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
1,262 results for “keyword:"context"” in ICLR 2027. 204 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]RouteCache: Efficient Long-Context Attention via Learnable Retrieval and Temporal Caching▲3952.67
[PDF]KV Cache Compression as State Substitution: When Does KV Compression Yield a Reliable Replacement for the Full Cache?▼4.3k2.00
[PDF]Accelerating Mixture of Block Attention via Dynamic Routing, KV-Centric Execution and Runtime Pipelining▼5.8k2.33
[PDF]Interpreting Multi-layer Transformers for In-context Linear Regression with Varying Covariance▲1.7k3.33
[PDF]The Ruler Agrees With Itself, Not With the Task: Auditing Held-Out Loss as an Instrument for Context Selection▲6.3k2.25
[PDF]Understanding and Accelerating Long-Context Extrapolation in Hybrid Models via State-Equilibration Curriculum▼2443.33
[PDF]SeriesPFN: Unifying Time-Series Classification and Extrinsic Regression through End-to-End In-Context Learning▼4.3k2.00
[PDF]Beyond State Capacity: Diagnosing and Improving Multi-Slot Linear Attention through Selectivity▼5.8k2.33
[PDF]When Contextual Skills Can Be Weighted: The Compilability and Reachability of In-Context to In-Weight Learning for LLM Agents▲5103.00
[PDF]LongHarness: Advancing Agentic Reasoning over 100M-Token Corpora via Stateful Evidence Management▲2623.67
[PDF]LatentGym: A Testbed for Cross-task Experiential Learning with Contollable Latent Structure▼1.2k3.00
[PDF]After Error Feedback: Continued Access to Failed Reasoning Contributes to Contextual Drag▲6.1k2.00
[PDF]Beyond Uncertainty: Turning Model Failures into Reusable Logic Templates for Adaptive Reasoning▲6.1k2.00
[PDF]Learning from Ugly Ducklings: Hierarchical Modeling of Intra-Patient Variance for Melanoma Prediction▼4.3k2.00
[PDF]CV-OPSD: Self-Evolving Long-Context Reasoners via Zero-Annotation Clean-View On-Policy Self-Distillation▲14k3.00
[PDF]The Answer Format Is Part of the Measurement: Option Labels Change Visual Context Effects in VLMs▲6.1k2.00
[PDF]Capability–Loss Dissociation in Language Models: A Theory and Empirical Study of Loss Signatures▼11k1.75
Withdrawn or desk rejected (204)
[PDF]Beyond Tokens: Read and Predict N-gram Spans with a Shared Dictionary for Genomic Foundation ModelsWithdrawn
[PDF]Machine Love: Emergent Bonding Behavior in Large Language Models and Its Implications for AI SafetyDesk rejected
[PDF]Implicit Strategic Optimization: Prediction-Aware Long-Horizon Learning for LLM AgentsDesk rejected1.67