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
311 results for “keyword:"context learning"” in ICLR 2027. 49 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]How Multi-Head Transformers Specialize for In-Context Learning: A Theoretical Analysis of Training Dynamics and Generalization▲2843.00
[PDF]Synthetic Control with Foundation Models: Nonlinear Gains and Context-Axis Sensitivity▼4.3k2.00
[PDF]Spatial representations that transfer by remapping emerge from meta-reinforcement learning▲9.2k2.67
[PDF]Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge▼4.5k2.67
[PDF]When Does Depth Matter For In-Context Learning? Adaptive Inference in Deep Transformers▼1.2k3.00
[PDF]Learning Heterogeneous Tabular Tasks through Multiregime Pretraining of Prior-Data Fitted Networks▼1351.33
[PDF]Rethinking Algorithmic Explanations of Transformer In-Context Learning: A Systematic Study of Noisy Linear Regression▼1351.33
[PDF]Where Membership Lives: Task Abstraction, Exemplar Retrieval, and Privacy Leakage in In-Context Learning▼4.3k2.00
[PDF]The Hidden Cost of Prompt Formatting: Measuring Representational Sensitivity in Language Models▼1351.33
[PDF]TabEvo: LLM-Guided Evolution of Dataset-Conditional Programs for Tabular In-Context Learning▼4.3k2.00
Withdrawn or desk rejected (49)
[PDF]VCRM: Empowering Efficient Memory for Vision-Language Models with Visual Context Record MemoryWithdrawn2.00
[PDF]FidelityFlow-PO: Bandit-Guided Allocation of Context Fidelity for Long-Context DPODesk rejected
[PDF]A Comparative Study of In-Context Linear Regression by Transformers with Chain-of-ThoughtWithdrawn1.67
[PDF]Diagnosing and Advancing Long-Video Understanding for Distributed Evidence CompositionWithdrawn1.67