arXiv subjects

Nistha Mitra

Publications and source records attributed to Nistha Mitra.

3 recordsLinked to original sources

arXiv2026

Au-M-ol: A Unified Model for Medical Audio and Language Understanding

In this work, we present Au-M-ol, a novel multimodal architecture that extends Large Language Models (LLMs) with audio processing. It is designed to improve performance on clinically relevant tasks such as Automatic Speech Recognition (ASR). Au-M-ol has three main components: (1) an audio encoder that extracts rich acoustic features from medical speech, (2) an adaptation layer that maps audio features into the LLM input space, and (3) a pretrained LLM that performs transcription and clinical language understanding. This design allows the model to interpret spoken medical content directly, improving both accuracy and robustness. In experiments, Au-M-ol reduces Word Error Rate (WER) by 56\% compared to state-of-the-art baselines on medical transcription tasks. The model also performs well in challenging conditions, including noisy environments, domain-specific terminology, and speaker variability. These results suggest that Au-M-ol is a strong candidate for real-world clinical applications, where reliable and context-aware audio understanding is essential.

cs.CL↗

arXiv2025

Syllabus: Portable Curricula for Reinforcement Learning Agents

Curriculum learning has been a quiet, yet crucial component of many high-profile successes of reinforcement learning. Despite this, it is still a niche topic that is not directly supported by any of the major reinforcement learning libraries. These methods can improve the capabilities and generalization of RL agents, but often require complex changes to training code. We introduce Syllabus, a portable curriculum learning library, as a solution to this problem. Syllabus provides a universal API for curriculum learning, modular implementations of popular automatic curriculum learning methods, and infrastructure that allows them to be easily integrated with asynchronous training code in nearly any RL library. Syllabus provides a minimal API for core curriculum learning components, making it easier to design new algorithms and adapt existing ones to new environments. We demonstrate this by evaluating the algorithms in Syllabus on several new environments, each using agents written in a different RL library. We present the first examples of automatic curriculum learning in NetHack and Neural MMO, two of the most challenging RL benchmarks, and find evidence that existing methods do not directly transfer to complex new environments. Syllabus can be found at https://github.com/RyanNavillus/Syllabus.

cs.AI↗

arXiv2023

A Comparative Evaluation of Visual Summarization Techniques for Event Sequences

Real-world event sequences are often complex and heterogeneous, making it difficult to create meaningful visualizations using simple data aggregation and visual encoding techniques. Consequently, visualization researchers have developed numerous visual summarization techniques to generate concise overviews of sequential data. These techniques vary widely in terms of summary structures and contents, and currently there is a knowledge gap in understanding the effectiveness of these techniques. In this work, we present the design and results of an insight-based crowdsourcing experiment evaluating three existing visual summarization techniques: CoreFlow, SentenTree, and Sequence Synopsis. We compare the visual summaries generated by these techniques across three tasks, on six datasets, at six levels of granularity. We analyze the effects of these variables on summary quality as rated by participants and completion time of the experiment tasks. Our analysis shows that Sequence Synopsis produces the highest-quality visual summaries for all three tasks, but understanding Sequence Synopsis results also takes the longest time. We also find that the participants evaluate visual summary quality based on two aspects: content and interpretability. We discuss the implications of our findings on developing and evaluating new visual summarization techniques.

cs.HC↗