The opioid crisis represents a significant moment in public health that reveals systemic shortcomings across regulatory systems, healthcare practices, corporate governance, and public policy. Analyzing how these interconnected systems simultaneously failed to protect public health requires innovative analytic approaches for exploring the vast amounts of data and documents disclosed in the UCSF-JHU Opioid Industry Documents Archive (OIDA). The complexity, multimodal nature, and specialized characteristics of these healthcare-related legal and corporate documents necessitate more advanced methods and models tailored to specific data types and detailed annotations, ensuring the precision and professionalism in the analysis. In this paper, we tackle this challenge by organizing the original dataset according to document attributes and constructing a benchmark with 400k training documents and 10k for testing. From each document, we extract rich multimodal information—including textual content, visual elements, and layout structures—to capture a comprehensive range of features. Using multiple AI models, we then generate a large-scale dataset comprising 360k training QA pairs and 10k testing QA pairs. Building on this foundation, we develop domain-specific multimodal Large Language Models (LLMs) and explore the impact of multimodal inputs on task performance. To further enhance response accuracy, we incorporate historical QA pairs as contextual grounding for answering current queries. Additionally, we incorporate page references within the answers and introduce an importance-based page classifier, further improving the precision and relevance of the information provided. Preliminary results indicate the improvements with our AI assistant in document information extraction and question-answering tasks.

Multimodal Language Language Models (MLLMs) demonstrate the emerging abilities of "world models"---interpreting and reasoning about complex real-world dynamics. To assess these abilities, we posit videos are the ideal medium, as they encapsulate rich representations of real-world dynamics and causalities. To this end, we introduce MMWorld, a new benchmark for multi-discipline, multi-faceted multimodal video understanding. MMWorld distinguishes itself from previous video understanding benchmarks with two unique advantages: (1) multi-discipline, covering various disciplines that often require domain expertise for comprehensive understanding; (2) multi-faceted reasoning, including explanation, counterfactual thinking, future prediction, etc. MMWorld consists of a human-annotated dataset to evaluate MLLMs with questions about the whole videos and a synthetic dataset to analyze MLLMs within a single modality of perception. Together, MMWorld encompasses 1,910 videos across seven broad disciplines and 69 subdisciplines, complete with 6,627 question-answer pairs and associated captions. The evaluation includes 4 proprietary and 11 open-source MLLMs, which struggle on MMWorld (e.g., GPT-4o performs the best with only 62.5% accuracy), showing large room for improvement. Further ablation studies reveal other interesting findings such as models' different skill sets from humans. We hope MMWorld can serve as an essential step towards world model evaluation in videos.

Incremental decision making in real-world environments is one of the most challenging tasks in embodied artificial intelligence. One particularly demanding scenario is Vision and Language Navigation (VLN) which requires visual and natural language understanding as well as spatial and temporal reasoning capabilities. The embodied agent needs to ground its understanding of navigation instructions in observations of a real-world environment like Street View. Despite the impressive results of LLMs in other research areas, it is an ongoing problem of how to best connect them with an interactive visual environment. In this work, we propose VELMA, an embodied LLM agent that uses a verbalization of the trajectory and of visual environment observations as contextual prompt for the next action. Visual information is verbalized by a pipeline that extracts landmarks from the human written navigation instructions and uses CLIP to determine their visibility in the current panorama view. We show that VELMA is able to successfully follow navigation instructions in Street View with only two in-context examples. We further finetune the LLM agent on a few thousand examples and achieve around 25% relative improvement in task completion over the previous state-of-the-art for two datasets.

The field of text-to-image (T2I) generation has garnered significant attention both within the research community and among everyday users.Despite the advancements of T2I models, a common issue encountered by users is the need for repetitive editing of input prompts in order to receive a satisfactory image, which is time-consuming and labor-intensive.Given the demonstrated text generation power of largescale language models, such as GPT-k, we investigate the potential of utilizing such models to improve the prompt editing process for T2I generation.We conduct a series of experiments to compare the common edits made by humans and GPT-k, evaluate the performance of GPT-k in prompting T2I, and examine factors that may influence this process.We found that GPT-k models focus more on inserting modifiers while humans tend to replace words and phrases, which includes changes to the subject matter.Experimental results show that GPT-k are more effective in adjusting modifiers rather than predicting spontaneous changes in the primary subject matters.Adopting the edit suggested by GPT-k models may reduce the percentage of remaining edits by 20-30%. 1 Our experiments are conducted upon StableDiffusion since it is a wide-adopted open-source large text-to-image generative model with SoTA performance.

We introduce VisIT-Bench (Visual InsTruction Benchmark), a benchmark for evaluating instruction-following vision-language models for real-world use. Our starting point is curating 70 "instruction families" that we envision instruction tuned vision-language models should be able to address. Extending beyond evaluations like VQAv2 and COCO, tasks range from basic recognition to game playing and creative generation. Following curation, our dataset comprises 592 test queries, each with a human-authored instruction-conditioned caption. These descriptions surface instruction-specific factors, e.g., for an instruction asking about the accessibility of a storefront for wheelchair users, the instruction-conditioned caption describes ramps/potential obstacles. These descriptions enable 1) collecting human-verified reference outputs for each instance; and 2) automatic evaluation of candidate multimodal generations using a text-only LLM, aligning with human judgment. We quantify quality gaps between models and references using both human and automatic evaluations; e.g., the top-performing instruction-following model wins against the GPT-4 reference in just 27% of the comparison. VisIT-Bench is dynamic to participate, practitioners simply submit their model's response on the project website; Data, code and leaderboard is available at https://visit-bench.github.io/.

Attaining a high degree of user controllability in visual generation often requires intricate, fine-grained inputs like layouts. However, such inputs impose a substantial burden on users when compared to simple text inputs. To address the issue, we study how Large Language Models (LLMs) can serve as visual planners by generating layouts from text conditions, and thus collaborate with visual generative models. We propose LayoutGPT, a method to compose in-context visual demonstrations in style sheet language to enhance visual planning skills of LLMs. We show that LayoutGPT can generate plausible layouts in multiple domains, ranging from 2D images to 3D indoor scenes. LayoutGPT also shows superior performance in converting challenging language concepts like numerical and spatial relations to layout arrangements for faithful text-to-image generation. When combined with a downstream image generation model, LayoutGPT outperforms text-to-image models/systems by 20-40\% and achieves comparable performance as human users in designing visual layouts for numerical and spatial correctness. Lastly, LayoutGPT achieves comparable performance to supervised methods in 3D indoor scene synthesis, demonstrating its effectiveness and potential in multiple visual domains.

In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context learning. However, existing literature has highlighted the sensitivity of this capability to the selection of few-shot demonstrations. Current understandings of the underlying mechanisms by which this capability arises from regular language model pretraining objectives remain disconnected from the real-world LLMs. This study aims to examine the in-context learning phenomenon through a Bayesian lens, viewing real-world LLMs as latent variable models. On this premise, we propose an algorithm to select optimal demonstrations from a set of annotated data with a small LM, and then directly generalize the selected demonstrations to larger LMs. We demonstrate significant improvement over baselines, averaged over eight GPT models on eight real-world text classification datasets. We also demonstrate the real-world usefulness of our algorithm on GSM8K, a math word problem dataset. Our empirical findings support our hypothesis that LLMs implicitly infer a latent variable containing task information.

In-context vision and language models like Flamingo support arbitrarily interleaved sequences of images and text as input.This format not only enables few-shot learning via interleaving independent supervised (image, text) examples, but also, more complex prompts involving interaction between images, e.g., ``What do image A and image B have in common?''To support this interface, pretraining occurs over web corpora that similarly contain interleaved images+text.To date, however, large-scale data of this form have not been publicly available.We release Multimodal C4, an augmentation of the popular text-only C4 corpus with images interleaved.We use a linear assignment algorithm to place images into longer bodies of text using CLIP features, a process that we show outperforms alternatives.Multimodal C4 spans everyday topics like cooking, travel, technology, etc. A manual inspection of a random sample of documents shows that a vast majority (88\%) of images are topically relevant, and that linear assignment frequently selects individual sentences specifically well-aligned with each image (80\%). After filtering NSFW images, ads, etc., the resulting corpus consists of 101.2M documents with 571M images interleaved in 43B English tokens.

Dense video captioning aims to identify the events of interest in an input video, and generate descriptive captions for each event. Previous approaches usually follow a two-stage generative process, which first proposes a segment for each event, then renders a caption for each identified segment. Recent advances in large-scale sequence generation pretraining have seen great success in unifying task formulation for a great variety of tasks, but so far, more complex tasks such as dense video captioning are not able to fully utilize this powerful paradigm. In this work, we show how to model the two subtasks of dense video captioning jointly as one sequence generation task, and simultaneously predict the events and the corresponding descriptions. Experiments on YouCook2 and ViTT show encouraging results and indicate the feasibility of training complex tasks such as end-to-end dense video captioning integrated into large-scale pretrained models.

Yujie Lu, Wanrong Zhu, Xin Wang, Miguel Eckstein, William Yang Wang. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Wanrong Zhu, Yuankai Qi, Pradyumna Narayana, Kazoo Sone, Sugato Basu, Xin Wang, Qi Wu, Miguel Eckstein, William Yang Wang. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

In this paper, we study the concentration property of stochastic gradient descent (SGD) solutions. In existing concentration analyses, researchers impose restrictive requirements on the gradient noise, such as boundedness or sub-Gaussianity. We consider a much richer class of noise where only finitely-many moments are required, thus allowing heavy-tailed noises. In particular, we obtain Nagaev type high-probability upper bounds for the estimation errors of averaged stochastic gradient descent (ASGD) in a linear model. Specifically, we prove that, after $T$ steps of SGD, the ASGD estimate achieves an $O(\sqrt{\log(1/\delta)/T} + (\delta T^{q-1})^{-1/q})$ error rate with probability at least $1-\delta$, where $q>2$ controls the tail of the gradient noise. In comparison, one has the $O(\sqrt{\log(1/\delta)/T})$ error rate for sub-Gaussian noises. We also show that the Nagaev type upper bound is almost tight through an example, where the exact asymptotic form of the tail probability can be derived. Our concentration analysis indicates that, in the case of heavy-tailed noises, the polynomial dependence on the failure probability $\delta$ is generally unavoidable for the error rate of SGD.

Wanrong Zhu, Xin Wang, Tsu-Jui Fu, An Yan, Pradyumna Narayana, Kazoo Sone, Sugato Basu, William Yang Wang. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 2021.

A major challenge in visually grounded language generation is to build robust benchmark datasets and models that can generalize well in real-world settings.To do this, it is critical to ensure that our evaluation protocols are correct, and benchmarks are reliable.In this work, we set forth to design a set of experiments to understand an important but often ignored problem in visually grounded language generation: given that humans have different utilities and visual attention, how will the sample variance in multi-reference datasets affect the models' performance?Empirically, we study several multi-reference datasets and corresponding vision-and-language tasks.We show that it is of paramount importance to report variance in experiments; that humangenerated references could vary drastically in different datasets/tasks, revealing the nature of each task; that metric-wise, CIDEr has shown systematically larger variances than others.Our evaluations on reference-per-instance shed light on the design of reliable datasets in the future.