Large Vision-Language Models (L-VLMs) have demonstrated remarkable performance in various vision and language tasks, including Visual Question Answering (VQA). However, their high computational cost makes them impractical for resource-constrained settings and inference-heavy applications. In contrast, Small Vision-Language Models (S-VLMs) offer efficiency but suffer from a significant performance gap compared to their larger counterparts. In this work, we introduce the Model Parity Aligner (MPA), a novel framework designed to systematically improve S-VLMs by leveraging unlabeled images and effective knowledge transfer from L-VLMs. Instead of traditional knowledge distillation methods that rely on labeled training data, MPA employs a strategic parity-based approach that precisely identifies the knowledge disparities between S-VLMs and L-VLMs, and optimizes training by targeting only these disparities. We conduct extensive experiments on four diverse VQA benchmarks, namely TextVQA, ST-VQA, ChartQA, and OKVQA, each of which required specialized reasoning capabilities such as text recognition, chart interpretation, and commonsense and factual understanding. Our results demonstrate that MPA consistently enhances the performance of S-VLM on all benchmarks, reducing the performance gap while maintaining computational efficiency. We shall make our code and MPA-aligned models publicly available upon acceptance of this work.

We describe the work carried out by our team, AI-Monitors, on the Binary Multilingual Machine-Generated Text Detection (Human vs. Machine) task at COLING 2025. This task aims to determine whether a given text is generated by a machine or authored by a human. We propose a lightweight, simple, and scalable approach using encoder models such as RoBERTa and XLM-R We provide an in-depth analysis based on our experiments. Our study found that carefully exploring fine-tuned parameters such as i) no. of training epochs, ii) maximum input size, iii) handling class imbalance etc., plays an important role in building an effective system to achieve good results and can significantly impact the underlying tasks. We found the optimum setting of these parameters can lead to a difference of about 5-6% in absolute terms for measure such as accuracy and F1 measure. The paper presents crucial insights into optimal parameter selection for fine-tuning RoBERTa and XLM-R based models to detect whether a given text is generated by a machine or a human.

We describe the work carried out by AMEX AI Labs on the structured sentiment analysis task at SemEval-2022. This task focuses on extracting fine grained information w.r.t. to source, target and polar expressions in a given text. We propose a BERT based encoder, which utilizes a novel concatenation mechanism for combining syntactic and pretrained embeddings with BERT embeddings. Our system achieved an average rank of 14/32 systems, based on the average scores across seven datasets for five languages provided for the monolingual task. The proposed BERT based approaches outperformed BiLSTM based approaches used for structured sentiment extraction problem. We provide an in-depth analysis based on our post submission analysis.

We describe work from our investigations of the novel area of multi-modal cross-lingual retrieval (MMCLIR) under low-resource conditions. We study the challenges associated with MMCLIR relating to: (i) data conversion between different modalities, for example speech and text, (ii) overcoming the language barrier between source and target languages; (iii) effectively scoring and ranking documents to suit the retrieval task; and (iv) handling low resource constraints that prohibit development of heavily tuned machine translation (MT) and automatic speech recognition (ASR) systems. We focus on the use case of retrieving text and speech documents in Swahili, using English queries which was the main focus of the OpenCLIR shared task. Our work is developed within the scope of this task. In this paper we devote special attention to the automatic translation (AT) component which is crucial for the overall quality of the MMCLIR system. We exploit a combination of dictionaries and phrase-based statistical machine translation (MT) systems to tackle effectively the subtask of query translation. We address each MMCLIR challenge individually, and develop separate components for automatic translation (AT), speech processing (SP) and information retrieval (IR). We find that results with respect to cross-lingual text retrieval are quite good relative to the task of cross-lingual speech retrieval. Overall we find that the task of MMCLIR and specifically cross-lingual speech retrieval is quite complex. Further we pinpoint open issues related to handling cross-lingual audio and text retrieval for low resource languages that need to be addressed in future research.

We describe the work carried out by AMEX AI-LABS on an extractive summarization benchmark task focused on Financial Narratives Summarization (FNS). This task focuses on summarizing annual financial reports which poses two main challenges as compared to typical news document summarization tasks : i) annual reports are more lengthier (average length about 80 pages) as compared to typical news documents, and ii) annual reports are more loosely structured e.g. comprising of tables, charts, textual data and images, which makes it challenging to effectively summarize. To address this summarization task we investigate a range of unsupervised, supervised and ensemble based techniques. We find that ensemble based techniques perform relatively better as compared to using only the unsupervised and supervised based techniques. Our ensemble based model achieved the highest rank of 9 out of 31 systems submitted for the benchmark task based on Rouge-L evaluation metric.

With recent developments in web technologies, percentage web content in Hindi is growing up at a lighting speed. This information can prove to be very useful for researchers, governments and organization to learn what's on public mind, to make sound decisions. In this paper, we present a graph based wordnet expansion method to generate a full (adjective and adverb) subjective lexicon. We used synonym and antonym relations to expand the initial seed lexicon. We show three different evaluation strategies to validate the lexicon. We achieve 70.4% agreement with human annotators and ∼79% accuracy on product review classification. Main contribution of our work 1) Developing a lexicon of adjectives and adverbs with polarity scores using Hindi Wordnet. 2) Developing an annotated corpora of Hindi Product Reviews.