The creation of high-quality human-labeled image-caption datasets presents a significant bottleneck in the development of Visual-Language Models (VLMs). In this work, we investigate an approach that leverages the strengths of Large Language Models (LLMs) and image generation models to create synthetic image-text pairs for efficient and effective VLM training. Our method employs a pretrained text-to-image model to synthesize image embeddings from captions generated by an LLM. Despite the text-to-image model and VLM initially being trained on the same data, our approach leverages the image generator's ability to create novel compositions, resulting in synthetic image embeddings that expand beyond the limitations of the original dataset. Extensive experiments demonstrate that our VLM, finetuned on synthetic data achieves comparable performance to models trained solely on human-annotated data, while requiring significantly less data. Furthermore, we perform a set of analyses on captions which reveals that semantic diversity and balance are key aspects for better downstream performance. Finally, we show that synthesizing images in the image embedding space is 25\% faster than in the pixel space. We believe our work not only addresses a significant challenge in VLM training but also opens up promising avenues for the development of self-improving multi-modal models.

We introduce the novel task of zero-shot Protein Question Answering (PQA) for free-form scientific enquiry. Given a previously unseen protein sequence and a natural language question, the task is to deliver a scientifically accurate answer. This task not only supports future biological research, but could also provide a test bed for assessing the scientific precision of large language models (LLMs). We contribute the first specialized dataset for PQA model training, containing 257K protein sequences annotated with 1.97M scientific question-answer pairs. Additionally, we propose and study several novel biologically relevant benchmarks for scientific PQA. Employing two robust multi-modal architectures, we establish an initial state-of-the-art performance for PQA and reveal key performance factors through ablation studies. Our comprehensive PQA framework, named Pika, including dataset, code, model checkpoints, and a user-friendly demo, is openly accessible on github.com/EMCarrami/Pika, promoting wider research and application in the field.

The field of multimodal research focusing on the comprehension and creation of both images and text has witnessed significant strides. This progress is exemplified by the emergence of sophisticated models dedicated to image captioning at scale, such as the notable Flamingo model and text-to-image generative models, with DALL-E serving as a prominent example. An interesting question worth exploring in this domain is whether Flamingo and DALL-E understand each other. To study this question, we propose a reconstruction task where Flamingo generates a description for a given image and DALL-E uses this description as input to synthesize a new image. We argue that these models understand each other if the generated image is similar to the given image. Specifically, we study the relationship between the quality of the image reconstruction and that of the text generation. We find that an optimal description of an image is one that gives rise to a generated image similar to the original one. The finding motivates us to propose a unified framework to finetune the text-to-image and image-to-text models. Concretely, the reconstruction part forms a regularization loss to guide the tuning of the models. Extensive experiments on multiple datasets with different image captioning and image generation models validate our findings and demonstrate the effectiveness of our proposed unified framework. As DALL-E and Flamingo are not publicly available, we use Stable Diffusion and BLIP in the remaining work. Project website: https://dalleflamingo.github.io.

Memes are a popular form of communicating trends and ideas in social media and on the internet in general, combining the modalities of images and text. They can express humor and sarcasm but can also have offensive content. Analyzing and classifying memes automatically is challenging since their interpretation relies on the understanding of visual elements, language, and background knowledge. Thus, it is important to meaningfully represent these sources and the interaction between them in order to classify a meme as a whole. In this work, we propose to use scene graphs, that express images in terms of objects and their visual relations, and knowledge graphs as structured representations for meme classification with a Transformer-based architecture. We compare our approach with ImgBERT, a multimodal model that uses only learned (instead of structured) representations of the meme, and observe consistent improvements. We further provide a dataset with human graph annotations that we compare to automatically generated graphs and entity linking. Analysis shows that automatic methods link more entities than human annotators and that automatically generated graphs are better suited for hatefulness classification in memes.

Simulating high-resolution detector responses is a storage-costly and computationally intensive process that has long been challenging in particle physics. Despite the ability of deep generative models to make this process more cost-efficient, ultra-high-resolution detector simulation still proves to be difficult as it contains correlated and fine-grained mutual information within an event. To overcome these limitations, we propose Intra-Event Aware GAN (IEA-GAN), a novel fusion of Self-Supervised Learning and Generative Adversarial Networks. IEA-GAN presents a Relational Reasoning Module that approximates the concept of an ''event'' in detector simulation, allowing for the generation of correlated layer-dependent contextualized images for high-resolution detector responses with a proper relational inductive bias. IEA-GAN also introduces a new intra-event aware loss and a Uniformity loss, resulting in significant enhancements to image fidelity and diversity. We demonstrate IEA-GAN's application in generating sensor-dependent images for the high-granularity Pixel Vertex Detector (PXD), with more than 7.5M information channels and a non-trivial geometry, at the Belle II Experiment. Applications of this work include controllable simulation-based inference and event generation, high-granularity detector simulation such as at the HL-LHC (High Luminosity LHC), and fine-grained density estimation and sampling. To the best of our knowledge, IEA-GAN is the first algorithm for faithful ultra-high-resolution detector simulation with event-based reasoning.

We present a unified computational theory of perception and memory. In our model, perception, episodic memory, and semantic memory are realized by different functional and operational modes of the oscillating interactions between an index layer and a representation layer in a bilayer tensor network (BTN). The memoryless semantic {representation layer} broadcasts information. In cognitive neuroscience, it would be the "mental canvas", or the "global workspace" and reflects the cognitive brain state. The symbolic {index layer} represents concepts and past episodes, whose semantic embeddings are implemented in the connection weights between both layers. In addition, we propose a {working memory layer} as a processing center and information buffer. Episodic and semantic memory realize memory-based reasoning, i.e., the recall of relevant past information to enrich perception, and are personalized to an agent's current state, as well as to an agent's unique memories. Episodic memory stores and retrieves past observations and provides provenance and context. Recent episodic memory enriches perception by the retrieval of perceptual experiences, which provide the agent with a sense about the here and now: to understand its own state, and the world's semantic state in general, the agent needs to know what happened recently, in recent scenes, and on recently perceived entities. Remote episodic memory retrieves relevant past experiences, contributes to our conscious self, and, together with semantic memory, to a large degree defines who we are as individuals.

The heterogeneity in recently published knowledge graph embedding models' implementations, training, and evaluation has made fair and thorough comparisons difficult. In order to assess the reproducibility of previously published results, we re-implemented and evaluated 19 interaction models in the PyKEEN software package. Here, we outline which results could be reproduced with their reported hyper-parameters, which could only be reproduced with alternate hyper-parameters, and which could not be reproduced at all as well as provide insight as to why this might be the case. We then performed a large-scale benchmarking on four datasets with several thousands of experiments and 21,246 GPU hours of computation time. We present insights gained as to best practices, best configurations for each model, and where improvements could be made over previously published best configurations. Our results highlight that the combination of model architecture, training approach, loss function, and the explicit modeling of inverse relations is crucial for a model's performances, and not only determined by the model architecture. We provide evidence that several architectures can obtain results competitive to the state-of-the-art when configured carefully. We have made all code, experimental configurations, results, and analyses that lead to our interpretations available at https://github.com/pykeen/pykeen and https://github.com/pykeen/benchmarking

Recently, knowledge graph embeddings (KGEs) received significant attention, and several software libraries have been developed for training and evaluating KGEs. While each of them addresses specific needs, we re-designed and re-implemented PyKEEN, one of the first KGE libraries, in a community effort. PyKEEN 1.0 enables users to compose knowledge graph embedding models (KGEMs) based on a wide range of interaction models, training approaches, loss functions, and permits the explicit modeling of inverse relations. Besides, an automatic memory optimization has been realized in order to exploit the provided hardware optimally, and through the integration of Optuna extensive hyper-parameter optimization (HPO) functionalities are provided.

State of the art visual relation detection methods have been relying on features extracted from RGB images including objects' 2D positions. In this paper, we argue that the 3D positions of objects in space can provide additional valuable information about object relations. This information helps not only to detect spatial relations, such as "standing behind", but also non-spatial relations, such as "holding". Since 3D information of a scene is not easily accessible, we propose incorporating a pre-trained RGB-to-Depth model within visual relation detection frameworks. We discuss different feature extraction strategies from depth maps and show their critical role in relation detection. Our experiments confirm that the performance of state-of-the-art visual relation detection approaches can significantly be improved by utilizing depth map information.

We propose an inverse reinforcement learning (IRL) approach using Deep Q-Networks to extract the rewards in problems with large state spaces. We evaluate the performance of this approach in a simulation-based autonomous driving scenario. Our results resemble the intuitive relation between the reward function and readings of distance sensors mounted at different poses on the car. We also show that, after a few learning rounds, our simulated agent generates collision-free motions and performs human-like lane change behaviour.