{"total":185,"rows":[{"id":"2506.08009","title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","created":"2025-06-09","cited_by_count":625,"area":"diffusion"},{"id":"2503.09573","title":"Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models","created":"2025-03-12","cited_by_count":409,"area":"diffusion"},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328,"area":"lr"},{"id":"2505.13211","title":"MAGI-1: Autoregressive Video Generation at Scale","created":"2025-05-19","cited_by_count":276,"area":"wm"},{"id":"2510.26692","title":"Kimi Linear: An Expressive, Efficient Attention Architecture","created":"2025-10-30","cited_by_count":196,"area":"deeprl"},{"id":"2602.06036","title":"DFlash: Block Diffusion for Flash Speculative Decoding","created":"2026-02-05","cited_by_count":135,"area":"diffusion"},{"id":"2502.04507","title":"Fast Video Generation with Sliding Tile Attention","created":"2025-02-06","cited_by_count":128,"area":"diffusion"},{"id":"2505.18875","title":"Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation","created":"2025-05-24","cited_by_count":106,"area":"diffusion"},{"id":"2505.13389","title":"VSA: Faster Video Diffusion with Trainable Sparse Attention","created":"2025-05-19","cited_by_count":104,"area":"diffusion"},{"id":"2505.16839","title":"LaViDa: A Large Diffusion Language Model for Multimodal Understanding","created":"2025-05-22","cited_by_count":84,"area":"lr"},{"id":"2505.20171","title":"Long-Context State-Space Video World Models","created":"2025-05-26","cited_by_count":64,"area":"wm"},{"id":"2512.01031","title":"VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference","created":"2025-11-30","cited_by_count":58,"area":"vla"},{"id":"2506.09018","title":"Edit Flows: Flow Matching with Edit Operations","created":"2025-06-10","cited_by_count":55,"area":"diffusion"},{"id":"2509.01025","title":"Any-Order Flexible Length Masked Diffusion","created":"2025-08-31","cited_by_count":51,"area":"diffusion"},{"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":"2511.08923","title":"TiDAR: Think in Diffusion, Talk in Autoregression","created":"2025-11-12","cited_by_count":37,"area":"lr"},{"id":"2603.03276","title":"Beyond Language Modeling: An Exploration of Multimodal Pretraining","created":"2026-03-03","cited_by_count":37,"area":"moe"},{"id":"2511.09057","title":"PAN: A World Model for General, Actionable, and Long-Horizon World Simulation","created":"2025-11-12","cited_by_count":36,"area":"wm"},{"id":"2505.16864","title":"Training-Free Efficient Video Generation via Dynamic Token Carving","created":"2025-05-22","cited_by_count":34,"area":"diffusion"},{"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":"2605.18739","title":"LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation","created":"2026-05-18","cited_by_count":30,"area":"diffusion"},{"id":"2506.22084","title":"Transformers are Graph Neural Networks","created":"2025-06-27","cited_by_count":29,"area":null},{"id":"2506.05345","title":"Inference-Time Hyper-Scaling with KV Cache Compression","created":"2025-06-05","cited_by_count":27,"area":"lr"},{"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":"2511.22625","title":"ReasonEdit: Towards Reasoning-Enhanced Image Editing Models","created":"2025-11-27","cited_by_count":25,"area":"lr"},{"id":"2606.25473","title":"Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models","created":"2026-06-24","cited_by_count":25,"area":"wm"},{"id":"2601.19278","title":"DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference","created":"2026-01-27","cited_by_count":24,"area":"inference"},{"id":"2509.04185","title":"Set Block Decoding is a Language Model Inference Accelerator","created":"2025-09-04","cited_by_count":23,"area":null},{"id":"2508.03334","title":"Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video Generation","created":"2025-08-05","cited_by_count":21,"area":"diffusion"},{"id":"2506.04648","title":"FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion","created":"2025-06-05","cited_by_count":19,"area":"diffusion"},{"id":"2509.24007","title":"Sequential Diffusion Language Models","created":"2025-09-28","cited_by_count":19,"area":"diffusion"},{"id":"2512.03324","title":"Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs","created":"2025-12-03","cited_by_count":19,"area":"inference"},{"id":"2510.14979","title":"From Pixels to Words -- Towards Native Vision-Language Primitives at Scale","created":"2025-10-16","cited_by_count":18,"area":"mllm"},{"id":"2502.02534","title":"Adaptive Self-improvement LLM Agentic System for ML Library Development","created":"2025-02-04","cited_by_count":16,"area":"agents"},{"id":"2512.12080","title":"BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Models","created":"2025-12-12","cited_by_count":16,"area":"wm"},{"id":"2602.21157","title":"HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoning","created":"2026-02-24","cited_by_count":16,"area":"lr"},{"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":"2606.03159","title":"NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation","created":"2026-06-02","cited_by_count":14,"area":"wm"},{"id":"2607.04884","title":"HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better","created":"2026-07-06","cited_by_count":14,"area":"mllm"},{"id":"2502.12352","title":"Towards Mechanistic Interpretability of Graph Transformers via Attention Graphs","created":"2025-02-17","cited_by_count":13,"area":"mechinterp"},{"id":"2505.14687","title":"Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers","created":"2025-05-20","cited_by_count":13,"area":"diffusion"},{"id":"2602.02579","title":"ProphetKV: User-Query-Driven Selective Recomputation for Efficient KV Cache Reuse in Retrieval-Augmented Generation","created":"2026-01-31","cited_by_count":13,"area":"rag"},{"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":"2605.22344","title":"Bernini: Latent Semantic Planning for Video Diffusion","created":"2026-05-21","cited_by_count":12,"area":"lr"},{"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":"2602.04705","title":"ERNIE 5.0 Technical Report","created":"2026-02-04","cited_by_count":11,"area":"moe"},{"id":"2604.07823","title":"LPM 1.0: Video-based Character Performance Model","created":"2026-04-09","cited_by_count":11,"area":null},{"id":"2506.21103","title":"Learning to Skip the Middle Layers of Transformers","created":"2025-06-26","cited_by_count":10,"area":"moe"},{"id":"2511.14751","title":"Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers","created":"2025-11-18","cited_by_count":10,"area":"inference"},{"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":"2512.22234","title":"DiRL: An Efficient Post-Training Framework for Diffusion Language Models","created":"2025-12-23","cited_by_count":10,"area":"diffusion"},{"id":"2505.13791","title":"Scalable Autoregressive 3D Molecule Generation","created":"2025-05-20","cited_by_count":8,"area":"diffusion"},{"id":"2508.18255","title":"Hermes 4 Technical Report","created":"2025-08-25","cited_by_count":8,"area":"lr"},{"id":"2510.06050","title":"Edit-Based Flow Matching for Temporal Point Processes","created":"2025-10-07","cited_by_count":8,"area":"diffusion"},{"id":"2510.26769","title":"SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models","created":"2025-10-30","cited_by_count":8,"area":"mllm"},{"id":"2512.07843","title":"ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models","created":"2025-11-24","cited_by_count":8,"area":"lr"},{"id":"2604.10103","title":"Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation","created":"2026-04-11","cited_by_count":8,"area":"diffusion"},{"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":"2604.15911","title":"Efficient Video Diffusion Models: Advancements and Challenges","created":"2026-04-17","cited_by_count":7,"area":"diffusion"},{"id":"2605.25343","title":"Toward Native Multimodal Modeling: A Roadmap","created":"2026-05-25","cited_by_count":7,"area":"wm"},{"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":"2601.12904","title":"From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation","created":"2026-01-19","cited_by_count":5,"area":"rag"},{"id":"2604.02330","title":"ActionParty: Multi-Subject Action Binding in Generative Video Games","created":"2026-04-02","cited_by_count":5,"area":"wm"},{"id":"2604.04215","title":"DARE: Diffusion Large Language Models Alignment and Reinforcement Executor","created":"2026-04-05","cited_by_count":5,"area":"alignment"},{"id":"2605.15871","title":"Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design","created":"2026-05-15","cited_by_count":5,"area":"agents"},{"id":"2605.25500","title":"Full-4D: Generating Full-Scope 4D Scenes from a Single-View Video","created":"2026-05-25","cited_by_count":5,"area":"diffusion"},{"id":"2606.19257","title":"DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models","created":"2026-06-17","cited_by_count":5,"area":"lr"},{"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":"2509.16518","title":"FG-Attn: Leveraging Fine-Grained Sparse Attention in Video Diffusion Models","created":"2025-09-20","cited_by_count":4,"area":"diffusion"},{"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":"2512.16144","title":"INTELLECT-3: Technical Report","created":"2025-12-18","cited_by_count":4,"area":"lr"},{"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":"2605.12825","title":"Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion","created":"2026-05-12","cited_by_count":4,"area":"diffusion"},{"id":"2606.09659","title":"End-to-End Context Compression at Scale","created":"2026-06-08","cited_by_count":4,"area":"inference"},{"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":"2510.20787","title":"Alleviating Forgetfulness of Linear Attention by Hybrid Sparse Attention and Contextualized Learnable Token Eviction","created":"2025-10-23","cited_by_count":3,"area":"inference"},{"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":"2512.20157","title":"SigLino: Efficient Multi-Teacher Distillation for Agglomerative Vision Foundation Models","created":"2025-12-23","cited_by_count":3,"area":"moe"},{"id":"2601.11716","title":"AllShowers: One model for all calorimeter showers","created":"2026-01-16","cited_by_count":3,"area":null},{"id":"2601.22031","title":"Causal Autoregressive Diffusion Language Model","created":"2026-01-29","cited_by_count":3,"area":"diffusion"},{"id":"2601.22275","title":"VMonarch: Efficient Video Diffusion Transformers with Structured Attention","created":"2026-01-29","cited_by_count":3,"area":"diffusion"},{"id":"2602.20943","title":"UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling","created":"2026-02-24","cited_by_count":3,"area":"driving"},{"id":"2603.00825","title":"COMBAT: Conditional World Models for Behavioral Agent Training","created":"2026-02-28","cited_by_count":3,"area":"wm"},{"id":"2603.15590","title":"Effective Distillation to Hybrid xLSTM Architectures","created":"2026-03-16","cited_by_count":3,"area":null}],"next_cursor":"100"}