activity
20242026
collaborators
Showing 2025Show all

7 papers · 1 filter

cs.CV2025

Calibrated Decomposition of Aleatoric and Epistemic Uncertainty in Deep Features for Inference-Time Adaptation

Divake Kumar, Patrick Poggi, Sina Tayebati +3

Most estimators collapse all uncertainty modes into a single confidence score, preventing reliable reasoning about when to allocate more compute or adjust inference. We introduce U…

cs.NE2025

Causal-Guided Dimension Reduction for Efficient Pareto Optimization

Dinithi Jayasuriya, Divake Kumar, Sureshkumar Senthilkumar +3

Multi-objective optimization of analog circuits is hindered by high-dimensional parameter spaces, strong feedback couplings, and expensive transistor-level simulations. Evolutionar…

cs.RO2025

Learnable Conformal Prediction with Context-Aware Nonconformity Functions for Robotic Planning and Perception

Divake Kumar, Sina Tayebati, Francesco Migliarba +2

Deep learning models in robotics often output point estimates with poorly calibrated confidences, offering no native mechanism to quantify predictive reliability under novel, noisy…

cs.RO2025

Beyond Confidence: Adaptive Abstention in Dual-Threshold Conformal Prediction for Autonomous System Perception

Divake Kumar, Nastaran Darabi, Sina Tayebati +1

Safety-critical perception systems require both reliable uncertainty quantification and principled abstention mechanisms to maintain safety under diverse operational conditions. We…

cs.LG2025

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…

cs.RO2025

Intelligent Sensing-to-Action for Robust Autonomy at the Edge: Opportunities and Challenges

Amit Ranjan Trivedi, Sina Tayebati, Hemant Kumawat +9

Autonomous edge computing in robotics, smart cities, and autonomous vehicles relies on the seamless integration of sensing, processing, and actuation for real-time decision-making…