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 in ICLR 2027. 109 withdrawn or desk rejected listed apart.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]Select Twice, Freeze Once: Jacobian-Based KV Cache Selection for Multi-Turn and Long-Context LLM Serving▼1.2k1.67
[PDF]No Passage Is an Island: Orphaned KV Caches, Phantom Peaks, and Warm Encoding for Retrieval-Augmented Generation▲3952.67
[PDF]E3J: An Efficient and Open-Source Backend for Euclidean Equivariant Operations on GPU and TPU▼4.3k2.00
[PDF]DyQ-VLA: Dynamic Quantization and Compensation for VLA models with Runtime Error Awareness▼1.2k3.00
[PDF]HorizonKV: An Overlap-Aware Sparse Attention System for Long-Horizon Autoregressive Video Diffusion▼4.3k2.75
[PDF]AlgoSAGE: Formal Problem Representation and Grounded Expertise for Algorithmic Code Generation▲3952.67
[PDF]EvokeAgent: A Hardware-Aware, Knowledge-Base-Co-Driven Self-Evolving Agent System for GPU Kernel Optimization▼1361.33
[PDF]BitLadder: Bit-Level Selective Loading of the KV Cache for Efficient Long-Context LLM Inference▼4.3k2.00
[PDF]FedESO: Exploration-to-Stabilization Optimization for Model-Heterogeneous Federated Learning▼5.8k2.33
[PDF]From Evidence to Effect: Authority Semantics and Runtime Infrastructure for Stateful Agents▼1.2k1.67
[PDF]Kernel-Level Context Parallelism: Bridging Incompatible Shard Layouts in Hybrid Linear-Attention Transformers▲6.1k2.00
[PDF]LRSR: Hardware-Friendly Approximation of Per-Element Quantization via Low-Rank Scale Reconstruction▲3.9k1.67
[PDF]MoEAtlas: Orchestrating Communication in MoE Inference via Pre-Routing, Expert Placement, and Migration▼4.5k2.67
[PDF]HeteroQuant: Resolving Expert Heterogeneity in MoE Quantization via Targeted Calibration▼1.2k1.67
[PDF]RouteCache: Efficient Long-Context Attention via Learnable Retrieval and Temporal Caching▲3952.67
[PDF]Accelerating Mixture of Block Attention via Dynamic Routing, KV-Centric Execution and Runtime Pipelining▼5.8k2.33
Withdrawn or desk rejected (109)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