EigenTrack: Spectral Activation Feature Tracking for Hallucination and Out-of-Distribution Detection in LLMs and VLMs
Fuente:
arXiv
Saved in:
| Main Authors: | Ettori, Davide, Darabi, Nastaran, Tayebati, Sina, Krishnan, Ranganath, Subedar, Mahesh, Tickoo, Omesh, Trivedi, Amit Ranjan |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
TRACER: Trajectory Risk Aggregation for Critical Episodes in Agentic Reasoning
by: Tayebati, Sina, et al.
Published: (2026)
by: Tayebati, Sina, et al.
Published: (2026)
EigenShield: Causal Subspace Filtering via Random Matrix Theory for Adversarially Robust Vision-Language Models
by: Darabi, Nastaran, et al.
Published: (2025)
by: Darabi, Nastaran, et al.
Published: (2025)
SPARC: Subspace-Aware Prompt Adaptation for Robust Continual Learning in LLMs
by: Jayasuriya, Dinithi, et al.
Published: (2025)
by: Jayasuriya, Dinithi, et al.
Published: (2025)
Learning Conformal Abstention Policies for Adaptive Risk Management in Large Language and Vision-Language Models
by: Tayebati, Sina, et al.
Published: (2025)
by: Tayebati, Sina, et al.
Published: (2025)
PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI
by: Narayanan, Athma, et al.
Published: (2025)
by: Narayanan, Athma, et al.
Published: (2025)
INTACT: Inducing Noise Tolerance through Adversarial Curriculum Training for LiDAR-based Safety-Critical Perception and Autonomy
by: Darabi, Nastaran, et al.
Published: (2025)
by: Darabi, Nastaran, et al.
Published: (2025)
Beyond Confidence: Adaptive Abstention in Dual-Threshold Conformal Prediction for Autonomous System Perception
by: Kumar, Divake, et al.
Published: (2025)
by: Kumar, Divake, et al.
Published: (2025)
Synthetic Data Generation for Long-Tail Medical Image Classification: A Case Study in Skin Lesions
by: Jiang, Jiaxiang, et al.
Published: (2026)
by: Jiang, Jiaxiang, et al.
Published: (2026)
RMT-KD: Random Matrix Theoretic Causal Knowledge Distillation
by: Ettori, Davide, et al.
Published: (2025)
by: Ettori, Davide, et al.
Published: (2025)
Enhancing Trust in Large Language Models via Uncertainty-Calibrated Fine-Tuning
by: Krishnan, Ranganath, et al.
Published: (2024)
by: Krishnan, Ranganath, et al.
Published: (2024)
Learnable Conformal Prediction with Context-Aware Nonconformity Functions for Robotic Planning and Perception
by: Kumar, Divake, et al.
Published: (2025)
by: Kumar, Divake, et al.
Published: (2025)
VLM Judges Can Rank but Cannot Score: Task-Dependent Uncertainty in Multimodal Evaluation
by: Kumar, Divake, et al.
Published: (2026)
by: Kumar, Divake, et al.
Published: (2026)
ProGAL-VLA: Grounded Alignment through Prospective Reasoning in Vision-Language-Action Models
by: Darabi, Nastaran, et al.
Published: (2026)
by: Darabi, Nastaran, et al.
Published: (2026)
Belief Dynamics for Detecting Behavioral Shifts in Safe Collaborative Manipulation
by: Naik, Devashri, et al.
Published: (2026)
by: Naik, Devashri, et al.
Published: (2026)
Parameter-Efficient Active Learning for Foundational models
by: Narayanan, Athmanarayanan Lakshmi, et al.
Published: (2024)
by: Narayanan, Athmanarayanan Lakshmi, et al.
Published: (2024)
Neural Precision Polarization: Simplifying Neural Network Inference with Dual-Level Precision
by: Jayasuriya, Dinithi, et al.
Published: (2024)
by: Jayasuriya, Dinithi, et al.
Published: (2024)
Sense Less, Generate More: Pre-training LiDAR Perception with Masked Autoencoders for Ultra-Efficient 3D Sensing
by: Tayebati, Sina, et al.
Published: (2024)
by: Tayebati, Sina, et al.
Published: (2024)
Calibrated Decomposition of Aleatoric and Epistemic Uncertainty in Deep Features for Inference-Time Adaptation
by: Kumar, Divake, et al.
Published: (2025)
by: Kumar, Divake, et al.
Published: (2025)
Enhancing 3D Robotic Vision Robustness by Minimizing Adversarial Mutual Information through a Curriculum Training Approach
by: Darabi, Nastaran, et al.
Published: (2024)
by: Darabi, Nastaran, et al.
Published: (2024)
Spectral Geometry for Deep Learning: Compression and Hallucination Detection via Random Matrix Theory
by: Ettori, Davide
Published: (2026)
by: Ettori, Davide
Published: (2026)
Causal-Guided Dimension Reduction for Efficient Pareto Optimization
by: Jayasuriya, Dinithi, et al.
Published: (2025)
by: Jayasuriya, Dinithi, et al.
Published: (2025)
Intelligent Sensing-to-Action for Robust Autonomy at the Edge: Opportunities and Challenges
by: Trivedi, Amit Ranjan, et al.
Published: (2025)
by: Trivedi, Amit Ranjan, et al.
Published: (2025)
Navigating the Unknown: Uncertainty-Aware Compute-in-Memory Autonomy of Edge Robotics
by: Darabi, Nastaran, et al.
Published: (2024)
by: Darabi, Nastaran, et al.
Published: (2024)
Structure and Redundancy in Large Language Models: A Spectral Study via Random Matrix Theory
by: Ettori, Davide
Published: (2026)
by: Ettori, Davide
Published: (2026)
TRIAGE: Type-Routed Interventions via Aleatoric-Epistemic Gated Estimation in Robotic Manipulation and Adaptive Perception -- Don't Treat All Uncertainty the Same
by: Kumar, Divake, et al.
Published: (2026)
by: Kumar, Divake, et al.
Published: (2026)
Uncertainty-Guided Inference-Time Depth Adaptation for Transformer-Based Visual Tracking
by: Poggi, Patrick, et al.
Published: (2026)
by: Poggi, Patrick, et al.
Published: (2026)
Windsock is Dancing: Adaptive Multimodal Retrieval-Augmented Generation
by: Zhao, Shu, et al.
Published: (2025)
by: Zhao, Shu, et al.
Published: (2025)
CONCLAD: COntinuous Novel CLAss Detector
by: Rios, Amanda, et al.
Published: (2024)
by: Rios, Amanda, et al.
Published: (2024)
Model of contracting with the indirect treatment paraclinical units of the social security organization
by: Sina Salehi Darabi
Published: (2025)
by: Sina Salehi Darabi
Published: (2025)
Parts-Mamba: Augmenting Joint Context with Part-Level Scanning for Occluded Human Skeleton
by: Shen, Tianyi, et al.
Published: (2025)
by: Shen, Tianyi, et al.
Published: (2025)
CUAL: Continual Uncertainty-aware Active Learner
by: Rios, Amanda, et al.
Published: (2024)
by: Rios, Amanda, et al.
Published: (2024)
A Dual Neural Network Approach with PID Control and Reference Tracking to Enhance Oil Recovery
by: Keyvan Ahangar Darabi, et al.
Published: (2025)
by: Keyvan Ahangar Darabi, et al.
Published: (2025)
Uncertainty Quantification in Continual Open-World Learning
by: Rios, Amanda S., et al.
Published: (2024)
by: Rios, Amanda S., et al.
Published: (2024)
Scalable APT Malware Classification via Parallel Feature Extraction and GPU-Accelerated Learning
by: Subedar, Noah, et al.
Published: (2025)
by: Subedar, Noah, et al.
Published: (2025)
Track Any Peppers: Weakly Supervised Sweet Pepper Tracking Using VLMs
by: Lim, Jia Syuen, et al.
Published: (2024)
by: Lim, Jia Syuen, et al.
Published: (2024)
Hallucination Detection in LLMs Using Spectral Features of Attention Maps
by: Binkowski, Jakub, et al.
Published: (2025)
by: Binkowski, Jakub, et al.
Published: (2025)
ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs
by: Zhang, Zhenliang, et al.
Published: (2025)
by: Zhang, Zhenliang, et al.
Published: (2025)
DOSA: Differentiable Model-Based One-Loop Search for DNN Accelerators
by: Hong, Charles, et al.
Published: (2025)
by: Hong, Charles, et al.
Published: (2025)
VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following
by: Hong, Hyesoo, et al.
Published: (2026)
by: Hong, Hyesoo, et al.
Published: (2026)
Data-Driven Feature Tracking for Event Cameras With and Without Frames
by: Messikommer, Nico, et al.
Published: (2022)
by: Messikommer, Nico, et al.
Published: (2022)
Similar Items
-
TRACER: Trajectory Risk Aggregation for Critical Episodes in Agentic Reasoning
by: Tayebati, Sina, et al.
Published: (2026) -
EigenShield: Causal Subspace Filtering via Random Matrix Theory for Adversarially Robust Vision-Language Models
by: Darabi, Nastaran, et al.
Published: (2025) -
SPARC: Subspace-Aware Prompt Adaptation for Robust Continual Learning in LLMs
by: Jayasuriya, Dinithi, et al.
Published: (2025) -
Learning Conformal Abstention Policies for Adaptive Risk Management in Large Language and Vision-Language Models
by: Tayebati, Sina, et al.
Published: (2025) -
PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI
by: Narayanan, Athma, et al.
Published: (2025)