Music-to-music-video generation is a challenging task due to the intrinsic differences between the music and video modalities. The advent of powerful text-to-video diffusion models has opened a promising pathway for music-video (MV) generation by first addressing the music-to-MV description task and subsequently leveraging these models for video generation. In this study, we focus on the MV description generation task and propose a comprehensive pipeline encompassing training data construction and multimodal model fine-tuning. We fine-tune existing pre-trained multimodal models on our newly constructed music-to-MV description dataset based on the Music4All dataset, which integrates both musical and visual information. Our experimental results demonstrate that music representations can be effectively mapped to textual domains, enabling the generation of meaningful MV description directly from music inputs. We also identify key components in the dataset construction pipeline that critically impact the quality of MV description and highlight specific musical attributes that warrant greater focus for improved MV description generation.

When Hans Hartman, a civil engineer, attempted to film the ocean depths in 1917, he pioneered what would become the first deep-sea ROV, or remotely operated vehicle. During an era of silent movies and wartime U-boats, Hartman's ambitious invention--a 1,500-pound electric, submarine camera--could be lowered to a depth of 1,000 feet to capture images of sunken ships and submerged treasures. Despite featuring a gyroscope for stability, a motorized propeller for controlled rotation, and an innovative light source, as Popular Science explained, it had a serious limitation: The hulking apparatus had to be operated blindly from a ship's deck, which meant it was impossible for the camera's operator to see what they were filming until the footage was viewed later. In 1925, Popular Science showcased his next breakthrough--a cylindrical apparatus (seen above) attached to a ship by a cable, housing a submersible, motor-driven camera, as well as enough room for a person who could control the camera, or communicate with crew members nearby to aid with various underwater missions, such as salvaging. The vertical, tin-can-like submarine, equipped with porthole windows and a powerful spotlight, allowed "the operator to go down into the water with a camera and photograph whatever he chooses."

Despite the ever-growing importance of online moderation, there has been no large-scale study evaluating the effectiveness of alternative moderation strategies. This is largely due to the lack of appropriate datasets, and the difficulty of getting human discussants, moderators, and evaluators involved in multiple experiments. In this paper, we propose a methodology for leveraging synthetic experiments performed exclusively by Large Language Models (LLMs) to initially bypass the need for human participation in experiments involving online moderation. We evaluate six LLM moderation configurations; two currently used real-life moderation strategies (guidelines issued for human moderators for online moderation and real-life facilitation), two baseline strategies (guidelines elicited for LLM alignment work, and LLM moderation with minimal prompting) a baseline with no moderator at all, as well as our own proposed strategy inspired by a Reinforcement Learning (RL) formulation of the problem. We find that our own moderation strategy significantly outperforms established moderation guidelines, as well as out-of-the-box LLM moderation. We also find that smaller LLMs, with less intensive instruction-tuning, can create more varied discussions than larger models. In order to run these experiments, we create and release an efficient, purpose-built, open-source Python framework, dubbed "SynDisco" to easily simulate hundreds of discussions using LLM user-agents and moderators. Additionally, we release the Virtual Moderation Dataset (VMD), a large dataset of LLM-generated and LLM-annotated discussions, generated by three families of open-source LLMs accompanied by an exploratory analysis of the dataset.

We introduce Rich Preference Optimization (RPO), a novel pipeline that leverages rich feedback signals to improve the curation of preference pairs for fine-tuning text-to-image diffusion models. Traditional methods, like Diffusion-DPO, often rely solely on reward model labeling, which can be opaque, offer limited insights into the rationale behind preferences, and are prone to issues such as reward hacking or overfitting. In contrast, our approach begins with generating detailed critiques of synthesized images to extract reliable and actionable image editing instructions. By implementing these instructions, we create refined images, resulting in synthetic, informative preference pairs that serve as enhanced tuning datasets. We demonstrate the effectiveness of our pipeline and the resulting datasets in fine-tuning state-of-the-art diffusion models.

While diffusion models show promising results in image editing given a target prompt, achieving both prompt fidelity and background preservation remains difficult. Recent works have introduced score distillation techniques that leverage the rich generative prior of text-to-image diffusion models to solve this task without additional fine-tuning. However, these methods often struggle with tasks such as object insertion. Our investigation of these failures reveals significant variations in gradient magnitude and spatial distribution, making hyperparameter tuning highly input-specific or unsuccessful. To address this, we propose two simple yet effective modifications: attention-based spatial regularization and gradient filtering-normalization, both aimed at reducing these variations during gradient updates. Experimental results show our method outperforms state-of-the-art score distillation techniques in prompt fidelity, improving successful edits while preserving the background. Users also preferred our method over state-of-the-art techniques across three metrics, and by 58-64% overall.

With a combination of quantitative experiments, human judgments, and qualitative analyses, we evaluate the quantity and quality of African American Language (AAL) representation in 12 predominantly English, open-source pretraining corpora. We specifically focus on the sources, variation, and naturalness of included AAL texts representing the AAL-speaking community. We find that AAL is underrepresented in all evaluated pretraining corpora compared to US demographics, constituting as little as 0.007% of documents. We also find that more than 25% of AAL texts in C4 may be inappropriate for LLMs to generate and reinforce harmful stereotypes. Finally, we find that most automated language, toxicity, and quality filters are more likely to conserve White Mainstream English (WME) texts over AAL in pretraining corpora.

Political polarization is a significant issue in American politics, influencing public discourse, policy, and consumer behavior. While studies on polarization in news media have extensively focused on verbal content, non-verbal elements, particularly visual content, have received less attention due to the complexity and high dimensionality of image data. Traditional descriptive approaches often rely on feature extraction from images, leading to biased polarization estimates due to information loss. In this paper, we introduce the Polarization Measurement using Counterfactual Image Generation (PMCIG) method, which combines economic theory with generative models and multi-modal deep learning to fully utilize the richness of image data and provide a theoretically grounded measure of polarization in visual content. Applying this framework to a decade-long dataset featuring 30 prominent politicians across 20 major news outlets, we identify significant polarization in visual content, with notable variations across outlets and politicians. At the news outlet level, we observe significant heterogeneity in visual slant. Outlets such as Daily Mail, Fox News, and Newsmax tend to favor Republican politicians in their visual content, while The Washington Post, USA Today, and The New York Times exhibit a slant in favor of Democratic politicians. At the politician level, our results reveal substantial variation in polarized coverage, with Donald Trump and Barack Obama among the most polarizing figures, while Joe Manchin and Susan Collins are among the least. Finally, we conduct a series of validation tests demonstrating the consistency of our proposed measures with external measures of media slant that rely on non-image-based sources.

Audio and music generation have emerged as crucial tasks in many applications, yet existing approaches face significant limitations: they operate in isolation without unified capabilities across modalities, suffer from scarce high-quality, multi-modal training data, and struggle to effectively integrate diverse inputs. In this work, we propose AudioX, a unified Diffusion Transformer model for Anything-to-Audio and Music Generation. Unlike previous domain-specific models, AudioX can generate both general audio and music with high quality, while offering flexible natural language control and seamless processing of various modalities including text, video, image, music, and audio. Its key innovation is a multi-modal masked training strategy that masks inputs across modalities and forces the model to learn from masked inputs, yielding robust and unified cross-modal representations. To address data scarcity, we curate two comprehensive datasets: vggsound-caps with 190K audio captions based on the VGGSound dataset, and V2M-caps with 6 million music captions derived from the V2M dataset. Extensive experiments demonstrate that AudioX not only matches or outperforms state-of-the-art specialized models, but also offers remarkable versatility in handling diverse input modalities and generation tasks within a unified architecture. The code and datasets will be available at https://zeyuet.github.io/AudioX/

In agricultural automation, inherent occlusion presents a major challenge for robotic harvesting. We propose a novel imitation learning-based viewpoint planning approach to actively adjust camera viewpoint and capture unobstructed images of the target crop. Traditional viewpoint planners and existing learning-based methods, depend on manually designed evaluation metrics or reward functions, often struggle to generalize to complex, unseen scenarios. Our method employs the Action Chunking with Transformer (ACT) algorithm to learn effective camera motion policies from expert demonstrations. This enables continuous six-degree-of-freedom (6-DoF) viewpoint adjustments that are smoother, more precise and reveal occluded targets. Extensive experiments in both simulated and real-world environments, featuring agricultural scenarios and a 6-DoF robot arm equipped with an RGB-D camera, demonstrate our method's superior success rate and efficiency, especially in complex occlusion conditions, as well as its ability to generalize across different crops without reprogramming. This study advances robotic harvesting by providing a practical "learn from demonstration" (LfD) solution to occlusion challenges, ultimately enhancing autonomous harvesting performance and productivity.

Vision Language Models (VLMs) have demonstrated significant potential in various downstream tasks, including Image/Video Generation, Visual Question Answering, Multimodal Chatbots, and Video Understanding. However, these models often struggle with basic image transformations. This paper investigates the image-level understanding of VLMs, specifically CLIP by OpenAI and SigLIP by Google. Our findings reveal that these models lack comprehension of multiple image-level augmentations. To facilitate this study, we created an augmented version of the Flickr8k dataset, pairing each image with a detailed description of the applied transformation. We further explore how this deficiency impacts downstream tasks, particularly in image editing, and evaluate the performance of state-of-the-art Image2Image models on simple transformations.