Cross-Video Reasoning (CVR) presents a significant challenge in video understanding, which requires simultaneous understanding of multiple videos to aggregate and compare information across groups of videos. Most existing video understanding benchmarks focus on single-video analysis, failing to assess the ability of multimodal large language models (MLLMs) to simultaneously reason over various videos. Recent benchmarks evaluate MLLMs' capabilities on multi-view videos that capture different perspectives of the same scene. However, their limited tasks hinder a thorough assessment of MLLMs in diverse real-world CVR scenarios. To this end, we introduce CrossVid, the first benchmark designed to comprehensively evaluate MLLMs' spatial-temporal reasoning ability in cross-video contexts. Firstly, CrossVid encompasses a wide spectrum of hierarchical tasks, comprising four high-level dimensions and ten specific tasks, thereby closely reflecting the complex and varied nature of real-world video understanding. Secondly, CrossVid provides 5,331 videos, along with 9,015 challenging question-answering pairs, spanning single-choice, multiple-choice, and open-ended question formats. Through extensive experiments on various open-source and closed-source MLLMs, we observe that Gemini-2.5-Pro performs best on CrossVid, achieving an average accuracy of 50.4%. Notably, our in-depth case study demonstrates that most current MLLMs struggle with CVR tasks, primarily due to their inability to integrate or compare evidence distributed across multiple videos for reasoning. These insights highlight the potential of CrossVid to guide future advancements in enhancing MLLMs’ CVR capabilities.

With the rapid advancement of multimodal information retrieval, increasingly complex retrieval tasks have emerged. Existing methods predominately rely on task-specific fine-tuning of vision-language models, often those trained with image-text contrastive learning. In this paper, we explore the possibility of re-purposing generative Large Multimodal Models (LMMs) for retrieval. This approach enables unifying all retrieval tasks under the same formulation and, more importantly, allows for extrapolation towards unseen retrieval tasks without additional training. Our contributions can be summarised in the following aspects: (i) We introduce LamRA, a versatile framework designed to empower LMMs with sophisticated retrieval and reranking capabilities. (ii) For retrieval, we adopt a two-stage training strategy comprising language-only pre-training and multimodal instruction tuning to progressively enhance LMM’s retrieval performance. (iii) For reranking, we employ joint training of both pointwise and listwise reranking, offering two distinct ways to further boost the retrieval performance. (iv) Extensive experiments underscore the efficacy of our method in handling more than ten retrieval tasks, demonstrating robust performance in both supervised and zero-shot settings, including scenarios involving previously unseen retrieval tasks. Project page: https://code-kunkun.github.io/LamRA/.

Video Large Language Models (VideoLLMs) have recently demonstrated remarkable progress in general video understanding. However, existing models primarily focus on high-level comprehension and are limited to text-only responses, restricting the flexibility for object-centric, multiround interactions. In this paper, we make three contributions: (i) we address these limitations by introducing a VideoLLM model, capable of performing both object referring for input and grounding for output in video reasoning tasks, i.e., allowing users to interact with videos using both textual and visual prompts; (ii) we propose STOM (Spatial-Temporal Overlay Module), a novel approach that propagates arbitrary visual prompts input at any single timestamp to the remaining frames within a video; (iii) we present VideoInfer, a manually curated object-centric video instruction dataset featuring questionanswering pairs that require reasoning. We conduct comprehensive experiments on VideoInfer and other existing benchmarks across video question answering and referring object segmentation. The results on 12 benchmarks of 6 tasks show that our proposed model consistently outperforms baselines in both video question answering and segmentation, underscoring its robustness in multimodal, object-centric video and image understanding. Project page: https://qirui-chen.github.io/RGA3-release/.

Test-time prompt tuning enhances zero-shot generalization of vision-language models but tends to ignore the relatedness among test samples during inference. Online test-time prompt tuning provides a simple way to leverage the information in previous test samples, albeit with the risk of prompt collapse due to error accumulation. To enhance test-time prompt tuning, we propose DynaPrompt, short for dynamic test-time prompt tuning, exploiting relevant data distribution information while reducing error accumulation. Built on an online prompt buffer, DynaPrompt adaptively selects and optimizes the relevant prompts for each test sample during tuning. Specifically, we introduce a dynamic prompt selection strategy based on two metrics: prediction entropy and probability difference. For unseen test data information, we develop dynamic prompt appending, which allows the buffer to append new prompts and delete the inactive ones. By doing so, the prompts are optimized to exploit beneficial information on specific test data, while alleviating error accumulation. Experiments on fourteen datasets demonstrate the effectiveness of dynamic test-time prompt tuning.

With the rapid development of generative models, discerning AI-generated content has evoked increasing attention from both industry and academia. In this paper, we conduct a sanity check on whether the task of AI-generated image detection has been solved. To start with, we present Chameleon dataset, consisting of AI-generated images that are genuinely challenging for human perception. To quantify the generalization of existing methods, we evaluate 9 off-the-shelf AI-generated image detectors on Chameleon dataset. Upon analysis, almost all models misclassify AI-generated images as real ones. Later, we propose AIDE AI-generated Image DEtector with Hybrid Features, which leverages multiple experts to simultaneously extract visual artifacts and noise patterns. Specifically, to capture the high-level semantics, we utilize CLIP to compute the visual embedding. This effectively enables the model to discern AI-generated images based on semantics and contextual information. Secondly, we select the highest and lowest frequency patches in the image, and compute the low-level patchwise features, aiming to detect AI-generated images by low-level artifacts, for example, noise patterns, anti-aliasing effects. While evaluating on existing benchmarks, for example, AIGCDetectBenchmark and GenImage, AIDE achieves +3.5% and +4.6% improvements to state-of-the-art methods, and on our proposed challenging Chameleon benchmarks, it also achieves promising results, despite the problem of detecting AI-generated images remains far from being solved.

With recent generative models facilitating photo-realistic image synthesis, the proliferation of synthetic images has also engendered certain negative impacts on social platforms, thereby raising an urgent imperative to develop effective detectors. Current synthetic image detection (SID) pipelines are primarily dedicated to crafting universal artifact features, accompanied by an oversight about SID training paradigm. In this paper, we re-examine the SID problem and identify two prevalent biases in current training paradigms, i.e., weakened artifact features and overfitted artifact features. Meanwhile, we discover that the imaging mechanism of synthetic images contributes to heightened local correlations among pixels, suggesting that detectors should be equipped with local awareness. In this light, we propose SAFE, a lightweight and effective detector with three simple image transformations. Firstly, for weakened artifact features, we substitute the down-sampling operator with the crop operator in image pre-processing to help circumvent artifact distortion. Secondly, for overfitted artifact features, we include ColorJitter and RandomRotation as additional data augmentations, to help alleviate irrelevant biases from color discrepancies and semantic differences in limited training samples. Thirdly, for local awareness, we propose a patch-based random masking strategy tailored for SID, forcing the detector to focus on local regions at training. Comparative experiments are conducted on an open-world dataset, comprising synthetic images generated by 26 distinct generative models. Our pipeline achieves a new state-of-the-art performance, with remarkable improvements of 4.5% in accuracy and 2.9% in average precision against existing methods. Our code is available at: https://github.com/Ouxiang-Li/SAFE.

Classifier-Free Guidance (CFG) significantly enhances controllability in generative models by interpolating conditional and unconditional predictions. However, standard CFG often employs a static unconditional input, which can be suboptimal for iterative generation processes where model uncertainty varies dynamically. We introduce Adaptive Classifier-Free Guidance (A-CFG), a novel method that tailors the unconditional input by leveraging the model's instantaneous predictive confidence. At each step of an iterative (masked) diffusion language model, A-CFG identifies tokens in the currently generated sequence for which the model exhibits low confidence. These tokens are temporarily re-masked to create a dynamic, localized unconditional input. This focuses CFG's corrective influence precisely on areas of ambiguity, leading to more effective guidance. We integrate A-CFG into a state-of-the-art masked diffusion language model and demonstrate its efficacy. Experiments on diverse language generation benchmarks show that A-CFG yields substantial improvements over standard CFG, achieving, for instance, a 3.9 point gain on GPQA. Our work highlights the benefit of dynamically adapting guidance mechanisms to model uncertainty in iterative generation.

This paper presents a novel video inpainting architecture named Deformed Vision Transformers (DeViT). We make three significant contributions to this task: First, we extended previous Transformers with patch alignment by introducing Deformed Patch-based Homography Estimator (DePtH), which enriches the patch-level feature alignments in key and query with additional offsets learned from patch pairs without additional supervision. DePtH enables our method to handle challenging scenes or agile motion with in-plane or out-of-plane deformation, which previous methods usually fail. Second, we introduce the Mask Pruning-based Patch Attention (MPPA) to improve the standard patch-wised feature matching by pruning out less essential features and considering the saliency map. MPPA enhances the matching accuracy between warped tokens with invalid pixels. Third, we introduce the Spatial-Temporal weighting Adaptor (STA) module to assign more accurate attention to spatial-temporal tokens under the guidance of the Deformation Factor learned from DePtH, especially for videos with agile motions. Experimental results demonstrate that our method outperforms previous state-of-the-art methods in quality and quantity and achieves a new state-of-the-art for video inpainting.

In this paper, we propose a new task of deep interactive video inpainting and an application for users to interact with machines. To our best knowledge, this is the first deep learning-based interactive video inpainting framework that only uses a free form of user input as guidance (i.e. scribbles) instead of mask annotations, which has academic, entertainment, and commercial value.

Recently, Recurrent Neural Network (RNN) based methods and Self-Attention (SA) based methods have achieved promising performance in Video Question Answering (VideoQA). Despite the success of these works, RNN-based methods tend to forget the global semantic contents due to the inherent drawbacks of the recurrent units themselves, while SA-based methods cannot precisely capture the dependencies of the local neighborhood, leading to insufficient modeling for temporal order. To tackle these problems, we propose a novel VideoQA framework which progressively refines the representations of videos and questions from fine to coarse grain in a sequence-sensitive manner. Specifically, our model improves the feature representations via the following two steps: (1) introducing two fine-grained feature-augmented memories to strengthen the information augmentation of video and text which can improve memory capacity by memorizing more relevant and targeted information. (2) appending the self-attention and co-attention module to the memory output thus the module is able to capture global interaction between high-level semantic informations. Experimental results show that our approach achieves state-of-the-art performance on VideoQA benchmark datasets.