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112 results for “keyword:"replay"” in ICLR 2027. 27 withdrawn or desk rejected listed apart.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]Replay the Seeds, Store the Remainder: Compressing Persistent Diffusion Inversion State▼4.3k2.00
[PDF]Replay on Demand: An Emergent Curriculum for Balancing Adaptation and Forgetting in Continued Pretraining▼5.8k2.33
[PDF]WorldModelLens: From Attention to Rollouts - A framework for World Model Interpretability▼4.3k2.00
[PDF]When Is Forgetting a Capacity Problem? Dissecting Catastrophic Forgetting under Controlled Capacity Pressure▼4.3k2.00
[PDF]Beyond Trust: Proof-Carrying Generation and Independent Release Assurance for Multi-Agent LLMs▼1.2k1.67
[PDF]Same Groups, Different Values: Decomposing Step-Level Credit Assignment for LLM Agents▲6.1k2.00
[PDF]The Fate of a Failed Training Run: Recovery Dynamics and Replay-Buffer Pathology in Soft Actor-Critic▲11.00
[PDF]Evolution Only When Needed: Triggered Evolutionary Data Injection for Off-Policy Reinforcement Learning▲3.0k2.33
[PDF]Present Action Is Not Persistent Write: Causal Rights of Optimizer History in Replay-Free Continual Learning▼71.25
[PDF]Rome Wasn’t Built in One Turn: Replay-Grounded Reward Signals for Long-Horizon Freeciv Agents▼4.3k2.00
[PDF]WHETHER VS. WHEN: SEPARATING SHORTCUT FORMATION FROM EVIDENCE-TIMING SENSITIVITY IN VALUE-BASED ONLINE REINFORCEMENT LEARNING▼1611.50
Withdrawn or desk rejected (27)
[PDF]Imagining Before Acting: Neuro-Inspired Counterfactual Critiques for Robot LearningDesk rejected
[PDF]RAM-CIL: Reliability-Aware Multimodal Class-Incremental Learning under Modality Reliability ShiftWithdrawn
[PDF]Continual Memory: Separating Selection and Representation in Continual Reinforcement LearningDesk rejected
[PDF]Emergent Tool Use in the Hide-and-Seek Environment via an Adaptive Auto-CurriculumWithdrawn1.33