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
612 results for “keyword:"transfer"” in ICLR 2027. 172 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Language2Utility: Transferable Natural-Language Preference Grounding for Multi-Objective Reinforcement Learning▼4.3k2.00
[PDF]What Is a Conversation Made Of? A Reusable Semantic–Relational State Across Safety Tasks▲3.8k2.50
[PDF]FedSocratic: Exploring Knowledge Transfer through Socratic Questioning in Heterogeneous Federated LLMs▼1361.33
[PDF]Adaptive Manifold‑Driven Knowledge Transfer via Reinforcement Learning for Multi‑Objective Multi‑Task Optimization▼4.3k2.00
[PDF]Bridging KV-Cache Quantization and Linear Attention: From Theory to Pretrained Weight Migration▲3952.67
[PDF]LoopFM: Learning frOm HistOrical RePresentations of Foundation Model for Recommendation▼5.8k2.33
[PDF]K-Scaling: Critical Batch Size Governs Learning Rate Scheduling Across Token Budgets in LLM Pretraining▼5.9k2.50
[PDF]Beyond Objective Expressivity: Geometry Preservation in Multimodal Contrastive Learning▼4.3k2.00
[PDF]Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks▲15k3.50
[PDF]Channel-Remix: Data efficient Synthesis of Task-Specific Compact Models by Remixing Vision Foundation Model Channels▲3952.67
[PDF]UMA-DOS: Transfer Learning from Pretrained Atomistic Models for Density of States Prediction▼1.2k3.00
[PDF]BE-CORR: Learning to Correct Source-Library Outcomes for Endogenous Base-Editing Prediction▼5.8k2.33
[PDF]From Fooling CNNs to Fooling MLLMs: Generating Unrestricted Adversarial Examples via Diffusion-Based Style Injection▼5.8k2.33
[PDF]AneumoBench: A Source-Linked Benchmark for Synthetic-Geometry Transfer in Aneurysm CFD▲3.0k2.33
[PDF]Reference-Image-Guided Relation Editing via Token Bottlenecking and Semantic Shift Alignment▲3952.67
[PDF]When Is Reuse Superiority Licensed? Evidence Separation for Heterogeneous Offline Experience Reuse▼1.2k1.67
Withdrawn or desk rejected (172)
[PDF]Physical and Evolutionary Constraints on Machine Learning Priors: Reconciling No Free Lunch with Real-World GeneralizationWithdrawn
[PDF]Decoupling Temporal Action Ownership and Actor Geometry for Spatio-Temporal Action LocalizationWithdrawn1.33
[PDF]Neat Cross-Domain Representations via Frozen Embedding-Anchored Training of Language ModelsWithdrawn