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
81 results for “keyword:"efficient llm inference"” in ICLR 2027. 10 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]HeteroLoRA-MoE: Heterogeneous Low-Rank Experts with Diverse Projection Patterns and Efficient GPU Kernels▼4.3k2.00
[PDF]Compression-Aware Fine-Tuning: Adapting Language Model Weights to a Frozen Cache Bottleneck▼4.3k2.00
[PDF]SpecSplice: Dynamic Composition of Parametric and Retrieval-based Drafts for Agentic Speculative Decoding▼1.2k3.00
[PDF]QSpar: Co-Designing Sparse Attention and Quantized Weights for Long-Context Self-Speculative Decoding▲5103.00
[PDF]TraceAttention: Efficient Long-Context Attribution in Reasoning LLMs via Cache-Preserving Evaluation▲5103.00
Withdrawn or desk rejected (10)
[PDF]DyS-MoE: Virtualizing Dynamic Expert Execution with Static Windows for Resource-Constrained MoE InferenceWithdrawn2.00
[PDF]Easy-Kuant: Diagnosing and Mitigating KV-Cache Quantization Collapse with Selective Layer ProtectionDesk rejected
[PDF]ForeCache: Efficient LLM-Based Multi-Agent Systems with Intent-Conditioned Pruning and Amortized KV ReuseWithdrawn2.00