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
112 results for “keyword:"replay"” in ICLR 2027. 27 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When Generative Replay Meets Evolving Deepfakes: Dual Confusion-Aware Regularization for Incremental Deepfake Detection▼4.3k2.00
[PDF]A DEAFENING SILENCE: CATASTROPHIC FORGETTING LIVES IN THE OUTPUT EMBEDDINGS OF TOKENS THE DATA NEVER SPEAKS▼4.5k2.67
[PDF]Minimal Repair Subtrajectories: Verifier-Certified Local Recovery for Long-Horizon Agents▼1.2k1.67
[PDF]Mitigating Catastrophic Forgetting in LLM Continual Learning through Attractor-Informed Latent Transition Alignment▲3952.67
[PDF]When Do Behavior Traces Validate MoE Interventions? Auditing Labels, Selection, and Decision Impact▼5.8k2.33
[PDF]Experience Is Not Knowledge: Where the Decision Knowledge in an Agent's Memory Comes From▼1361.33
[PDF]Fine-Tuning VLAs with Self-Demonstrated Generative Control for Multi-Task Manipulation▼1.2k3.00
[PDF]Guardrails Must Be Earned: Fabrication-Resistant Compilation of Failure Traces into Anti-Pattern Skills▲5103.00
[PDF]Loss of Plasticity and Its Recovery via Replay-Driven Compression in a Spiking Model of Hippocampal CA3▼4.3k2.00
[PDF]Beyond Uniform Forgetting in Alignment: Characterising, Predicting, and Recovering Retention in Sequential Preference Optimisation▼4.3k2.00
[PDF]Credit Without Ground Truth: Claim-Matched Evaluation of Step-Level Credit with Finite Executed Replay▼1361.33
[PDF]Neural Succession: A Mesoscopic Theory of Invasion, Coexistence, and Stabilization in Continual Learning▼1.2k1.67
[PDF]ASSERT: Synthesizing Replay-Verified Trajectories with Access Isolation for Software Engineering Agents▲5103.00
[PDF]PRESERVE WHAT MATTERS: COUNTERFACTUAL TASK-VECTOR DECOMPOSITION FOR REPLAY-FREE CONTINUAL VISION-LANGUAGE-ACTION LEARNING▲3952.67
[PDF]Anchor the Past, Calibrate the Present: Maintaining Geometric Consistency for Online Class-Incremental Learning▲3.0k2.33
[PDF]Distribution Matching Guided Replay Sample Selection for Online Class-Incremental Learning▲5.4k3.00
[PDF]WAVE: Optimal-Transport-based Domain-Incremental Learning and Generalization for Cross-Subject EEG Decoding▼1.2k1.67
[PDF]Dynamic Elite Replay: Learning Beyond Suboptimal Experts in Human-in-the-Loop Reinforcement Learning▼4.3k2.00
[PDF]What Do Attack-Success Rates Measure? A Matched-Sham Control for GUI-Agent Injection Benchmarks▼1361.33
[PDF]Historical Supervision Reactivation with Dynamic Heterogeneous Memory for Long-Horizon Class-Incremental Learning▼1361.33
[PDF]ARCH-CPTQ: Replay-Free Continual Post-Training Quantization with Curvature History and Anchoring▲3.8k2.50
Withdrawn or desk rejected (27)
[PDF]Generalizable Action Editor: Sharing Corrections across Tasks for Online Post-Training of Pretrained Robot PoliciesWithdrawn2.00
[PDF]Residual-Guided Adaptive Function-Space Projection for Replay-Free Continual LearningWithdrawn1.00