{"total":40,"rows":[{"id":"2604.07823","title":"LPM 1.0: Video-based Character Performance Model","created":"2026-04-09","cited_by_count":11,"area":null},{"id":"2603.14360","title":"M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling","created":"2026-03-15","cited_by_count":8,"area":null},{"id":"2607.04422","title":"Full-Stack FP4: Stable LLM Pretraining with Quantized Projections, Optimizers, and Attention","created":"2026-07-05","cited_by_count":8,"area":null},{"id":"2608.12629","title":"CAKE: Compiler-Agent Co-Design for Frontier Kernel Evolution","created":"2026-08-12","cited_by_count":5,"area":null},{"id":"2605.23081","title":"ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention","created":"2026-05-21","cited_by_count":4,"area":null},{"id":"2604.12798","title":"VFA: Relieving Vector Operations in Flash Attention with Global Maximum Pre-computation","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2606.22932","title":"FORGE: Fused On-Register Gradient Elimination for Memory-Efficient LLM Training","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2609.04105","title":"Hardware-Aware FP4 FlashAttention-4","created":"2026-09-03","cited_by_count":2,"area":null},{"id":"2603.06738","title":"Rank-Factorized Implicit Neural Bias: Scaling Super-Resolution Transformer with FlashAttention","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2604.14825","title":"Nautilus: An Auto-Scheduling Tensor Compiler for Efficient Tiled GPU Kernels","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2605.08467","title":"CUDAHercules: Benchmarking Hardware-Aware Expert-level CUDA Optimization for LLMs","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.10414","title":"Remember to Forget: Gated Adaptive Positional Encoding","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2607.04302","title":"HiFA4: Training-Free 4-bit FlashAttention on Ascend HIF4 NPUs for LLM Inference","created":"2026-07-05","cited_by_count":1,"area":null},{"id":"2607.25291","title":"CoSA: Accelerating Long-Context Inference via Proxy-Kernel Co-Designed Sparse Attention","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2607.28418","title":"WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2609.03807","title":"Almost Free State Prediction Separation","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2604.07242","title":"Weaves, Wires, and Morphisms: Formalizing and Implementing the Algebra of Deep Learning","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.09512","title":"Integrated electro-optic attention nonlinearities for transformers","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.15617","title":"A Few GPUs, A Whole Lotta Scale: Faithful LLM Training Emulation with PrismLLM","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2607.19378","title":"Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.23264","title":"X-Stage: Modeling Post-Issue Backpressure in GPU Communication--Computation Fusion","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2607.27744","title":"ROCS: Request-Oriented Compute Sharing for Efficient Large-Scale Recommendation","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.13517","title":"DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.21607","title":"Subzero matrix completion for sparse data analysis: large-scale learning of latent low-rank structure","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.24664","title":"Maia 200: A Software Defined Dataflow System for Large-scale AI Acceleration","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.26418","title":"Redwood: A Frontier AI Accelerator Designed, Verified, and Deployed from Scratch in 2 Weeks by AI","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.26965","title":"ClusterAttention: A training-free speedup of bidirectional attention","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.13031","title":"Attention Quantization for Tabular Foundation Models","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.24089","title":"FlashBoB: I/O-Efficient Exact Backward-over-Backward for Softmax Attention","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.31306","title":"Benchmarking Attention for Tabular Foundation Models","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33586","title":"Approximating Softmax in Pretrained LLMs: Model Sensitivity and Kernel Acceleration","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.37809","title":"Pixel-Level Transformers in Remote Sensing: A Canopy Height Case Study","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38198","title":"FlashDiffusion: Fused Tiled Kernel Spectral Decomposition","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.39034","title":"Switching Linear Attention","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39111","title":"Bongard: Training Machine Intuition","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39361","title":"LampAttention: Look-Ahead Mixed-Precision FlashAttention for Dedicated Accelerators","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00049","title":"Fast Polynomial Transcendentals for LLMs","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2610.05854","title":"TurboPairFormer: Fast and Stable Protein Folding Model Training with an Optimized Triangle Attention Kernel","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.12545","title":"AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of Edits","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.17184","title":"DuoDiscover: Scaling Autonomous Discovery Beyond the Evaluation Bottleneck","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}