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
580 results for “area:"infrastructure, software libraries, hardware, systems, etc."” in ICLR 2027. 109 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Does Execution Require Target KV Fidelity? A Mixed-Fidelity KV Runtime for LLM Serving▼4.5k2.67
[PDF]RIVET: Ragged Inference with Variable-Granularity Execution for Token-Tree Verification in Speculative Decoding▼1.2k1.67
[PDF]DynamicKV: Predictive and Reversible KV-Cache Precision Allocation for Agentic LLM Inference▲2.0k4.00
[PDF]Stop Early, Spend Less: Equal-Accuracy Frame-Budget Saving via Agreement-Gated Adaptive Sampling in Video Language Models▲11.00
[PDF]LigerMoE: Efficient Expert Parallelism via Warp-Specialized Communication-Compute Fusion▼4.3k2.00
[PDF]Reciprocal Guidance: Orchestrating Draft and Verify Budgets for Advancing the Diffusion–AR Self-Speculation Frontier▼5.8k2.33
[PDF]Refreshing Less, Selecting Better: Cache-Efficient Diverse Influence Selection for LLM▼4.3k2.00
[PDF]FactorEP: Accelerating Expert-Parallel MoE Inference through End-to-End Factor-Space Execution▼5.8k2.33
[PDF]When the Second GPU Helps: Topology-Aware Mode Selection for Narrow-Interconnect LLM Serving▼1.3k1.75
[PDF]TraceAttention: Efficient Long-Context Attribution in Reasoning LLMs via Cache-Preserving Evaluation▲5103.00
[PDF]AdaptSpec: Input- and Step-Adaptive Tree-Based Speculative Decoding to Accelerate LLM Inference▼1.2k1.67
[PDF]KernelCompass: Traversing the Feasible Resource Space of the Target GPU Toward a Task-Contracted Objective▼4.3k2.00
[PDF]FluidMoE: An Asymmetric Scheduling Framework for Context-Parallel Mixture-of-Experts Training▲5.4k3.00
[PDF]Beyond Failed Trajectories: Diagnosing and Repairing LLM Agent Harnesses Across Three Observability Levels▼5.8k2.33
[PDF]One Static Schedule Does Not Fit All: Platform-Aware and Runtime-Adaptive Scheduling for Agentic RL Rollouts▲6.1k2.00
[PDF]When Space Flips a Bit: Recovering Transformer Inference from Radiation-Induced Faults▼4.3k2.00
Withdrawn or desk rejected (109)
[PDF]Guided Reasoning Across ISA Dialects: Inference-Time Control for GPU Assembly TranslationWithdrawn1.67
[PDF]The More The Merrier: Numerically Accurate Coded Computing for Machine Learning InferenceDesk rejected