. The…

In the realm of Text-attributed Graphs (TAGs), traditional graph neural networks (GNNs) often fall short due to the complex textual information associated with each node. Recent methods have improved node representations by leveraging large…

Test-time adaptation (TTA) aims to correct performance degradation of deep models under distribution shifts by updating models or inputs using unlabeled test data. Input-only diffusion-based TTA methods improve robustness for classification…

Person re-identification (re-id), which aims to retrieve images of the same person in a given image from a database, is one of the most practical image recognition applications. In the real world, however, the environments that the images…

Diffusion models have achieved remarkable success as generative models. However, even a well-trained model can accumulate errors throughout the generation process. These errors become particularly problematic when arbitrary guidance is…

Text-to-image generation has advanced rapidly, yet aligning complex textual prompts with generated visuals remains challenging, especially with intricate object relationships and fine-grained details. This paper introduces Fast Prompt…

Scene Graph Generation (SGG) has achieved significant progress recently. However, most previous works rely heavily on fixed-size entity representations based on bounding box proposals, anchors, or learnable queries. As each representation's…

Recent generative models based on score matching and flow matching have significantly advanced generation tasks, but their potential in discriminative tasks remains underexplored. Previous approaches, such as generative classifiers, have…

In self-supervised spatio-temporal representation learning, the temporal resolution and long-short term characteristics are not yet fully explored, which limits representation capabilities of learned models. In this paper, we propose a…

Generative models have recently undergone significant advancement due to the diffusion models. The success of these models can be often attributed to their use of guidance techniques, such as classifier or classifier-free guidance, which…

Diffusion models deliver high quality in image synthesis but remain expensive during training and inference. Recent works have leveraged the inherent redundancy in visual content to make training more affordable by training only on a subset…

Graph Neural Networks frequently exhibit significant performance degradation in the out-of-distribution test scenario. While test-time training (TTT) offers a promising solution, existing Parameter Finetuning (PaFT) paradigm suffer from…

Existing test-time prompt tuning (TPT) methods focus on single-modality data, primarily enhancing images and using confidence ratings to filter out inaccurate images. However, while image generation models can produce visually diverse…

The ability to scene understanding in adverse visual conditions, e.g., nighttime, has sparked active research for RGB-Thermal (RGB-T) semantic segmentation. However, it is essentially hampered by two critical problems: 1) the day-night gap…

Conditional GANs are widely used in translating an image from one category to another. Meaningful conditions to GANs provide greater flexibility and control over the nature of the target domain synthetic data. Existing conditional GANs…

Scene Graph Generation (SGG) provides basic language representation of visual scenes, requiring models to grasp complex and diverse semantics between objects. This complexity and diversity in SGG leads to underrepresentation, where parts of…

Diffusion models has emerged as a powerful framework for tasks like image controllable generation and dense prediction. However, existing models often struggle to capture underlying semantics (e.g., edges, textures, shapes) and effectively…