While language models have made many milestones in text inference and classification tasks, they remain susceptible to adversarial attacks that can lead to unforeseen outcomes. Existing works alleviate this problem by equipping language models with defense patches. However, these defense strategies often rely on impractical assumptions or entail substantial sacrifices in model performance. Consequently, enhancing the resilience of the target model using such defense mechanisms is a formidable challenge. This paper introduces an innovative model for robust text inference and classification, built upon diffusion models (ROIC-DM). Benefiting from its training involving denoising stages, ROIC-DM inherently exhibits greater robustness compared to conventional language models. Moreover, ROIC-DM can attain comparable, and in some cases, superior performance to language models, by effectively incorporating them as advisory components. Extensive experiments conducted with several strong textual adversarial attacks on three datasets demonstrate that (1) ROIC-DM outperforms traditional language models in robustness, even when the latter are fortified with advanced defense mechanisms; (2) ROIC-DM can achieve comparable and even better performance than traditional language models by using them as advisors.
Recently, text-guided scalable vector graphics (SVGs) synthesis has shown promise in domains such as iconography and sketch. However, existing text-to-SVG generation methods lack editability and struggle with visual quality and result diversity. To address these limitations, we propose a novel text-guided vector graphics synthesis method called SVGDreamer. SVGDreamer incorporates a semantic-driven image vectorization (SIVE) process that enables the decomposition of synthesis into foreground objects and background, thereby enhancing editability. Specifically, the SIVE process introduce attention-based primitive control and an attention-mask loss function for effective control and manipulation of individual elements. Additionally, we propose a Vectorized Particle-based Score Distillation (VPSD) approach to tackle the challenges of color over-saturation, vector primitives over-smoothing, and limited result diversity in existing text-to-SVG generation methods. Furthermore, on the basis of VPSD, we introduce Reward Feedback Learning (ReFL) to accelerate VPSD convergence and improve aesthetic appeal. Extensive experiments have been conducted to validate the effectiveness of SVGDreamer, demonstrating its superiority over baseline methods in terms of editability, visual quality, and diversity. The code and demo of SVGDreamer can be found at \href{https://ximinng.github.io/SVGDreamer-project/}{https://ximinng.github.io/SVGDreamer-project/}.
This technical report aims to fill a deficiency in the assessment of large multimodal models (LMMs) by specifically examining the self-consistency of their outputs when subjected to common corruptions. We investigate the cross-modal interactions between text, image, and speech, encompassing four essential generation tasks: text-to-image, image-to-text, text-to-speech, and speech-to-text. We create a comprehensive benchmark, named MMCBench, that covers more than 100 popular LMMs (totally over 150 model checkpoints). A thorough evaluation under common corruptions is critical for practical deployment and facilitates a better understanding of the reliability of cutting-edge LMMs. The benchmarking code is available at https://github.com/sail-sg/MMCBench
Recent text-to-image generation models have demonstrated incredible success in generating images that faithfully follow input prompts. However, the requirement of using words to describe a desired concept provides limited control over the appearance of the generated concepts. In this work, we address this shortcoming by proposing an approach to enable personalization capabilities in existing text-to-image diffusion models. We propose a novel architecture (BootPIG) that allows a user to provide reference images of an object in order to guide the appearance of a concept in the generated images. The proposed BootPIG architecture makes minimal modifications to a pretrained text-to-image diffusion model and utilizes a separate UNet model to steer the generations toward the desired appearance. We introduce a training procedure that allows us to bootstrap personalization capabilities in the BootPIG architecture using data generated from pretrained text-to-image models, LLM chat agents, and image segmentation models. In contrast to existing methods that require several days of pretraining, the BootPIG architecture can be trained in approximately 1 hour. Experiments on the DreamBooth dataset demonstrate that BootPIG outperforms existing zero-shot methods while being comparable with test-time finetuning approaches. Through a user study, we validate the preference for BootPIG generations over existing methods both in maintaining fidelity to the reference object's appearance and aligning with textual prompts.
The prevalent approach in speech emotion recognition (SER) involves integrating both audio and textual information to comprehensively identify the speaker's emotion, with the text generally obtained through automatic speech recognition (ASR). An essential issue of this approach is that ASR errors from the text modality can worsen the performance of SER. Previous studies have proposed using an auxiliary ASR error detection task to adaptively assign weights of each word in ASR hypotheses. However, this approach has limited improvement potential because it does not address the coherence of semantic information in the text. Additionally, the inherent heterogeneity of different modalities leads to distribution gaps between their representations, making their fusion challenging. Therefore, in this paper, we incorporate two auxiliary tasks, ASR error detection (AED) and ASR error correction (AEC), to enhance the semantic coherence of ASR text, and further introduce a novel multi-modal fusion (MF) method to learn shared representations across modalities. We refer to our method as MF-AED-AEC. Experimental results indicate that MF-AED-AEC significantly outperforms the baseline model by a margin of 4.1\%.
Recent advancements in large vision-language models (LVLMs) have demonstrated impressive capability in visual information understanding with human language. Despite these advances, LVLMs still face challenges with multimodal hallucination, such as generating text descriptions of objects that are not present in the visual information. However, the underlying fundamental reasons of multimodal hallucinations remain poorly explored. In this paper, we propose a new perspective, suggesting that the inherent biases in LVLMs might be a key factor in hallucinations. Specifically, we systematically identify a semantic shift bias related to paragraph breaks ('$\textbackslash n\textbackslash n$'), where the content before and after '$\textbackslash n\textbackslash n$' in the training data frequently exhibit significant semantic changes. This pattern leads the model to infer that the contents following '$\textbackslash n\textbackslash n$' should be obviously different from the preceding contents with less hallucinatory descriptions, thereby increasing the probability of hallucinatory descriptions subsequent to the '$\textbackslash n\textbackslash n$'. We have validated this hypothesis on multiple publicly available LVLMs. Besides, we find that deliberately inserting '$\textbackslash n\textbackslash n$' at the generated description can induce more hallucinations. A simple method is proposed to effectively mitigate the hallucination of LVLMs by skipping the output of `\textbackslash n'.
Domain randomization is an effective computer vision technique for improving transferability of vision models across visually distinct domains exhibiting similar content. Existing approaches, however, rely extensively on tweaking complex and specialized simulation engines that are difficult to construct, subsequently affecting their feasibility and scalability. This paper introduces BehAVE, a video understanding framework that uniquely leverages the plethora of existing commercial video games for domain randomization, without requiring access to their simulation engines. Under BehAVE (1) the inherent rich visual diversity of video games acts as the source of randomization and (2) player behavior -- represented semantically via textual descriptions of actions -- guides the *alignment* of videos with similar content. We test BehAVE on 25 games of the first-person shooter (FPS) genre across various video and text foundation models and we report its robustness for domain randomization. BehAVE successfully aligns player behavioral patterns and is able to zero-shot transfer them to multiple unseen FPS games when trained on just one FPS game. In a more challenging setting, BehAVE manages to improve the zero-shot transferability of foundation models to unseen FPS games (up to 22%) even when trained on a game of a different genre (Minecraft). Code and dataset can be found at https://github.com/nrasajski/BehAVE.
Fine-tuning large pre-trained language models (LLMs) on particular datasets is a commonly employed strategy in Natural Language Processing (NLP) classification tasks. However, this approach usually results in a loss of models generalizability. In this paper, we present a framework that allows for maintaining generalizability, and enhances the performance on the downstream task by utilizing task-specific context attribution. We show that a linear transformation of the text representation from any transformer model using the task-specific concept operator results in a projection onto the latent concept space, referred to as context attribution in this paper. The specific concept operator is optimized during the supervised learning stage via novel loss functions. The proposed framework demonstrates that context attribution of the text representation for each task objective can improve the capacity of the discriminator function and thus achieve better performance for the classification task. Experimental results on three datasets, namely HateXplain, IMDB reviews, and Social Media Attributions, illustrate that the proposed model attains superior accuracy and generalizability. Specifically, for the non-fine-tuned BERT on the HateXplain dataset, we observe 8% improvement in accuracy and 10% improvement in F1-score. Whereas for the IMDB dataset, fine-tuned state-of-the-art XLNet is outperformed by 1% for both accuracy and F1-score. Furthermore, in an out-of-domain cross-dataset test, DistilBERT fine-tuned on the IMDB dataset in conjunction with the proposed model improves the F1-score on the HateXplain dataset by 7%. For the Social Media Attributions dataset of YouTube comments, we observe 5.2% increase in F1-metric. The proposed framework is implemented with PyTorch and provided open-source on GitHub.
In recent years, large-scale pre-trained multimodal models (LMM) generally emerge to integrate the vision and language modalities, achieving considerable success in various natural language processing and computer vision tasks. The growing size of LMMs, however, results in a significant computational cost for fine-tuning these models for downstream tasks. Hence, prompt-based interaction strategy is studied to align modalities more efficiently. In this contex, we propose a novel prompt-based multimodal interaction strategy inspired by human memory strategy, namely Memory-Inspired Temporal Prompt Interaction (MITP). Our proposed method involves in two stages as in human memory strategy: the acquiring stage, and the consolidation and activation stage. We utilize temporal prompts on intermediate layers to imitate the acquiring stage, leverage similarity-based prompt interaction to imitate memory consolidation, and employ prompt generation strategy to imitate memory activation. The main strength of our paper is that we interact the prompt vectors on intermediate layers to leverage sufficient information exchange between modalities, with compressed trainable parameters and memory usage. We achieve competitive results on several datasets with relatively small memory usage and 2.0M of trainable parameters (about 1% of the pre-trained foundation model).
Apart from what (little) OpenAI may be concealing from us, we all know (roughly) how ChatGPT works (its huge text database, its statistics, its vector representations, and their huge number of parameters, its next-word training, and so on). But none of us can say (hand on heart) that we are not surprised by what ChatGPT has proved to be able to do with these resources. This has even driven some of us to conclude that ChatGPT actually understands. It is not true that it understands. But it is also not true that we understand how it can do what it can do. I will suggest some hunches about benign biases: convergent constraints that emerge at LLM scale that may be helping ChatGPT do so much better than we would have expected. These biases are inherent in the nature of language itself, at LLM scale, and they are closely linked to what it is that ChatGPT lacks, which is direct sensorimotor grounding to connect its words to their referents and its propositions to their meanings. These convergent biases are related to (1) the parasitism of indirect verbal grounding on direct sensorimotor grounding, (2) the circularity of verbal definition, (3) the mirroring of language production and comprehension, (4) iconicity in propositions at LLM scale, (5) computational counterparts of human categorical perception in category learning by neural nets, and perhaps also (6) a conjecture by Chomsky about the laws of thought. The exposition will be in the form of a dialogue with ChatGPT-4.