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 in ICLR 2027. 109 withdrawn or desk rejected listed apart.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]AVQ-Attention-2: Adaptive Vector-Quantized Attention with Exact Local Blocks and Linear-Cost Training▲9.2k2.67
[PDF]JointLoom: Compact-State GPU Simulation and Streaming Imitation Learning for Multi-Agent Pathfinding▼4.3k2.00
[PDF]RANA: Accelerating Multi-Turn Agentic Reinforcement Learning with Speculative Decoding▼4.3k2.00
[PDF]EvoKe: Progressive Hierarchical Evolution for Structural Exploration in Ascend C Kernel Synthesis▼1.2k1.67
[PDF]Coarse KV Residency: Decoupling KV Reachability from GPU Memory in Long-Context RL Rollouts▲3952.67
[PDF]TEMPO: Temporal Error-Modulated Precision Overlays for Recursive Transformer Quantization▲3.0k2.33
[PDF]Removing Redundant Computation in a BDH-GPU-Derived Language Model: Exact Recurrent Training and Conditional Neuron Selection▲11.00
[PDF]Beyond Berry–Esseen: Loss-Aware Distortion Transfer for Randomized Hadamard Quantization▼1.2k1.67
[PDF]ONE VOCABULARY PASS, MANY REQUESTS: A STREAM-ONCE OUTPUT-HEAD KERNEL FOR CONCURRENT LLM DECODING▼4.3k2.00
[PDF]Beyond Accuracy: Prefix-Invariant Realizations of Low-Precision Fast Matrix Multiplication▲8052.80
[PDF]Exact, Batch-Invariant and Fast Test-Time Query Optimization for Late-Interaction Retrieval▲5.4k3.00
[PDF]Does Energy-Aware Sparsity Allocation Help Dynamic Sparse Training? Leverage, Execution Back Ends, and Stable Regrowth▲5103.00
[PDF]What Sets a Block-Sparse Training Speedup? SM Count, the Dense Baseline and the Kernel, on Six GPUs▲13k2.33
[PDF]Collective Algebra Above a Closed Library: A Research-Loop Agent Finds the Rewrites a Search Misses▲5.7k2.00
[PDF]When to Wait Before Fan-Out: Warm-Up, Verification, and Residency in Cache-Aware LLM Evaluation▲9.2k2.67
[PDF]KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization▲5103.00
Withdrawn or desk rejected (109)
[PDF]CHARACTERIZING REPRODUCIBILITY: RUN-TO-RUN NUMERICAL VARIATION IN A NEAR PRODUCTION EXASCALE COMPUTERDesk rejected
[PDF]AlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM GenerationWithdrawn2.00