We present LoCoVQA, a dynamic benchmark generator for evaluating long-context reasoning in vision language models (VLMs). LoCoVQA augments test examples for mathematical reasoning, VQA, and character recognition tasks with increasingly long visual contexts composed of both in-distribution and out-of-distribution distractor images.Across these tasks, a diverse set of VLMs rapidly lose performance as the visual context length grows, often exhibiting a striking logarithmic decay trend. This test assesses how well VLMs can ignore irrelevant information when answering queries—a task that is quite easy for language models (LMs) in the text domain—demonstrating that current state-of-the-art VLMs lack this essential capability for many long-context applications.

Recent years have witnessed interest in Temporal Question Answering over Knowledge Graphs (TKGQA), resulting in the development of multiple methods. However, these are highly engineered, thereby limiting their generalizability, and they do not automatically discover relevant parts of the KG during multi-hop reasoning. Relational graph convolutional networks (RGCN) provide an opportunity to address both of these challenges – we explore this direction in the paper. Specifically, we propose a novel, intuitive and interpretable scheme to modulate the messages passed through a KG edge during convolution based on the relevance of its associated period to the question. We also introduce a gating device to predict if the answer to a complex temporal question is likely to be a KG entity or time and use this prediction to guide our scoring mechanism. We evaluate the resulting system, which we call TwiRGCN, on a recent challenging dataset for multi-hop complex temporal QA called TimeQuestions. We show that TwiRGCN significantly outperforms state-of-the-art models on this dataset across diverse question types. Interestingly, TwiRGCN improves accuracy by 9–10 percentage points for the most difficult ordinal and implicit question types.

Sanskrit is one of the oldest languages of the Asian Subcontinent that fell out of common usage around 600 B.C. In this paper, we attempt to translate Sanskrit to English using Neural Machine Translation approaches based on Reinforcement Learning and Transfer learning that were never tried and tested on Sanskrit. Along with the paper, we also release monolingual Sanskrit and parallel aligned Sanskrit-English corpora for the research community. Our methodologies outperform the previous approaches applied to Sanskrit by various re- searchers and will further help the linguistic community to accelerate the costly and time consuming manual translation process.

Knowledge Graph (KG) embedding has emerged as a very active area of research over the last few years, resulting in the development of several embedding methods. These KG embedding methods represent KG entities and relations as vectors in a high-dimensional space. Despite this popularity and effectiveness of KG embeddings in various tasks (e.g., link prediction), geometric understanding of such embeddings (i.e., arrangement of entity and relation vectors in vector space) is unexplored – we fill this gap in the paper. We initiate a study to analyze the geometry of KG embeddings and correlate it with task performance and other hyperparameters. To the best of our knowledge, this is the first study of its kind. Through extensive experiments on real-world datasets, we discover several insights. For example, we find that there are sharp differences between the geometry of embeddings learnt by different classes of KG embeddings methods. We hope that this initial study will inspire other follow-up research on this important but unexplored problem.

RLIE-DQN is a recently proposed Reinforcement Learning-based Information Extraction (IE) technique which is able to incorporate external evidence during the extraction process. RLIE-DQN trains a single agent sequentially, training on one instance at a time. This results in significant training slowdown which is undesirable. We leverage recent advances in parallel RL training using asynchronous methods and propose RLIE-A3C. RLIE-A3C trains multiple agents in parallel and is able to achieve upto 6x training speedup over RLIE-DQN, while suffering no loss in average accuracy.