{"total":66,"rows":[{"id":"2603.24517","title":"AVO: Agentic Variation Operators for Autonomous Evolutionary Search","created":"2026-03-25","cited_by_count":24,"area":"agents"},{"id":"2605.22344","title":"Bernini: Latent Semantic Planning for Video Diffusion","created":"2026-05-21","cited_by_count":12,"area":"lr"},{"id":"2604.07823","title":"LPM 1.0: Video-based Character Performance Model","created":"2026-04-09","cited_by_count":11,"area":null},{"id":"2604.27472","title":"PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations","created":"2026-04-30","cited_by_count":9,"area":"vla"},{"id":"2605.17757","title":"OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization","created":"2026-05-18","cited_by_count":9,"area":"inference"},{"id":"2607.24027","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","created":"2026-07-27","cited_by_count":9,"area":"diffusion"},{"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":"2605.12825","title":"Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion","created":"2026-05-12","cited_by_count":4,"area":"diffusion"},{"id":"2605.23081","title":"ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention","created":"2026-05-21","cited_by_count":4,"area":null},{"id":"2605.17170","title":"TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks","created":"2026-05-16","cited_by_count":3,"area":"agents"},{"id":"2607.19064","title":"Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing","created":"2026-07-21","cited_by_count":3,"area":"diffusion"},{"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":"2608.19758","title":"FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving","created":"2026-08-20","cited_by_count":2,"area":"inference"},{"id":"2609.04105","title":"Hardware-Aware FP4 FlashAttention-4","created":"2026-09-03","cited_by_count":2,"area":null},{"id":"2609.15810","title":"VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention","created":"2026-09-14","cited_by_count":2,"area":"diffusion"},{"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":"2604.15464","title":"Ragged Paged Attention: A High-Performance and Flexible LLM Inference Kernel for TPU","created":"2026-04-16","cited_by_count":1,"area":"inference"},{"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":"2606.06453","title":"Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents","created":"2026-06-04","cited_by_count":1,"area":"agents"},{"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":"2608.02947","title":"ATFlash: Per-RoPE-Wavelength Attention Windows for Compute/Memory-Efficient LLM Inference","created":"2026-08-03","cited_by_count":1,"area":"inference"},{"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":"2604.15672","title":"Faster LLM Inference via Sequential Monte Carlo","created":"2026-04-17","cited_by_count":0,"area":"inference"},{"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":"2606.24937","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2607.07740","title":"Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE","created":"2026-07-08","cited_by_count":0,"area":"rag"},{"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":"2608.01891","title":"Energy-Efficient LLM Serving via Disaggregated Attention--FFN and Flexible Frequency Scaling","created":"2026-08-03","cited_by_count":0,"area":"inference"},{"id":"2608.09119","title":"Motif 3: Technical Report","created":"2026-08-10","cited_by_count":0,"area":"moe"},{"id":"2608.10605","title":"Compute-Optimal Is Not Cluster-Optimal: Systems-Aware Scaling for Sparse Mixture-of-Experts","created":"2026-08-11","cited_by_count":0,"area":"moe"},{"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":"2609.19242","title":"Block Parallelism For Efficient Distributed Long-Context Diffusion Language Model Training","created":"2026-09-16","cited_by_count":0,"area":"diffusion"},{"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":"2609.26796","title":"Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs","created":"2026-09-22","cited_by_count":0,"area":"inference"},{"id":"2609.31306","title":"Benchmarking Attention for Tabular Foundation Models","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33410","title":"FoldAttention: Declared-Reference Softmax for Fast Decode and Deterministic Backward","created":"2026-09-27","cited_by_count":0,"area":"inference"},{"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":"2609.36301","title":"MoRE: Scaling mixture of experts with hardware-aware low-rank routing","created":"2026-09-28","cited_by_count":0,"area":"moe"},{"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":"2610.09051","title":"A Self-Pruning Transformer: Extreme KV-Cache Compression with Universal Attention","created":"2026-10-06","cited_by_count":0,"area":"inference"},{"id":"2610.11302","title":"iCATS: Fast Video Generation via Interaction-Aware Sparse Attention and Timestep-Adaptive Sparsity","created":"2026-10-08","cited_by_count":0,"area":"diffusion"},{"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},{"id":"2610.17434","title":"World-T3: Test-Time Training as Persistent Memory for Real-Time Video World Models","created":"2026-10-12","cited_by_count":0,"area":"wm"}],"next_cursor":null}