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
113 results for “keyword:"gpu"” in ICLR 2027. 22 withdrawn or desk rejected listed apart.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]Coarse KV Residency: Decoupling KV Reachability from GPU Memory in Long-Context RL Rollouts▲4002.67
[PDF]What Sets a Block-Sparse Training Speedup? SM Count, the Dense Baseline and the Kernel, on Six GPUs▲13k2.33
[PDF]Conditional Deontics Over Terminals: A Cross-subtree Reference Mechanism for Efficient yet Expressive Constrained Decoding▼1.2k1.67
[PDF]Convex-SKM-Net: Low-Latency Block Halfspace Corrections for Neural Convex Constraint Satisfaction▼4.3k2.00
[PDF]JaxNaviSim: A GPU-Accelerated, Data-Driven Simulator and Learning Benchmark for Maritime Navigation▼3.7k2.25
[PDF]How to Train Your Little Dragon: Teaching a Small Language Model to Construct and Refine GPU Optimization Scripts▼5.8k2.33
[PDF]Scaling Graph Topology Augmentation with Structured Variations and Spectral Trust in Non-stationary Reinforcement Learning▼1.2k1.67
[PDF]HEPH: 3-Bit Grid-Aligned Trellis Quantization of MXFP4 Mixture-of-Experts for Accurate, Hadamard-Free Serving▲20k2.67
[PDF]TurboPairFormer: Fast and Stable Protein Folding Model Training with an Optimized Triangle Attention Kernel▼1.2k3.00
[PDF]E3J: An Efficient and Open-Source Backend for Euclidean Equivariant Operations on GPU and TPU▼4.3k2.00
[PDF]HorizonKV: An Overlap-Aware Sparse Attention System for Long-Horizon Autoregressive Video Diffusion▼4.3k2.75
[PDF]EvokeAgent: A Hardware-Aware, Knowledge-Base-Co-Driven Self-Evolving Agent System for GPU Kernel Optimization▼1351.33
[PDF]Accelerating Mixture of Block Attention via Dynamic Routing, KV-Centric Execution and Runtime Pipelining▼5.8k2.33
[PDF]SparkDiffusion: A Unified Sparse Warm-Up and Few-Step Distillation Framework for Mitigating the High-Sparsity Trap▼5.8k2.33
[PDF]AWSLQ: Activation-Wise Sparse-Ladder Quantization for Accurate W4A4 Single-Load Decoding▼4.3k2.00
Withdrawn or desk rejected (22)
[PDF]FusionAgent: Joint Search over Fusion Boundaries and Kernel Implementations for Whole-Model InferenceWithdrawn
[PDF]Fuse-PINN: Combining Finite Element Methods and Physics-Informed Neural Networks to enable massively parallel simulations of non-linear PDEsWithdrawn1.67
[PDF]Fast and Precise Learned Charged-Particle Trajectory Regression at the Large Hadron ColliderWithdrawn1.33
[PDF]Prior Knowledge or Search? A Study of LLM Agents in Hardware-Aware Code OptimizationWithdrawn1.33