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
180 results for “keyword:"llm inference"” in ICLR 2027. 24 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]KV Cache Compression as State Substitution: When Does KV Compression Yield a Reliable Replacement for the Full Cache?▼4.3k2.00
[PDF]Pareto Frontier of LLM Test-Time Compute: Adaptive Rollouts and Voting Under Token Budgets▲3.0k2.33
[PDF]AWSLQ: Activation-Wise Sparse-Ladder Quantization for Accurate W4A4 Single-Load Decoding▼4.3k2.00
[PDF]Albus: Network-Aware Expert Localization and Dynamic Balancing with Unified Scheduling for MoE Serving▼4.5k2.67
[PDF]Weights or KV Cache? Where Activation Sparsity and KV-Cache Sparsity Cross in LLM Decoding▼1361.33
[PDF]DP-LAIR: Differentially Private LLM Inference with Adaptive Routing and Latent Perturbation▲3.0k2.50
[PDF]Cannot Wait to Verify: Parallel Drafting to Eliminate Verifier Idle Time in Speculative Decoding▼1361.33
[PDF]Every Cache Entry Earns Its Place: Global Allocation of Resolution and Coverage for KV Cache Compression▲4.6k3.00
[PDF]AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines▼4.5k2.67
[PDF]The Compression Square: Weight Quantization and KV-Cache Eviction Do Not Compose at the Operating Point▲143.33
[PDF]ASIR: An Agent-Structure-Aware Indexer with Block-Local Reuse for Native Sparse Attention▼4.3k2.00
[PDF]CSAttention: Centroid-Scoring Sparse Attention for Reusable-Prefix Long-Context LLM Serving▲3952.67
[PDF]When Secrets Reveal Themselves: Vulnerabilities of Covariant Transformations in Private LLM Inference and a Low-rank Remedy▼1.2k3.00
[PDF]EXACT WARM-STATE REUSE FOR HYBRID DIFFUSION LANGUAGE MODELS: CONTRACTS, SPEEDUPS, AND FAILURE BOUNDARIES▲3.0k2.33
[PDF]Duplex: Actively Secure, Dealer-Free Two-Party Function Secret Sharing for Private LLM Inference▼5.8k2.33
[PDF]BranchWeave: Local Wavefronts with Device-Wide Batching for Verifier-Guided Test-Time Scaling▲5.4k3.20
[PDF]Draft in Parallel, Condition Through Depth: Adjacent Causal Injection for Speculative Decoding▲143.33
Withdrawn or desk rejected (24)
[PDF]DyS-MoE: Virtualizing Dynamic Expert Execution with Static Windows for Resource-Constrained MoE InferenceWithdrawn2.00
[PDF]SpecRelay: Amortize or Avoid the Round Trip in Edge–Cloud Speculative DecodingDesk rejected2.00
[PDF]Easy-Kuant: Diagnosing and Mitigating KV-Cache Quantization Collapse with Selective Layer ProtectionDesk rejected