ICLR 2026PastOther
Catch, Adapt, and Operate: Monitoring ML Models Under Drift Workshop
CAO
- Submission deadline
- Feb 11, 2026, 13:01 UTCOpenReview-synced 2026-02-11 13:01 UTC (as of 2026-06-23) — extensions on OpenReview are applied automatically; verify on the website.
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (74)
Fetched from OpenReview (v2) on 2026-06-10.
A Credal-Set Perspective on Task-Induced Distributional Drift in Text Generation
A Geometry-Based View of Mahalanobis OOD Detection
Adaptive Quasimetric Mapping : Principled Topological Abstraction for Robust Offline Goal-Conditioned Navigation
Approximating Function Space Distance for Continual Learning in Transformers
Beyond Accuracy: Evaluating Visual Grounding in Multimodal Medical Reasoning
CAdam: Confidence-Based Optimization for Online Learning
Can Linear Probes Effectively Measure LLM Uncertainty ?
CAO-LLM: Catching, Adapting and Operating Under Distribution Drift for Large Language Models
Capacity and Redundancy Trade-offs in Multi-Task Learning
CATS: Conformalized Adaptive Test-Time Scaling
Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples
CROSS-LINGUAL FAIRNESS DRIFT IN LLM MORAL REASONING
Detecting Distributional Drift in Transformers Through Representation Dynamics
DISCO: Diversifying Sample Condensation for Efficient Model Evaluation
Drift ≠ Error: Reliability Analysis of Agricultural Foundation Models Under Distribution Shift
Drift-Aware Uncertainty Quantification via a Functional Spectral-Newton Method
Drift-to-Action Controllers: Budgeted Interventions with Online Risk Certificates
Duration Aware Scheduling for ASR Serving Under Workload Drift
Efficient Dataset Selection for Continual Adaptation of Generative Recommenders
Emergent Misalignment: Tracking the Emergence and Evolution of Misaligned traits throughout Model Training
Evaluating Domain-Shift Generalization of Liquid Neural Networks in Autonomous Driving
Evaluating Performance Drift from Model Switching in Multi-Turn LLM Systems
Evi-BALD: Bayesian Active Learning by Disagreement via Evidential Deep Learning
Explainability of predictive uncertainty models under drift in the telecom domain
FedAgree: Leveraging Federated Checkpoints for Label-Free OOD Evaluation via Agreement
Hidden-Layer Self-Distillation Yields Drift-Resilient Visual Representations
Hindsight-Anchored Policy Optimization: Turning Failure into Feedback in Sparse Reward Settings
Hyperspherical Filtering for Online Classification under Drift
In-Context Adaptation
Layer by layer, module by module: Choose both for optimal OOD probing of ViT
Lifting the Veil of Non-Stationarity in Financial Market
Localized Dynamics-Aware Domain Adaption for Off-Dynamics Offline Reinforcement Learning
Locally Adaptive Multi-Objective Learning
LogitScope: A Framework for Analyzing LLM Uncertainty Through Information Metrics
LookSharp: Attention Entropy Minimization for Test-Time Adaptation
Loss Smoothing for Continual Adaptation
Manifold-Aware Temporal Domain Generalization for Large Language Models
Measuring Control Intervention Awareness Across Frontier LLMs
Network System Forecasting Despite Topology Shift
Noise-Response Calibration: A Causal Intervention Protocol for LLM-Judges
Not All Clients Are Equal: Collaborative Model Personalization on Heterogeneous Multi-Modal Clients
Not All Queries Need Rewriting: When Prompt-Only LLM Refinement Helps and Hurts Dense Retrieval
Noticing the Watcher: LLM Agents Can Infer CoT Monitoring from Blocking Feedback
OASIS: Online Sample Selection for Continual Instruction Tuning
On the Identifiability of Steering Vectors in Large Language Models
Online Fine-Tuning of Pretrained Controllers for Autonomous Driving via Real-Time Recurrent RL
Out-of-Support Generalisation via Weight-Space Sequence Modelling
Paranoid Monitors: How Long Context Breaks LLM Agent Supervision
PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective
Pitfalls of Unlabeled Disagreement-Based Drift Detection in Streaming Tree Ensembles
Prior Distribution and Model Confidence
Prompt-Level Drift as an Operational Monitoring Problem: Schema Failure Cliffs and Judge-Version Risk in Artifact-Grounded Evaluation
Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling
QueST: Persistent Queries as Semantic Monitors for Drift Suppression in Long-Horizon Tracking
RDUMB++: DRIFT-AWARE CONTINUAL TEST-TIME ADAPTATION
Reasoning Is Not Free: Robust Adaptive Cost-Efficient Router for LLM-as-a-Judge
Reliability-Aware Environment Discovery: Leveraging Feature Entanglement for Subpopulation Robustness
Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity
Right Regions, Wrong Labels: Semantic Label Flips in Segmentation under Correlation Shift
Risk-Averse Learning with Nonstationary Distribution
Robust LLM Performance Certification via Constrained Maximum Likelihood Estimation
Structured Event Logging for Tracking Model Behavior Under Distributional Drift
SymTorch: A Framework for Symbolic Distillation of Deep Neural Networks
TamperBench: A Systematic Framework to Stress-Test LLM Safety Under Fine-Tuning and Tampering
TamperTest: A Framework for Testing Tamper Resistance in Open-Weight LLMs
Test-Time Adaptation for Event Prediction via Lightweight Adapters
The Magic Correlations: Understanding Knowledge Transfer from Pretraining to Supervised Fine-Tuning
TRUST: Trajectory-guided State-Space Temporal Test-Time Adaptation
Understanding Reasoning Collapse in Multi-Turn Agent Reinforcement Learning
Value Drifts: Tracing Value Alignment During LLM Post-Training
Weighted Partial Optimal Transport for Multi-Source Partial Domain Adaptation
WHEN DRIFT DETECTORS CRY WOLF: FALSE ALARM RATES IN CONTINUOUS ML MONITORING
When Sensors Fail: Temporal Sequence Models for Robust PPO under Sensor Drift
White-Box Monitoring for Personality Mirroring in Conversational AI