4 citations · 9 across the 31 of their papers we have counts for
11 papers · 1 filter
Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets
Divake Kumar, Sina Tayebati, Devashri Naik +5
Computer-use agents turn vision-language model (VLM) predictions into executable GUI clicks, so reliable uncertainty estimates are essential for rejection, calibration, miss-severi…
VLM Judges Can Rank but Cannot Score: Task-Dependent Uncertainty in Multimodal Evaluation
Divake Kumar, Sina Tayebati, Devashri Naik +2
Vision-language models (VLMs) are increasingly used as automated judges for multimodal systems, yet their scores provide no indication of reliability. We study this problem through…
Cerebellar-Inspired Residual Control for Fault Recovery: From Inference-Time Adaptation to Structural Consolidation
Nethmi Jayasinghe, Diana Gontero, Spencer T. Brown +3
Robotic policies deployed in real-world environments often encounter post-training faults, where retraining, exploration, or system identification are impractical. We introduce an…
EigenTrack: Spectral Activation Feature Tracking for Hallucination and Out-of-Distribution Detection in LLMs and VLMs
Davide Ettori, Nastaran Darabi, Sina Tayebati +4
Large language models (LLMs) offer broad utility but remain prone to hallucination and out-of-distribution (OOD) errors. We propose EigenTrack, an interpretable real-time detector…
RMT-KD: Random Matrix Theoretic Causal Knowledge Distillation
Davide Ettori, Nastaran Darabi, Sureshkumar Senthilkumar +1
Large deep learning models such as BERT and ResNet achieve state-of-the-art performance but are costly to deploy at the edge due to their size and compute demands. We present RMT-K…
EigenShield: Causal Subspace Filtering via Random Matrix Theory for Adversarially Robust Vision-Language Models
Nastaran Darabi, Devashri Naik, Sina Tayebati +3
Vision-Language Models (VLMs) inherit adversarial vulnerabilities of Large Language Models (LLMs), which are further exacerbated by their multimodal nature. Existing defenses, incl…
Learning Conformal Abstention Policies for Adaptive Risk Management in Large Language and Vision-Language Models
Sina Tayebati, Divake Kumar, Nastaran Darabi +3
Large Language and Vision-Language Models (LLMs/VLMs) are increasingly used in safety-critical applications, yet their opaque decision-making complicates risk assessment and reliab…
SPARC: Subspace-Aware Prompt Adaptation for Robust Continual Learning in LLMs
Dinithi Jayasuriya, Sina Tayebati, Davide Ettori +2
We propose SPARC, a lightweight continual learning framework for large language models (LLMs) that enables efficient task adaptation through prompt tuning in a lower-dimensional sp…
Neural Precision Polarization: Simplifying Neural Network Inference with Dual-Level Precision
Dinithi Jayasuriya, Nastaran Darabi, Maeesha Binte Hashem +1
We introduce a precision polarization scheme for DNN inference that utilizes only very low and very high precision levels, assigning low precision to the majority of network weight…
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…
Containing Analog Data Deluge at Edge through Frequency-Domain Compression in Collaborative Compute-in-Memory Networks
Nastaran Darabi, Amit R. Trivedi
Edge computing is a promising solution for handling high-dimensional, multispectral analog data from sensors and IoT devices for applications such as autonomous drones. However, ed…