Related papers: EraseLoRA: MLLM-Driven Foreground Exclusion and Ba…

We present YOEO, an approach for object erasure. Unlike recent diffusion-based methods which struggle to erase target objects without generating unexpected content within the masked regions due to lack of sufficient paired training data and…

Image retargeting aims at altering an image size while preserving important content and minimizing noticeable distortions. However, previous image retargeting methods create outputs that suffer from artifacts and distortions. Besides, most…

Concept unlearning aims to erase a target concept from a pretrained text-to-image diffusion model without retraining. Closed-form methods are attractive in this setting because they apply a single deterministic edit to the cross-attention…

Vision-language-action (VLA) models are emerging as embodied foundation models for robotic manipulation, but their deployment introduces a new unlearning challenge: removing unsafe, spurious, or privacy-sensitive behaviors without degrading…

Text-guided video editing, particularly for object removal and addition, remains a challenging task due to the need for precise spatial and temporal consistency. Existing methods often rely on auxiliary masks or reference images for editing…

The traditional image inpainting task aims to restore corrupted regions by referencing surrounding background and foreground. However, the object erasure task, which is in increasing demand, aims to erase objects and generate harmonious…

Text-to-image diffusion models have shown great success in generating high-quality text-guided images. Yet, these models may still fail to semantically align generated images with the provided text prompts, leading to problems like…

Multimodal large language models (MLLMs) have attracted increasing attention in the past few years, but they may still generate descriptions that include objects not present in the corresponding images, a phenomenon known as object…

Modern large language models increasingly require long contexts for reasoning and multi-document tasks, but attention's quadratic complexity creates a severe computational bottleneck. We present Block-Sparse FlashAttention (BSFA), a drop-in…

Vision-language models (VLMs) raise growing concerns about privacy, copyright, and bias, motivating machine unlearning to remove sensitive knowledge. However, existing methods primarily fine-tune the language decoder, leading to superficial…

Existing video omnimatte methods typically rely on slow, multi-stage, or inference-time optimization pipelines that fail to fully exploit powerful generative priors, producing suboptimal decompositions. Our key insight is that, if a video…

Machine unlearning is an emerging technology that removes a subset of the training data from a trained model without significantly affecting the model performance on the remaining data. This topic is becoming increasingly important in…

Cross-Domain Few-Shot Learning (CDFSL) aims to adapt large-scale pretrained models to specialized target domains with limited samples, yet the few-shot fine-tuning of vision-language models like CLIP remains underexplored. By establishing…

In the anomaly detection setting, the native feature embedding can be a crucial source of bias. We present a technique, Feature Omission using Context in Unsupervised Settings (FOCUS) to learn a feature mapping that is invariant to changes…

General object detectors use powerful backbones that uniformly extract features from images for enabling detection of a vast amount of object types. However, utilization of such backbones in object detection applications developed for…

High-precision scene parsing tasks, including image matting and dichotomous segmentation, aim to accurately predict masks with extremely fine details (such as hair). Most existing methods focus on salient, single foreground objects. While…

More and more evidence has shown that strengthening layer interactions can enhance the representation power of a deep neural network, while self-attention excels at learning interdependencies by retrieving query-activated information.…

Despite great success across various multimodal tasks, Large Vision-Language Models (LVLMs) often encounter object hallucinations with generated textual responses being inconsistent with the actual objects in images. We examine different…

Text-driven object insertion in 3D scenes is an emerging task that enables intuitive scene editing through natural language. However, existing 2D editing-based methods often rely on spatial priors such as 2D masks or 3D bounding boxes, and…

Image editing has advanced significantly with the development of diffusion models using both inversion-based and instruction-based methods. However, current inversion-based approaches struggle with big modifications (e.g., adding or…