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
380 results for “keyword:"long context"” in ICLR 2027. 52 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]A model-agnostic scaling rule behind the critical inverse temperature in softmax self-attention▲2843.00
[PDF]CapSynth: Capability-Decomposed Synthesis for Long-Context Multi-Constraint Instruction Following▼5.8k2.33
[PDF]From Dilution to Alignment: Understanding and Mitigating Long-Context Safety Degradation▼4.3k2.00
[PDF]MusicSTAR: Structure-Aware Temporal Attention Routing for Song Generation from a Single Long Caption▼1361.33
[PDF]AB-Sparse: Sparse Attention with Adaptive Block Size for Accurate and Efficient Long-Context Inference▲6.1k2.00
[PDF]Never Evict Always Taper: A Static Logarithmic Bit-Width Schedule for KV Cache Quantization▲11.00
[PDF]GoLongRL: Capability-Oriented Long-Context Reinforcement Learning with Heterogeneous Multitask Alignment▼5.8k2.33
[PDF]Task-Oriented Memory Compilation: Executable State Representations for Long-Context Language Models▼5.8k2.33
Withdrawn or desk rejected (52)
[PDF]Certified Best-First Sparse Attention: Provable Early Termination via Admissible Block BoundsWithdrawn2.00
[PDF]From Frequency to Function: Component-Specific RoPE Extrapolation for Long-Context Language ModelsDesk rejected3.00
[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]Diagnosing and Advancing Long-Video Understanding for Distributed Evidence CompositionWithdrawn1.67