Zhengyuan Yang

Reinforcement learning (RL) has shown great effectiveness for fine-tuning large language models (LLMs) using tasks that are challenging yet easily verifiable, such as math reasoning or code generation. However, extending this success to visual perception in vision-language models (VLMs) has been impeded by the scarcity of vision-centric tasks that are simultaneously challenging and unambiguously verifiable. To this end, we introduce ViCrit (Visual Caption Hallucination Critic), an RL proxy task that trains VLMs to localize a subtle, synthetic visual hallucination injected into paragraphs of human-written image captions. Starting from a 200-word captions, we inject a single, subtle visual description error-altering a few words on objects, attributes, counts, or spatial relations-and task the model to pinpoint the corrupted span given the image and the modified caption. This formulation preserves the full perceptual difficulty while providing a binary, exact-match reward that is easy to compute and unambiguous. Models trained with the ViCrit Task exhibit substantial gains across a variety of VL benchmarks. Crucially, the improvements transfer beyond natural-image training data to abstract image reasoning and visual math, showing promises of learning to perceive rather than barely memorizing seen objects. To facilitate evaluation, we further introduce ViCrit-Bench, a category-balanced diagnostic benchmark that systematically probes perception errors across diverse image domains and error types. Together, our results demonstrate that fine-grained hallucination criticism is an effective and generalizable objective for enhancing visual perception in VLMs.

Recent research has shed light on the capabilities of Large Multimodal Models (LMMs) across various general vision and language tasks. The performance of LMMs in specialized domains, such as social media, which integrates text, images, videos, and sometimes audio, remains an area of active interest. Effective analysis of such content requires models to interpret the complex interactions between different communication modalities and their influence on the conveyed message. This article explores GPT-4V(ision)’s performance in social multimedia analysis. We evaluate GPT-4V across five representative tasks: sentiment analysis, hate speech detection, fake news identification, demographic inference, and political ideology detection. Our approach includes a preliminary quantitative analysis for each task using existing benchmark datasets, followed by a review of the results and a selection of qualitative samples to demonstrate GPT-4V’s performance in multimodal social media content analysis. GPT-4V shows effectiveness in these tasks, exhibiting capabilities like joint image–text understanding, contextual and cultural awareness, and commonsense knowledge application. However, challenges persist, including struggles with multilingual social multimedia comprehension and difficulty in adapting to the latest social media trends. It also sometimes generates incorrect information about evolving knowledge of celebrities and politicians. This preliminary study aims to inform further research across disciplines, particularly in computational social science and social media studies. The findings highlight the potential of LMMs to enhance our understanding of social media content and its users through multimodal analysis. All images and prompts used in this study will be available at https://github.com/VIStA-H/GPT-4V_Social_Media .

We introduce OpenLEAF, a new benchmark designed for the emerging open-domain interleaved image-text generation task. This task aims to generate arbitrarily interleaved multimodal content from input queries. It goes beyond commonly seen single-modality image or text generation, thereby enabling various novel applications by creating content such as visual storybooks and how-to instructions. Despite the importance of this task, no established benchmark exists due to the challenges in defining evaluation scenarios and formulating effective metrics. To introduce and facilitate the new task of interleaved image-text generation, we create a new dataset covering queries with various input-output formats and 10 different application scenarios. We also propose a novel evaluation pipeline named "detection-summarization-scoring," which breaks down the evaluation into multiple reasoning steps. This pipeline leverages large multimodal models (LMMs) to thoroughly evaluate ten aspects of the generated content, which leads to the final rating. With experiments on a proposed agent system, we demonstrate that our evaluation method aligns closely with human judgments, thus together with the dataset, offering the research community a valuable benchmark for exploring interleaved image-text generation.

The advent of large Vision-Language Models (VLMs) has significantly advanced multimodal understanding, enabling more sophisticated and accurate integration of visual and textual information across various tasks, including image and video captioning, visual question answering, and cross-modal retrieval. Despite VLMs' superior capabilities, researchers lack a comprehensive understanding of their compositionality -- the ability to understand and produce novel combinations of known visual and textual components. Prior benchmarks provide only a relatively rough compositionality evaluation from the perspectives of objects, relations, and attributes while neglecting deeper reasoning about object interactions, counting, and complex compositions. However, compositionality is a critical ability that facilitates coherent reasoning and understanding across modalities for VLMs. To address this limitation, we propose MMCOMPOSITION, a novel human-annotated benchmark for comprehensively and accurately evaluating VLMs' compositionality. Our proposed benchmark serves as a complement to these earlier works. With MMCOMPOSITION, we can quantify and explore the compositionality of the mainstream VLMs. Surprisingly, we find GPT-4o's compositionality inferior to the best open-source model, and we analyze the underlying reasons. Our experimental analysis reveals the limitations of VLMs in fine-grained compositional perception and reasoning, and points to areas for improvement in VLM design and training. Resources available at: https://hanghuacs.github.io/MMComposition/

With the advancement of generative models, the synthesis of different sensory elements such as music, visuals, and speech has achieved significant realism. However, the approach to generate multi-sensory outputs has not been fully explored, limiting the application on high-value scenarios such as of directing a film. Developing a movie director agent faces two major challenges: (1) Lack of parallelism and online scheduling with production steps: In the production of multi-sensory films, there are complex dependencies between different sensory elements, and the production time for each element varies. (2) Diverse needs and clear communication demands with users: Users often cannot clearly express their needs until they see a draft, which requires human-computer interaction and iteration to continually adjust and optimize the film content based on user feedback. To address these issues, we introduce AutoDirector, an interactive multi-sensory composition framework that supports long shots, special effects, music scoring, dubbing, and lip-syncing. This framework improves the efficiency of multi-sensory film production through automatic scheduling and supports the modification and improvement of interactive tasks to meet user needs. AutoDirector not only expands the application scope of human-machine collaboration but also demonstrates the potential of AI in collaborating with humans in the role of a film director to complete multi-sensory films.

We introduce a Cascaded Diffusion Model (Cas-DM) that improves a Denoising Diffusion Probabilistic Model (DDPM) by effectively incorporating additional metric functions in training. Metric functions such as the LPIPS loss have been proven highly effective in consistency models derived from the score matching. However, for the diffusion counterparts, the methodology and efficacy of adding extra metric functions remain unclear. One major challenge is the mismatch between the noise predicted by a DDPM at each step and the desired clean image that the metric function works well on. To address this problem, we propose Cas-DM, a network architecture that cascades two network modules to effectively apply metric functions to the diffusion model training. The first module, similar to a standard DDPM, learns to predict the added noise and is unaffected by the metric function. The second cascaded module learns to predict the clean image, thereby facilitating the metric function computation. Experiment results show that the proposed diffusion model backbone enables the effective use of the LPIPS loss, improving the image quality (FID, sFID) of diffusion models on various established benchmarks.

Significant advances have been made in human-centric video generation, yet the joint video-depth generation problem remains underexplored. Most existing monocular depth estimation methods may not generalize well to synthesized images or videos, and multi-view-based methods have difficulty controlling the human appearance and motion. In this work, we present IDOL (unIfied Dual-mOdal Latent diffusion) for high-quality human-centric joint video-depth generation. Our IDOL consists of two novel designs. First, to enable dual-modal generation and maximize the information exchange between video and depth generation, we propose a unified dual-modal U-Net, a parameter-sharing framework for joint video and depth denoising, wherein a modality label guides the denoising target, and cross-modal attention enables the mutual information flow. Second, to ensure a precise video-depth spatial alignment, we propose a motion consistency loss that enforces consistency between the video and depth feature motion fields, leading to harmonized outputs. Additionally, a cross-attention map consistency loss is applied to align the cross-attention map of the video denoising with that of the depth denoising, further facilitating spatial alignment. Extensive experiments on the TikTok and NTU120 datasets show our superior performance, significantly surpassing existing methods in terms of video FVD and depth accuracy.

This monograph presents a comprehensive survey of the taxonomy and evolution of multimodal foundation models that demonstrate vision and vision-language capabilities, focusing on the transition from specialist models to generalpurpose assistants. The research landscape encompasses five core topics, categorized into two classes. (i) We start with a survey of well-established research areas: multimodal foundation models pre-trained for specific purposes, including two topics – methods of learning vision backbones for visual understanding and text-to-image generation. (ii) Then, we present recent advances in exploratory, open research areas: multimodal foundation models that aim to play the role of general-purpose assistants, including three topics – unified vision models inspired by large language models (LLMs), end-to-end training of multimodal LLMs, and chaining multimodal tools with LLMs. The target audiences of the monograph are researchers, graduate students, and professionals in computer vision and vision-language multimodal communities who are eager to learn the basics and recent advances in multimodal foundation models.