6 papers
Not All Attention Is Equal: A Quantitative Survey of the EEI Trade-off
Aditya Singh
Attention mechanisms have driven machine learning for a decade, from neural machine translation to language models that do general-purpose reasoning. This survey covers four connec…
The Voronoi Bottleneck: Capacity-Aware Dense Retrieval for Product Search
Charith Chandra Sai Balne, Rithwik Maramraju, Siddharth Pratap Singh +4
Dense embedding retrieval compresses all relevance information into a single inner product, imposing a fundamental geometric limit -- the Voronoi Bottleneck -- on the number of que…
T2I-BiasBench: A Multi-Metric Framework for Auditing Demographic and Cultural Bias in Text-to-Image Models
Nihal Jaiswal, Siddhartha Arjaria, Gyanendra Chaubey +3
Text-to-image (T2I) generative models achieve impressive visual fidelity but inherit and amplify demographic imbalances and cultural biases embedded in training data. We introduce…
DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference
Aditya Kumar Singh, Hitesh Kandala, Pratik Prabhanjan Brahma +2
Vision-language models (VLMs) have achieved remarkable multimodal understanding and reasoning capabilities, yet remain computationally expensive due to dense visual tokenization. E…
Simple Unsupervised Knowledge Distillation With Space Similarity
Aditya Singh, Haohan Wang
As per recent studies, Self-supervised learning (SSL) does not readily extend to smaller architectures. One direction to mitigate this shortcoming while simultaneously training a s…
Approximate Nullspace Augmented Finetuning for Robust Vision Transformers
Haoyang Liu, Aditya Singh, Yijiang Li +1
Enhancing the robustness of deep learning models, particularly in the realm of vision transformers (ViTs), is crucial for their real-world deployment. In this work, we provide a fi…