Interleaved Scene Graph for Interleaved Text-and-Image Generation Assessment

Many real-world user queries (e.g. "How do to make egg fried rice?") could benefit from systems capable of generating responses with both textual steps with accompanying images, similar to a cookbook. Models designed to generate interleaved text and images face challenges in ensuring consistency within and across these modalities. To address these challenges, we present ISG, a comprehensive evaluation framework for interleaved text-and-image generation. ISG leverages a scene graph structure to capture relationships between text and image blocks, evaluating responses on four levels of granularity: holistic, structural, block-level, and image-specific. This multi-tiered evaluation allows for a nuanced assessment of consistency, coherence, and accuracy, and provides interpretable question-answer feedback. In conjunction with ISG, we introduce a benchmark, ISG-Bench, encompassing 1,150 samples across 8 categories and 21 subcategories. This benchmark dataset includes complex language-vision dependencies and golden answers to evaluate models effectively on vision-centric tasks such as style transfer, a challenging area for current models. Using ISG-Bench, we demonstrate that recent unified vision-language models perform poorly on generating interleaved content. While compositional approaches that combine separate language and image models show a 111% improvement over unified models at the holistic level, their performance remains suboptimal at both block and image levels. To facilitate future work, we develop ISG-Agent, a baseline agent employing a "plan-execute-refine" pipeline to invoke tools, achieving a 122% performance improvement.

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination

Multimodal large language models (MLLMs) have advanced the integration of visual and linguistic modalities, establishing themselves as the dominant paradigm for visual-language tasks. Current approaches like chain of thought (CoT) reasoning have augmented the cognitive capabilities of large language models (LLMs), yet their adaptation to MLLMs is hindered by heightened risks of hallucination in cross-modality comprehension. In this paper, we find that the thinking while looking paradigm in current multimodal CoT approaches--where reasoning chains are generated alongside visual input--fails to mitigate hallucinations caused by misleading images. To address these limitations, we propose the Visual Inference Chain (VIC) framework, a novel approach that constructs reasoning chains using textual context alone before introducing visual input, effectively reducing cross-modal biases and enhancing multimodal reasoning accuracy. Comprehensive evaluations demonstrate that VIC significantly improves zero-shot performance across various vision-related tasks, mitigating hallucinations while refining the reasoning capabilities of MLLMs. Our code repository can be found at https://github.com/Terry-Xu-666/visual_inference_chain.

Investigating and Defending Shortcut Learning in Personalized Diffusion Models

Personalized diffusion models have gained popularity for adapting pre-trained text-to-image models to generate images of specific topics with only a few images. However, recent studies find that these models are vulnerable to minor adversarial perturbation, and the fine-tuning performance is largely degraded on corrupted datasets. Such characteristics are further exploited to craft protective perturbation on sensitive images like portraits that prevent unauthorized generation. In response, diffusion-based purification methods have been proposed to remove these perturbations and retain generation performance. However, existing works lack detailed analysis of the fundamental shortcut learning vulnerability of personalized diffusion models and also turn to over-purifying the images cause information loss. In this paper, we take a closer look at the fine-tuning process of personalized diffusion models through the lens of shortcut learning and propose a hypothesis that could explain the underlying manipulation mechanisms of existing perturbation methods. Specifically, we find that the perturbed images are greatly shifted from their original paired prompt in the CLIP-based latent space. As a result, training with this mismatched image-prompt pair creates a construction that causes the models to dump their out-of-distribution noisy patterns to the identifier, thus causing serious performance degradation. Based on this observation, we propose a systematic approach to retain the training performance with purification that realigns the latent image and its semantic meaning and also introduces contrastive learning with a negative token to decouple the learning of wanted clean identity and the unwanted noisy pattern, that shows strong potential capacity against further adaptive perturbation.

Mora: Enabling Generalist Video Generation via A Multi-Agent Framework

Sora is the first large-scale generalist video generation model that garnered significant attention across society. Since its launch by OpenAI in February 2024, no other video generation models have paralleled {Sora}'s performance or its capacity to support a broad spectrum of video generation tasks. Additionally, there are only a few fully published video generation models, with the majority being closed-source. To address this gap, this paper proposes a new multi-agent framework Mora, which incorporates several advanced visual AI agents to replicate generalist video generation demonstrated by Sora. In particular, Mora can utilize multiple visual agents and successfully mimic Sora's video generation capabilities in various tasks, such as (1) text-to-video generation, (2) text-conditional image-to-video generation, (3) extend generated videos, (4) video-to-video editing, (5) connect videos and (6) simulate digital worlds. Our extensive experimental results show that Mora achieves performance that is proximate to that of Sora in various tasks. However, there exists an obvious performance gap between our work and Sora when assessed holistically. In summary, we hope this project can guide the future trajectory of video generation through collaborative AI agents.

Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models

Sora is a text-to-video generative AI model, released by OpenAI in February 2024. The model is trained to generate videos of realistic or imaginative scenes from text instructions and show potential in simulating the physical world. Based on public technical reports and reverse engineering, this paper presents a comprehensive review of the model's background, related technologies, applications, remaining challenges, and future directions of text-to-video AI models. We first trace Sora's development and investigate the underlying technologies used to build this "world simulator". Then, we describe in detail the applications and potential impact of Sora in multiple industries ranging from film-making and education to marketing. We discuss the main challenges and limitations that need to be addressed to widely deploy Sora, such as ensuring safe and unbiased video generation. Lastly, we discuss the future development of Sora and video generation models in general, and how advancements in the field could enable new ways of human-AI interaction, boosting productivity and creativity of video generation.

MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark

Multimodal Large Language Models (MLLMs) have gained significant attention recently, showing remarkable potential in artificial general intelligence. However, assessing the utility of MLLMs presents considerable challenges, primarily due to the absence multimodal benchmarks that align with human preferences. Inspired by LLM-as-a-Judge in LLMs, this paper introduces a novel benchmark, termed MLLM-as-a-Judge, to assess the ability of MLLMs in assisting judges including three distinct tasks: Scoring Evaluation, Pair Comparison, and Batch Ranking. Our study reveals that, while MLLMs demonstrate remarkable human-like discernment in Pair Comparisons, there is a significant divergence from human preferences in Scoring Evaluation and Batch Ranking tasks. Furthermore, MLLMs still face challenges in judgment, including diverse biases, hallucinatory responses, and inconsistencies, even for advanced models such as GPT-4V. These findings emphasize the pressing need for enhancements and further research efforts regarding MLLMs as fully reliable evaluators. Code and dataset are available at https://github.com/Dongping-Chen/MLLM-as-a-Judge.

GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models

The discovery of "jailbreaks" to bypass safety filters of Large Language Models (LLMs) and harmful responses have encouraged the community to implement safety measures. One major safety measure is to proactively test the LLMs with jailbreaks prior to the release. Therefore, such testing will require a method that can generate jailbreaks massively and efficiently. In this paper, we follow a novel yet intuitive strategy to generate jailbreaks in the style of the human generation. We propose a role-playing system that assigns four different roles to the user LLMs to collaborate on new jailbreaks. Furthermore, we collect existing jailbreaks and split them into different independent characteristics using clustering frequency and semantic patterns sentence by sentence. We organize these characteristics into a knowledge graph, making them more accessible and easier to retrieve. Our system of different roles will leverage this knowledge graph to generate new jailbreaks, which have proved effective in inducing LLMs to generate unethical or guideline-violating responses. In addition, we also pioneer a setting in our system that will automatically follow the government-issued guidelines to generate jailbreaks to test whether LLMs follow the guidelines accordingly. We refer to our system as GUARD (Guideline Upholding through Adaptive Role-play Diagnostics). We have empirically validated the effectiveness of GUARD on three cutting-edge open-sourced LLMs (Vicuna-13B, LongChat-7B, and Llama-2-7B), as well as a widely-utilized commercial LLM (ChatGPT). Moreover, our work extends to the realm of vision language models (MiniGPT-v2 and Gemini Vision Pro), showcasing GUARD's versatility and contributing valuable insights for the development of safer, more reliable LLM-based applications across diverse modalities.

AdvCheck: Characterizing Adversarial Examples via Local Gradient Checking

Deep neural networks (DNNs) are vulnerable to adversarial examples, which may lead to catastrophe in security-critical domains. Numerous detection methods are proposed to characterize the feature uniqueness of adversarial examples, or to distinguish DNN's behavior activated by the adversarial examples. Detections based on features cannot handle adversarial examples with large perturbations. Besides, they require a large amount of specific adversarial examples. Another mainstream, model-based detections, which characterize input properties by model behaviors, suffer from heavy computation cost. To address the issues, we introduce the concept of local gradient, and reveal that adversarial examples have a quite larger bound of local gradient than the benign ones. Inspired by the observation, we leverage local gradient for detecting adversarial examples, and propose a general framework AdvCheck. Specifically, by calculating the local gradient from a few benign examples and noise-added misclassified examples to train a detector, adversarial examples and even misclassified natural inputs can be precisely distinguished from benign ones. Through extensive experiments, we have validated the AdvCheck's superior performance to the state-of-the-art (SOTA) baselines, with detection rate ($\sim \times 1.2$) on general adversarial attacks and ($\sim \times 1.4$) on misclassified natural inputs on average, with average 1/500 time cost. We also provide interpretable results for successful detection.

Is Multi-Modal Necessarily Better? Robustness Evaluation of Multi-modal Fake News Detection

The proliferation of fake news and its serious negative social influence push fake news detection methods to become necessary tools for web managers. Meanwhile, the multi-media nature of social media makes multi-modal fake news detection popular for its ability to capture more modal features than uni-modal detection methods. However, current literature on multi-modal detection is more likely to pursue the detection accuracy but ignore the robustness of the detector. To address this problem, we propose a comprehensive robustness evaluation of multi-modal fake news detectors. In this work, we simulate the attack methods of malicious users and developers, i.e., posting fake news and injecting backdoors. Specifically, we evaluate multi-modal detectors with five adversarial and two backdoor attack methods. Experiment results imply that: (1) The detection performance of the state-of-the-art detectors degrades significantly under adversarial attacks, even worse than general detectors; (2) Most multi-modal detectors are more vulnerable when subjected to attacks on visual modality than textual modality; (3) Popular events' images will cause significant degradation to the detectors when they are subjected to backdoor attacks; (4) The performance of these detectors under multi-modal attacks is worse than under uni-modal attacks; (5) Defensive methods will improve the robustness of the multi-modal detectors.

Convex Combination Consistency between Neighbors for Weakly-supervised Action Localization

In weakly-supervised temporal action localization (WS-TAL), the methods commonly follow the "localization by classification" procedure, which uses the snippet predictions to form video class scores and then optimizes a video classification loss. In this procedure, the snippet predictions (or snippet attention weights) are used to separate foreground and background. However, the snippet predictions are usually inaccurate due to absence of frame-wise labels, and then the overall performance is hindered. In this paper, we propose a novel C$^3$BN to achieve robust snippet predictions. C$^3$BN includes two key designs by exploring the inherent characteristics of video data. First, because of the natural continuity of adjacent snippets, we propose a micro data augmentation strategy to increase the diversity of snippets with convex combination of adjacent snippets. Second, we propose a macro-micro consistency regularization strategy to force the model to be invariant (or equivariant) to the transformations of snippets with respect to video semantics, snippet predictions and snippet features. Experimental results demonstrate the effectiveness of our proposed method on top of baselines for the WS-TAL tasks with video-level and point-level supervision.