Cropper: Vision-Language Model for Image Cropping through In-Context Learning

The goal of image cropping is to identify visually appealing crops within an image. Conventional methods rely on specialized architectures trained on specific datasets, which struggle to be adapted to new requirements. Recent breakthroughs in large vision-language models (VLMs) have enabled visual in-context learning without explicit training. However, effective strategies for vision downstream tasks with VLMs remain largely unclear and underexplored. In this paper, we propose an effective approach to leverage VLMs for better image cropping. First, we propose an efficient prompt retrieval mechanism for image cropping to automate the selection of in-context examples. Second, we introduce an iterative refinement strategy to iteratively enhance the predicted crops. The proposed framework, named Cropper, is applicable to a wide range of cropping tasks, including free-form cropping, subject-aware cropping, and aspect ratio-aware cropping. Extensive experiments and a user study demonstrate that Cropper significantly outperforms state-of-the-art methods across several benchmarks.

ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling

Recognizing and disentangling visual attributes from objects is a foundation to many computer vision applications. While large vision language representations like CLIP had largely resolved the task of zero-shot object recognition, zero-shot visual attribute recognition remains a challenge because CLIP's contrastively-learned vision-language representation cannot effectively capture object-attribute dependencies. In this paper, we target this weakness and propose a sentence generation-based retrieval formulation for attribute recognition that is novel in 1) explicitly modeling a to-be-measured and retrieved object-attribute relation as a conditional probability graph, which converts the recognition problem into a dependency-sensitive language-modeling problem, and 2) applying a large pretrained Vision-Language Model (VLM) on this reformulation and naturally distilling its knowledge of image-object-attribute relations to use towards attribute recognition. Specifically, for each attribute to be recognized on an image, we measure the visual-conditioned probability of generating a short sentence encoding the attribute's relation to objects on the image. Unlike contrastive retrieval, which measures likelihood by globally aligning elements of the sentence to the image, generative retrieval is sensitive to the order and dependency of objects and attributes in the sentence. We demonstrate through experiments that generative retrieval consistently outperforms contrastive retrieval on two visual reasoning datasets, Visual Attribute in the Wild (VAW), and our newly-proposed Visual Genome Attribute Ranking (VGARank).

Fluid-Antenna Enhanced ISAC: Joint Antenna Positioning and Dual-Functional Beamforming Design under Perfect and Imperfect CSI

Integrated sensing and communication (ISAC) emerges as an essential technique for overcoming spectrum congestion. However, the performance of traditional ISAC systems with fixed-position-antennas (FPA) is limited due to insufficient spatial degree of freedom (DoF) exploration. Recently, fluid antenna (FA) with reconfigurable antenna position is developed to enhance the sensing and communication performance by reshaping the channel. This paper investigates an FA-enhanced ISAC system where a base station is equipped with multiple FAs to communicate with multiple single-antenna users and with FPAs to sense a point target. In this paper, we consider both perfect and imperfect channel state information (CSI) of the communication channel and sensing channel. In two cases, we focus on the maximization of the sensing signal-to-noise (SNR) by optimizing the positions of FAs and the dual-functional beamforming under the constraints of the FA moving region, the minimum FA distance and the minimum signal-to-interference-plus-noise (SINR) per user. Specifically, for the ideal case of perfect CSI, an iterative alternating optimization (AO) algorithm is proposed to tackle the formulated problem where the dual-functional beamforming and the FA positions are obtained via semidefinite relaxation (SDR) and successive convex approximation (SCA) techniques. Then, for the imperfect CSI case, we propose an AO-based iterative algorithm where $\mathcal{S}-$Procedure and SCA are applied to obtain the dual-functional beamforming and the FA positions. Furthermore, we analytically and numerically prove the convergence of the proposed algorithms. Numerical results demonstrate the notable gains of the proposed algorithms in the respective cases.

Optical Diffusion Models for Image Generation

Diffusion models generate new samples by progressively decreasing the noise from the initially provided random distribution. This inference procedure generally utilizes a trained neural network numerous times to obtain the final output, creating significant latency and energy consumption on digital electronic hardware such as GPUs. In this study, we demonstrate that the propagation of a light beam through a semi-transparent medium can be programmed to implement a denoising diffusion model on image samples. This framework projects noisy image patterns through passive diffractive optical layers, which collectively only transmit the predicted noise term in the image. The optical transparent layers, which are trained with an online training approach, backpropagating the error to the analytical model of the system, are passive and kept the same across different steps of denoising. Hence this method enables high-speed image generation with minimal power consumption, benefiting from the bandwidth and energy efficiency of optical information processing.

Fluid-Antenna Enhanced Integrated Sensing and Communication: Joint Antenna Positioning and Beamforming Design

This paper investigates a fluid antenna (FA) enhanced integrated sensing and communication (ISAC) system consisting of a base station (BS), multiple single-antenna communication users, and one point target, where the BS is equipped with FAs to enhance both the communication and sensing performance. First, we formulate a problem that maximizes the radar signal-to-noise ratio (SNR) by jointly optimizing the FAs' positions and transmit beamforming matrix. Then, to tackle this highly non-convex problem, we present efficient algorithms by using alternating optimization (AO), successive convex approximation (SCA), and semi-definite relaxation (SDR). Numerical results demonstrate the convergence behavior and effectiveness of the proposed algorithm.

MonoDETRNext: Next-generation Accurate and Efficient Monocular 3D Object Detection Method

Monocular vision-based 3D object detection is crucial in various sectors, yet existing methods face significant challenges in terms of accuracy and computational efficiency. Building on the successful strategies in 2D detection and depth estimation, we propose MonoDETRNext, which seeks to optimally balance precision and processing speed. Our methodology includes the development of an efficient hybrid visual encoder, enhancement of depth prediction mechanisms, and introduction of an innovative query generation strategy, augmented by an advanced depth predictor. Building on MonoDETR, MonoDETRNext introduces two variants: MonoDETRNext-F, which emphasizes speed, and MonoDETRNext-A, which focuses on precision. We posit that MonoDETRNext establishes a new benchmark in monocular 3D object detection and opens avenues for future research. We conducted an exhaustive evaluation demonstrating the model's superior performance against existing solutions. Notably, MonoDETRNext-A demonstrated a 4.60% improvement in the AP3D metric on the KITTI test benchmark over MonoDETR, while MonoDETRNext-F showed a 2.21% increase. Additionally, the computational efficiency of MonoDETRNext-F slightly exceeds that of its predecessor.

WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights

The advances in the Neural Radiance Fields (NeRF) research offer extensive applications in diverse domains, but protecting their copyrights has not yet been researched in depth. Recently, NeRF watermarking has been considered one of the pivotal solutions for safely deploying NeRF-based 3D representations. However, existing methods are designed to apply only to implicit or explicit NeRF representations. In this work, we introduce an innovative watermarking method that can be employed in both representations of NeRF. This is achieved by fine-tuning NeRF to embed binary messages in the rendering process. In detail, we propose utilizing the discrete wavelet transform in the NeRF space for watermarking. Furthermore, we adopt a deferred back-propagation technique and introduce a combination with the patch-wise loss to improve rendering quality and bit accuracy with minimum trade-offs. We evaluate our method in three different aspects: capacity, invisibility, and robustness of the embedded watermarks in the 2D-rendered images. Our method achieves state-of-the-art performance with faster training speed over the compared state-of-the-art methods.

Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation

Recent works demonstrate that using reinforcement learning (RL) with quality rewards can enhance the quality of generated images in text-to-image (T2I) generation. However, a simple aggregation of multiple rewards may cause over-optimization in certain metrics and degradation in others, and it is challenging to manually find the optimal weights. An effective strategy to jointly optimize multiple rewards in RL for T2I generation is highly desirable. This paper introduces Parrot, a novel multi-reward RL framework for T2I generation. Through the use of the batch-wise Pareto optimal selection, Parrot automatically identifies the optimal trade-off among different rewards during the RL optimization of the T2I generation. Additionally, Parrot employs a joint optimization approach for the T2I model and the prompt expansion network, facilitating the generation of quality-aware text prompts, thus further enhancing the final image quality. To counteract the potential catastrophic forgetting of the original user prompt due to prompt expansion, we introduce original prompt centered guidance at inference time, ensuring that the generated image remains faithful to the user input. Extensive experiments and a user study demonstrate that Parrot outperforms several baseline methods across various quality criteria, including aesthetics, human preference, image sentiment, and text-image alignment.

Gemini: A Family of Highly Capable Multimodal Models

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultra model advances the state of the art in 30 of 32 of these benchmarks - notably being the first model to achieve human-expert performance on the well-studied exam benchmark MMLU, and improving the state of the art in every one of the 20 multimodal benchmarks we examined. We believe that the new capabilities of Gemini models in cross-modal reasoning and language understanding will enable a wide variety of use cases and we discuss our approach toward deploying them responsibly to users.

Rich Human Feedback for Text-to-Image Generation

Recent Text-to-Image (T2I) generation models such as Stable Diffusion and Imagen have made significant progress in generating high-resolution images based on text descriptions. However, many generated images still suffer from issues such as artifacts/implausibility, misalignment with text descriptions, and low aesthetic quality. Inspired by the success of Reinforcement Learning with Human Feedback (RLHF) for large language models, prior works collected human-provided scores as feedback on generated images and trained a reward model to improve the T2I generation. In this paper, we enrich the feedback signal by (i) marking image regions that are implausible or misaligned with the text, and (ii) annotating which words in the text prompt are misrepresented or missing on the image. We collect such rich human feedback on 18K generated images and train a multimodal transformer to predict the rich feedback automatically. We show that the predicted rich human feedback can be leveraged to improve image generation, for example, by selecting high-quality training data to finetune and improve the generative models, or by creating masks with predicted heatmaps to inpaint the problematic regions. Notably, the improvements generalize to models (Muse) beyond those used to generate the images on which human feedback data were collected (Stable Diffusion variants).