{"total":83,"rows":[{"id":"2512.03052","title":"LATTICE: Democratize High-Fidelity 3D Generation at Scale","created":"2025-11-24","cited_by_count":44,"area":null},{"id":"2510.06377","title":"Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data","created":"2025-10-07","cited_by_count":39,"area":null},{"id":"2603.03269","title":"LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory","created":"2026-03-03","cited_by_count":39,"area":null},{"id":"2506.01928","title":"Esoteric Language Models: A Family of Any-Order Diffusion LLMs","created":"2025-06-02","cited_by_count":34,"area":null},{"id":"2506.22084","title":"Transformers are Graph Neural Networks","created":"2025-06-27","cited_by_count":29,"area":null},{"id":"2506.10968","title":"Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop","created":"2025-06-12","cited_by_count":25,"area":null},{"id":"2509.04185","title":"Set Block Decoding is a Language Model Inference Accelerator","created":"2025-09-04","cited_by_count":23,"area":null},{"id":"2603.12938","title":"Thinking in Streaming Video","created":"2026-03-13","cited_by_count":16,"area":null},{"id":"2506.22419","title":"The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements","created":"2025-06-27","cited_by_count":15,"area":null},{"id":"2506.18839","title":"4Real-Video-V2: Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation","created":"2025-06-18","cited_by_count":14,"area":null},{"id":"2511.17826","title":"Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch","created":"2025-11-21","cited_by_count":14,"area":null},{"id":"2502.12082","title":"AdaSplash: Adaptive Sparse Flash Attention","created":"2025-02-17","cited_by_count":12,"area":null},{"id":"2503.08640","title":"Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention","created":"2025-03-11","cited_by_count":12,"area":null},{"id":"2505.12044","title":"FlashBias: Fast Computation of Attention with Bias","created":"2025-05-17","cited_by_count":11,"area":null},{"id":"2508.20258","title":"SwizzlePerf: Hardware-Aware LLMs for GPU Kernel Performance Optimization","created":"2025-08-27","cited_by_count":11,"area":null},{"id":"2604.07823","title":"LPM 1.0: Video-based Character Performance Model","created":"2026-04-09","cited_by_count":11,"area":null},{"id":"2512.16864","title":"RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing","created":"2025-12-18","cited_by_count":10,"area":null},{"id":"2510.10620","title":"DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism","created":"2025-10-12","cited_by_count":7,"area":null},{"id":"2505.18883","title":"Partition Generative Modeling: Masked Modeling Without Masks","created":"2025-05-24","cited_by_count":6,"area":null},{"id":"2508.02124","title":"Trainable Dynamic Mask Sparse Attention","created":"2025-08-04","cited_by_count":6,"area":null},{"id":"2511.14712","title":"FreeSwim: Revisiting Sliding-Window Attention Mechanisms for Training-Free Ultra-High-Resolution Video Generation","created":"2025-11-18","cited_by_count":6,"area":null},{"id":"2601.11579","title":"Bielik 11B v3: Multilingual Large Language Model for European Languages","created":"2025-12-30","cited_by_count":6,"area":null},{"id":"2502.05967","title":"$\\mu$nit Scaling: Simple and Scalable FP8 LLM Training","created":"2025-02-09","cited_by_count":5,"area":null},{"id":"2503.06671","title":"Emulating Self-attention with Convolution for Efficient Image Super-Resolution","created":"2025-03-09","cited_by_count":5,"area":null},{"id":"2505.17083","title":"Scale-invariant Attention","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2502.15349","title":"AttentionEngine: A Versatile Framework for Efficient Attention Mechanisms on Diverse Hardware Platforms","created":"2025-02-21","cited_by_count":4,"area":null},{"id":"2506.12355","title":"QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm","created":"2025-06-14","cited_by_count":4,"area":null},{"id":"2510.08726","title":"Neptune: Advanced ML Operator Fusion for Locality and Parallelism on GPUs","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2512.17065","title":"XLM: A Python package for non-autoregressive language models","created":"2025-12-18","cited_by_count":4,"area":null},{"id":"2602.04361","title":"SparVAR: Exploring Sparsity in Visual AutoRegressive Modeling for Training-Free Acceleration","created":"2026-02-04","cited_by_count":4,"area":null},{"id":"2502.16912","title":"When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time?","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2511.05313","title":"Controllably Efficient Language Models","created":"2025-11-07","cited_by_count":3,"area":null},{"id":"2511.11581","title":"The Anatomy of a Triton Attention Kernel","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2601.11716","title":"AllShowers: One model for all calorimeter showers","created":"2026-01-16","cited_by_count":3,"area":null},{"id":"2603.15590","title":"Effective Distillation to Hybrid xLSTM Architectures","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2604.15180","title":"AdaSplash-2: Faster Differentiable Sparse Attention","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2605.09430","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","created":"2026-05-10","cited_by_count":3,"area":null},{"id":"2607.01218","title":"The State-Prediction Separation Hypothesis","created":"2026-07-01","cited_by_count":3,"area":null},{"id":"2605.26519","title":"$R^3$: 3D Reconstruction via Relative Regression","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2606.03803","title":"LiveBand: Live Accompaniment Generation in the Audio Domain","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2607.01538","title":"Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale","created":"2026-07-01","cited_by_count":2,"area":null},{"id":"2506.09163","title":"Scalable Spatiotemporal Inference with Biased Scan Attention Transformer Neural Processes","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2506.16580","title":"Streaming Non-Autoregressive Model for Accent Conversion and Pronunciation Improvement","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2507.13546","title":"NABLA: Neighborhood Adaptive Block-Level Attention","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2509.25044","title":"A Scalable Distributed Framework for Multimodal GigaVoxel Image Registration","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2511.05832","title":"Hilbert-Guided Sparse Local Attention","created":"2025-11-08","cited_by_count":1,"area":null},{"id":"2511.08854","title":"Decomposition of Small Transformer Models","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2511.18105","title":"AdaPerceiver: Transformers with Adaptive Width, Depth, and Tokens","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2602.00482","title":"AREAL-DTA: Dynamic Tree Attention for Efficient Reinforcement Learning of Large Language Models","created":"2026-01-31","cited_by_count":1,"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":"2605.09877","title":"Key-Value Means: Transformers with Expandable Block-Recurrent Compressed Memory","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2606.00422","title":"UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2608.02515","title":"LiveMem: Maintaining Memory State Continuity in Long-Running LLM Inference","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2503.21473","title":"DeepRV: Accelerating Spatiotemporal Inference with Pre-trained Neural Priors","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2505.18522","title":"How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2506.05007","title":"QiMeng: Fully Automated Hardware and Software Design for Processor Chip","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2506.06095","title":"Accelerating Sparse Transformer Inference on GPU","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2508.11921","title":"ENA: Efficient N-dimensional Attention","created":"2025-08-16","cited_by_count":0,"area":null},{"id":"2509.26411","title":"TrackFormers Part 2: Enhanced Transformer-Based Models for High-Energy Physics Track Reconstruction","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.05175","title":"Exact Causal Attention with 10% Fewer Operations","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2511.02043","title":"Flashlight: PyTorch Compiler Extensions to Accelerate Attention Variants","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2512.14237","title":"Ladder Up, Memory Down: Low-Cost Fine-Tuning With Side Nets","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2512.19283","title":"OmniEgoCap: Camera-Agnostic Sequence-Level Egocentric Motion Reconstruction","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2512.23049","title":"Accelerating Language Model Workflows with Prompt Choreography","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2601.17334","title":"Power-based Partial Attention: Bridging Linear-Complexity and Full Attention","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2602.11410","title":"CADET: Context-Conditioned Ads CTR Prediction With a Decoder-Only Transformer","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.06731","title":"PolyBlocks: A Compiler Infrastructure for AI Chips and Programming Frameworks","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.18572","title":"UEPS: Robust and Efficient MRI Reconstruction","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2603.27915","title":"FlashSign: Pose-Free Guidance for Efficient Sign Language Video Generation","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.00754","title":"Stochastic Attention: Connectome-Inspired Randomized Routing for Expressive Linear-Time Attention","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.18603","title":"Dual Triangle Attention: Effective Bidirectional Attention Without Positional Embeddings","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.27124","title":"Better Models, Faster Training: Sigmoid Attention for single-cell Foundation Models","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2608.10519","title":"SparSTAR: Sparse Attention for SpaceTime AutoRegressive Video Synthesis","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.19920","title":"Learning how to Forget: Fine-tuning for Long-Context Sparse Attention","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.20427","title":"BF1: A Causal Dyadic Sparse-Attention Retrofit for Efficient Long-Context Transformers","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.28706","title":"Variable-Granularity Tokenization for High-Resolution Object Detection","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.32704","title":"CoWindow Attention: Full Causal Coverage Is a Collective Property","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32712","title":"MassAlloc Attention: Let Attention Allocate Its Own Compute","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36529","title":"Triadic Linear Attention: Three-Dimensional Recurrent States for Long-Context Sequence Modeling","created":"2026-09-29","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":"2610.02395","title":"FlashSinkhorn 2: Block-Sparse Entropic Optimal Transport","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.15638","title":"MERIT: Scaling KG Foundation Models with Relation Transformers","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.18284","title":"Efficient Scene-Text Refinement via Pixel-Space Grouped Image Generation","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}