10 papers
Understanding Submodular Information Measure Based Objectives for Representation Learning: A Variance and Separation Perspective
Rishabh Iyer, Truong Pham, Anay Majee
Submodular Information Measures (SIMs) have recently emerged as a powerful framework for representation learning and multimodal learning. In particular, the SCORE framework~\cite{m…
SHaSaM: Submodular Hard Sample Mining for Fair Facial Attribute Recognition
Anay Majee, Rishabh Iyer
Deep neural networks often inherit social and demographic biases from annotated data during model training, leading to unfair predictions, especially in the presence of sensitive a…
Explicit Entropic Constructions for Coverage, Facility Location, and Graph Cuts
Rishabh Iyer
Shannon entropy is a polymatroidal set function and lies at the foundation of information theory, yet the class of entropic polymatroids is strictly smaller than the class of all s…
Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detection
Anay Majee, Amitesh Gangrade, Rishabh Iyer
Open-World Object Detection (OWOD) enriches traditional object detectors by enabling continual discovery and integration of unknown objects via human guidance. However, existing OW…
InSQuAD: In-Context Learning for Efficient Retrieval via Submodular Mutual Information to Enforce Quality and Diversity
Souradeep Nanda, Anay Majee, Rishabh Iyer
In this paper, we introduce InSQuAD, designed to enhance the performance of In-Context Learning (ICL) models through Submodular Mutual Information} (SMI) enforcing Quality and Dive…
AI Agents for Photonic Integrated Circuit Design Automation
Ankita Sharma, YuQi Fu, Vahid Ansari +8
We present Photonics Intelligent Design and Optimization (PhIDO), a multi-agent framework that converts natural-language photonic integrated circuit (PIC) design requests into layo…
Predicting Brain Responses To Natural Movies With Multimodal LLMs
Cesar Kadir Torrico Villanueva, Jiaxin Cindy Tu, Mihir Tripathy +3
We present MedARC's team solution to the Algonauts 2025 challenge. Our pipeline leveraged rich multimodal representations from various state-of-the-art pretrained models across vid…
SMILe: Leveraging Submodular Mutual Information For Robust Few-Shot Object Detection
Anay Majee, Ryan Sharp, Rishabh Iyer
Confusion and forgetting of object classes have been challenges of prime interest in Few-Shot Object Detection (FSOD). To overcome these pitfalls in metric learning based FSOD tech…
STENCIL: Submodular Mutual Information Based Weak Supervision for Cold-Start Active Learning
Nathan Beck, Adithya Iyer, Rishabh Iyer
As supervised fine-tuning of pre-trained models within NLP applications increases in popularity, larger corpora of annotated data are required, especially with increasing parameter…
Theoretical Analysis of Submodular Information Measures for Targeted Data Subset Selection
Nathan Beck, Truong Pham, Rishabh Iyer
With increasing volume of data being used across machine learning tasks, the capability to target specific subsets of data becomes more important. To aid in this capability, the re…