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
1,665 results for “keyword:"mor"” in ICLR 2027. 388 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Mem-Sonar: Self-Organizing and Self-Navigating Memory via Alternating Reinforcement Learning▼4.5k2.67
[PDF]PhysMRV: Physical Memory Retrieval and Verification for Physical Plausibility Reasoning▲9.2k2.67
[PDF]Expert-Level Analog-Digital Mapping of Mixture-of-Experts with Theoretical Generalization Guarantees▼4.5k2.25
[PDF]KoopCell: Koopman-Based Generative Model for Learning Single-Cell Dynamics from Distribution Snapshots▲2623.67
[PDF]Compression-Aware Fine-Tuning: Adapting Language Model Weights to a Frozen Cache Bottleneck▼4.3k2.00
[PDF]ACT-SNN: Activity-Constrained Two-Stage Conversion for Efficient Spiking Large Language Models▲3912.67
[PDF]From Preference to Action: A Benchmark for Continual Preference Memory in Multimodal Agents▼5.8k2.33
[PDF]From Experience to Lessons: Organizing Visual Memory for Chest X-Ray Report Generation▼4.5k2.67
[PDF]When to End, Which to Invoke Next: Transition-Aware Tokenized Procedural Memory for LLMs▲3.0k2.33
[PDF]Quantize the Keys, Audit the Values: Retained-State Certificates for KV-Cache Compression▲3912.67
[PDF]When More Experience Hurts: Diagnosing Experience Growth and Reader Alignment in Self-Evolving Language Agents▼5.8k2.33
[PDF]Towards Practical FHE-Federated LLMs Training: FHE-Compatible Compression Techniques and Versatile Advanced Aggregation▲13k2.00
[PDF]Retrospective Affective Belief Revision: When New Evidence Changes How LLM Agents Interpret Past Emotions▲11k2.00
[PDF]Coding Agent Memory Post-training: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via Reinforcement Learning▲5.4k3.00
[PDF]OBELISK: Co-designing Post-Packing Execution for Efficient Transformer Inference under Fully Homomorphic Encryption▼4.5k2.67
[PDF]Same Fit, Different Functions: Evidence Structure and Training Order Shape Held-Out Behavior▲11.00
[PDF]SegMem: Segment-wise Procedural Memory with Future-aware Gating for Long-Horizon Robotic Manipulation▼4.3k2.00
Withdrawn or desk rejected (388)
[PDF]MIRAGE: Memory Revision and Path-Aware Retrieval for Conflict Resolution in LLM Agent MemoryDesk rejected
[PDF]Caustic Spectroscopy: Identifiability and Acquisition Limits of Topological Event TimingWithdrawn2.00
[PDF]Preserving Decision-Relevant History: Response-Rank Memory for Write-Before-Query PredictionWithdrawn1.00