24 citations · 118 across the 50 of their papers we have counts for
53 papers
Uncertainty-Guided Inference-Time Depth Adaptation for Transformer-Based Visual Tracking
Patrick Poggi, Divake Kumar, Theja Tulabandhula +1
Transformer-based single-object trackers achieve state-of-the-art accuracy but rely on fixed-depth inference, executing the full encoder--decoder stack for every frame regardless o…
MEMETRON: Metaheuristic Mechanisms for Test-time Response Optimization of Large Language Models
Son The Nguyen, Theja Tulabandhula
Large language models (LLMs) are increasingly used for both open-ended and structured tasks, yet their inference-time behavior is still largely dictated by heuristic decoding strat…
Prediction of Lung Metastasis from Hepatocellular Carcinoma using the SEER Database
Jeff J. H. Kim, George R. Nahass, Yang Dai +1
Hepatocellular carcinoma (HCC) is a leading cause of cancer-related mortality, with lung metastases being the most common site of distant spread and significantly worsening prognos…
Enhancing 3D Robotic Vision Robustness by Minimizing Adversarial Mutual Information through a Curriculum Training Approach
Nastaran Darabi, Dinithi Jayasuriya, Devashri Naik +2
Adversarial attacks exploit vulnerabilities in a model's decision boundaries through small, carefully crafted perturbations that lead to significant mispredictions. In 3D vision, t…
Sense Less, Generate More: Pre-training LiDAR Perception with Masked Autoencoders for Ultra-Efficient 3D Sensing
Sina Tayebati, Theja Tulabandhula, Amit R. Trivedi
In this work, we propose a disruptively frugal LiDAR perception dataflow that generates rather than senses parts of the environment that are either predictable based on the extensi…
CURATRON: Complete and Robust Preference Data for Rigorous Alignment of Large Language Models
Son The Nguyen, Niranjan Uma Naresh, Theja Tulabandhula
This paper addresses the challenges of aligning large language models (LLMs) with human values via preference learning (PL), focusing on incomplete and corrupted data in preference…
InteraRec: Screenshot Based Recommendations Using Multimodal Large Language Models
Saketh Reddy Karra, Theja Tulabandhula
Weblogs, comprised of records detailing user activities on any website, offer valuable insights into user preferences, behavior, and interests. Numerous recommendation algorithms,…
Echoes of Socratic Doubt: Embracing Uncertainty in Calibrated Evidential Reinforcement Learning
Alex Christopher Stutts, Danilo Erricolo, Theja Tulabandhula +1
We present a novel statistical approach to incorporating uncertainty awareness in model-free distributional reinforcement learning involving quantile regression-based deep Q networ…
User Friendly and Adaptable Discriminative AI: Using the Lessons from the Success of LLMs and Image Generation Models
Son The Nguyen, Theja Tulabandhula, Mary Beth Watson-Manheim
While there is significant interest in using generative AI tools as general-purpose models for specific ML applications, discriminative models are much more widely deployed current…
InteraSSort: Interactive Assortment Planning Using Large Language Models
Saketh Reddy Karra, Theja Tulabandhula
Assortment planning, integral to multiple commercial offerings, is a key problem studied in e-commerce and retail settings. Numerous variants of the problem along with their integr…
Dynamic Tiling: A Model-Agnostic, Adaptive, Scalable, and Inference-Data-Centric Approach for Efficient and Accurate Small Object Detection
Son The Nguyen, Theja Tulabandhula, Duy Nguyen
We introduce Dynamic Tiling, a model-agnostic, adaptive, and scalable approach for small object detection, anchored in our inference-data-centric philosophy. Dynamic Tiling starts…
Conformalized Multimodal Uncertainty Regression and Reasoning
Domenico Parente, Nastaran Darabi, Alex C. Stutts +2
This paper introduces a lightweight uncertainty estimator capable of predicting multimodal (disjoint) uncertainty bounds by integrating conformal prediction with a deep-learning re…
STARNet: Sensor Trustworthiness and Anomaly Recognition via Approximated Likelihood Regret for Robust Edge Autonomy
Nastaran Darabi, Sina Tayebati, Sureshkumar S. +3
Complex sensors such as LiDAR, RADAR, and event cameras have proliferated in autonomous robotics to enhance perception and understanding of the environment. Meanwhile, these sensor…
Mutual Information-calibrated Conformal Feature Fusion for Uncertainty-Aware Multimodal 3D Object Detection at the Edge
Alex C. Stutts, Danilo Erricolo, Sathya Ravi +2
In the expanding landscape of AI-enabled robotics, robust quantification of predictive uncertainties is of great importance. Three-dimensional (3D) object detection, a critical rob…
Generative AI for Business Strategy: Using Foundation Models to Create Business Strategy Tools
Son The Nguyen, Theja Tulabandhula
Generative models (foundation models) such as LLMs (large language models) are having a large impact on multiple fields. In this work, we propose the use of such models for busines…
Lightweight, Uncertainty-Aware Conformalized Visual Odometry
Alex C. Stutts, Danilo Erricolo, Theja Tulabandhula +1
Data-driven visual odometry (VO) is a critical subroutine for autonomous edge robotics, and recent progress in the field has produced highly accurate point predictions in complex e…
Robust Monocular Localization of Drones by Adapting Domain Maps to Depth Prediction Inaccuracies
Priyesh Shukla, Sureshkumar S., Alex C. Stutts +3
We present a novel monocular localization framework by jointly training deep learning-based depth prediction and Bayesian filtering-based pose reasoning. The proposed cross-modal f…
Unified Embeddings of Structural and Functional Connectome via a Function-Constrained Structural Graph Variational Auto-Encoder
Carlo Amodeo, Igor Fortel, Olusola Ajilore +3
Graph theoretical analyses have become standard tools in modeling functional and anatomical connectivity in the brain. With the advent of connectomics, the primary graphs or networ…
Estimating the Personality of White-Box Language Models
Saketh Reddy Karra, Son The Nguyen, Theja Tulabandhula
Technology for open-ended language generation, a key application of artificial intelligence, has advanced to a great extent in recent years. Large-scale language models, which are…
ENOS: Energy-Aware Network Operator Search for Hybrid Digital and Compute-in-Memory DNN Accelerators
Shamma Nasrin, Ahish Shylendra, Yuti Kadakia +4
This work proposes a novel Energy-Aware Network Operator Search (ENOS) approach to address the energy-accuracy trade-offs of a deep neural network (DNN) accelerator. In recent year…
Choice-Aware User Engagement Modeling andOptimization on Social Media
Saketh Reddy Karra, Theja Tulabandhula
We address the problem of maximizing user engagement with content (in the form of like, reply, retweet, and retweet with comments)on the Twitter platform. We formulate the engageme…
Price Discrimination in the Presence of Customer Loyalty and Differing Firm Costs
Theja Tulabandhula, Aris Ouksel, Son Nguyen
We study how loyalty behavior of customers and differing costs to produce undifferentiated products by firms can influence market outcomes. In prior works that study such markets,…
Probabilistic Localization of Insect-Scale Drones on Floating-Gate Inverter Arrays
Priyesh Shukla, Ankith Muralidhar, Nick Iliev +3
We propose a novel compute-in-memory (CIM)-based ultra-low-power framework for probabilistic localization of insect-scale drones. The conventional probabilistic localization approa…
Off-Policy Optimization of Portfolio Allocation Policies under Constraints
Nymisha Bandi, Theja Tulabandhula
The dynamic portfolio optimization problem in finance frequently requires learning policies that adhere to various constraints, driven by investor preferences and risk. We motivate…