NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
135 results for “keyword:"drift"” in ICLR 2027. 32 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Drift Forcing: Sample-Based Drift Fields as Initialization for Autoregressive Video Diffusion Distillation▼5.8k2.33
[PDF]Reachable Adaptation under Delayed Feedback: Budgeted Partial Updates in Nonstationary Streams▲3.0k2.33
[PDF]Specialist Drift: Continual RL for Capability-Preserving Foundation Model Post-Training▲6.1k2.00
[PDF]Give the Policy Its View Back: Recovering Frozen Visuomotor Policies from Camera Drift▲8.9k2.75
[PDF]Rating-Scale Drift in Automated Paper Reviewers after Domain-Specific Reinforcement Learning▼1.3k1.75
[PDF]Zero-Drift Expert Pool: Factorized Routing for Stable Pre-Trained-Model Continual Learning▲11.00
[PDF]Gradient as Behavior Fingerprint: Stable Sequential Model Editing via Gradient Drift Regularization▲14k3.00
[PDF]Router Drift Control: Mitigating Off-Policy Degradation in Mixture-of-Experts Reinforcement Learning▲6.1k2.00
[PDF]Maintaining the Right Abstraction: A Finite-Sample Theory of Adaptive Low-Rank Representations under Drift▼1.2k1.67
[PDF]Trace the Source: Behavioral Drift Discrimination via Profile Replay for Knowledge Tracing▼1.2k1.67
[PDF]Normal Fréchet Drift: Measuring Post-Training Departure from Pretrained Reference Manifold▲13k2.33
[PDF]Q-Guided Drifting Policy: Value-Guided Target Construction for One-Step Offline Reinforcement Learning▼4.3k2.00
[PDF]EvoCDS: Unifying Video Context-Dependent Concept Segmentation via Evolving Concept Discriminative Subspaces▲5103.00
[PDF]A Thresholded ReLU Unit with Fixed Output Weight Goes Dormant under Target Drift: Phase Diagram and Entry Time▲6.1k2.00
[PDF]The Correction Budget: When Test-Time Refinement Can and Cannot Fix World-Model Rollouts▼1611.50
Withdrawn or desk rejected (32)
[PDF]Machine Love: Emergent Bonding Behavior in Large Language Models and Its Implications for AI SafetyDesk rejected
[PDF]ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution ShapingWithdrawn1.67
[PDF]The Truncation Trap: Silent Failure of Fixed-Window Diffusion Likelihood and Information Estimators under Representation DriftWithdrawn1.00
[PDF]Complexity Guarantees for Heterogeneous Federated Bilevel Optimization with Lower-Level ConstraintsWithdrawn2.00
[PDF]Less Drift, Better Alignment: Selecting the Fittest Preference Data for Offline DPOWithdrawn2.00