{"total":196,"rows":[{"id":"2601.02780","title":"MiMo-V2-Flash Technical Report","created":"2026-01-06","cited_by_count":191,"area":"moe"},{"id":"2607.24653","title":"Kimi K3: Open Frontier Intelligence","created":"2026-07-27","cited_by_count":138,"area":"agents"},{"id":"2603.15569","title":"Mamba-3: Improved Sequence Modeling using State Space Principles","created":"2026-03-16","cited_by_count":89,"area":"lr"},{"id":"2601.07372","title":"Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models","created":"2026-01-12","cited_by_count":86,"area":"moe"},{"id":"2603.04379","title":"Helios: Real Real-Time Long Video Generation Model","created":"2026-03-04","cited_by_count":65,"area":null},{"id":"2603.15031","title":"Attention Residuals","created":"2026-03-16","cited_by_count":65,"area":null},{"id":"2512.23675","title":"End-to-End Test-Time Training for Long Context","created":"2025-12-29","cited_by_count":62,"area":null},{"id":"2605.15178","title":"SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer","created":"2026-05-14","cited_by_count":55,"area":"wm"},{"id":"2606.13392","title":"MiniMax Sparse Attention","created":"2026-06-11","cited_by_count":44,"area":"lr"},{"id":"2605.22791","title":"Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention","created":"2026-05-21","cited_by_count":33,"area":"ssm"},{"id":"2603.12201","title":"IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse","created":"2026-03-12","cited_by_count":31,"area":"agents"},{"id":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22,"area":null},{"id":"2512.14080","title":"SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations","created":"2025-12-16","cited_by_count":21,"area":"moe"},{"id":"2608.13546","title":"Alaya-EVOKE: From Linear-Scaling Supervision to Endless World","created":"2026-08-13","cited_by_count":14,"area":"wm"},{"id":"2601.02346","title":"Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling","created":"2026-01-05","cited_by_count":13,"area":"lr"},{"id":"2602.21204","title":"Test-Time Training with KV Binding Is Secretly Linear Attention","created":"2026-02-24","cited_by_count":13,"area":null},{"id":"2605.12357","title":"$\\delta$-mem: Efficient Online Memory for Large Language Models","created":"2026-05-12","cited_by_count":13,"area":null},{"id":"2511.21016","title":"Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression","created":"2025-11-26","cited_by_count":11,"area":null},{"id":"2602.17004","title":"Arcee Trinity Large Technical Report","created":"2026-02-19","cited_by_count":11,"area":"moe"},{"id":"2604.10098","title":"Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation","created":"2026-04-11","cited_by_count":11,"area":null},{"id":"2604.15039","title":"Prefill-as-a-Service: KVCache of Next-Generation Models Could Go Cross-Datacenter","created":"2026-04-16","cited_by_count":11,"area":"inference"},{"id":"2605.30409","title":"SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer","created":"2026-05-28","cited_by_count":11,"area":"diffusion"},{"id":"2512.08829","title":"InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models","created":"2025-12-09","cited_by_count":10,"area":"mllm"},{"id":"2602.03560","title":"HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache Sharing","created":"2026-02-03","cited_by_count":10,"area":"moe"},{"id":"2602.05758","title":"LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards","created":"2026-02-05","cited_by_count":10,"area":"lr"},{"id":"2602.08064","title":"SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm","created":"2026-02-08","cited_by_count":10,"area":null},{"id":"2603.06199","title":"FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling","created":"2026-03-06","cited_by_count":9,"area":null},{"id":"2605.23889","title":"HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction","created":"2026-05-22","cited_by_count":9,"area":null},{"id":"2602.10743","title":"Kalman Linear Attention: Parallel Bayesian Filtering For Efficient Language Modelling and State Tracking","created":"2026-02-11","cited_by_count":8,"area":null},{"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":"2512.02337","title":"SpecPV: Improving Self-Speculative Decoding for Long-Context Generation via Partial Verification","created":"2025-12-02","cited_by_count":7,"area":"inference"},{"id":"2607.01299","title":"HYPIC: Accelerating Hybrid-Attention LLM Serving with Position-Independent Caching","created":"2026-07-01","cited_by_count":7,"area":"rag"},{"id":"2602.04852","title":"On State Reduction in Linear Attention","created":"2026-02-04","cited_by_count":6,"area":null},{"id":"2602.14814","title":"Learning State-Tracking from Code Using Linear RNNs","created":"2026-02-16","cited_by_count":6,"area":null},{"id":"2604.07279","title":"Mem3R: Streaming 3D Reconstruction with Hybrid Memory via Test-Time Training","created":"2026-04-08","cited_by_count":6,"area":null},{"id":"2606.01774","title":"FLARE: Diffusion for Hybrid Language Model","created":"2026-06-01","cited_by_count":6,"area":null},{"id":"2607.02303","title":"A Hippocampus for Linear Attention: An Exact Memory for What the Recurrent State Forgets","created":"2026-07-02","cited_by_count":6,"area":null},{"id":"2607.25357","title":"Raven: High-Recall Sequence Modeling with Sparse Memory Routing","created":"2026-07-28","cited_by_count":6,"area":null},{"id":"2608.27513","title":"DAMP: Decay-Aware Mixed-Precision Recurrent-State Quantization","created":"2026-08-27","cited_by_count":6,"area":"inference"},{"id":"2602.10377","title":"Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs","created":"2026-02-10","cited_by_count":5,"area":"vla"},{"id":"2604.19241","title":"UniEP: Unified Expert-Parallel MoE MegaKernel for LLM Training","created":"2026-04-21","cited_by_count":5,"area":"moe"},{"id":"2605.19660","title":"OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond","created":"2026-05-19","cited_by_count":5,"area":"inference"},{"id":"2606.12195","title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","created":"2026-06-10","cited_by_count":5,"area":"agents"},{"id":"2606.15378","title":"Rethinking the Role of Efficient Attention in Hybrid Architectures","created":"2026-06-13","cited_by_count":5,"area":"lr"},{"id":"2512.12602","title":"Exact Flow Linear Attention: Exact Solution from Continuous-Time Dynamics","created":"2025-12-14","cited_by_count":4,"area":null},{"id":"2602.02180","title":"STILL: Selecting Tokens for Intra-Layer Hybrid Attention to Linearize LLMs","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2603.22473","title":"Component Ablation for Efficient Hybrid Language Model Architectures: Performance, Resilience, and Compression Implications","created":"2026-03-23","cited_by_count":4,"area":null},{"id":"2603.26380","title":"Switch Attention: Towards Dynamic and Fine-grained Hybrid Transformers","created":"2026-03-27","cited_by_count":4,"area":null},{"id":"2604.22782","title":"Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing","created":"2026-04-03","cited_by_count":4,"area":null},{"id":"2605.05838","title":"MDN: Parallelizing Stepwise Momentum for Delta Linear Attention","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2606.09659","title":"End-to-End Context Compression at Scale","created":"2026-06-08","cited_by_count":4,"area":"inference"},{"id":"2607.14144","title":"The Capability Convergence Hypothesis: Capability from Access Structure, Not Scale","created":"2026-07-14","cited_by_count":4,"area":null},{"id":"2607.25380","title":"Memory for Large Language Models","created":"2026-07-28","cited_by_count":4,"area":null},{"id":"2602.03681","title":"Neural Attention Search Linear: Towards Adaptive Token-Level Hybrid Attention Models","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2602.13215","title":"When to Think Fast and Slow? AMOR: Adaptive Entropy Gate for Hybrid Models","created":"2026-01-22","cited_by_count":3,"area":null},{"id":"2603.20397","title":"KV Cache Optimization Strategies for Scalable and Efficient LLM Inference","created":"2026-03-20","cited_by_count":3,"area":"inference"},{"id":"2605.19049","title":"KVBuffer: IO-aware Serving for Linear Attention","created":"2026-05-18","cited_by_count":3,"area":"inference"},{"id":"2607.20062","title":"Solar Open 2 Technical Report","created":"2026-07-22","cited_by_count":3,"area":"agents"},{"id":"2607.28611","title":"Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers","created":"2026-07-30","cited_by_count":3,"area":"diffusion"},{"id":"2608.01651","title":"Bole: Efficient Tree Speculation for Hybrid-Attention Language Models","created":"2026-08-03","cited_by_count":3,"area":"inference"},{"id":"2608.24814","title":"Effective Learning Rate Governs Loss Dynamics in Language Model Pretraining","created":"2026-08-25","cited_by_count":3,"area":null},{"id":"2609.02986","title":"Modern Transformers Are Implicit Hybrids: From Functional Differentiation to Principled Hybrid Architecture Design","created":"2026-09-02","cited_by_count":3,"area":null},{"id":"2602.10300","title":"Configuration-to-Performance Scaling Law with Neural Ansatz","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2602.11958","title":"RAM-Net: Linear-Time Sequence Modeling with Sparsely Addressable State","created":"2026-02-12","cited_by_count":2,"area":null},{"id":"2602.13680","title":"AllMem: A Memory-centric Recipe for Efficient Long-context Modeling","created":"2026-02-14","cited_by_count":2,"area":null},{"id":"2603.27086","title":"EFlow: Fast Few-Step Video Generator Training from Scratch via Efficient Solution Flow","created":"2026-03-28","cited_by_count":2,"area":"diffusion"},{"id":"2604.05688","title":"Attention Editing: A Versatile Framework for Cross-Architecture Attention Conversion","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2604.18058","title":"Sonata: A Hybrid World Model for Inertial Kinematics under Clinical Data Scarcity","created":"2026-04-20","cited_by_count":2,"area":"wm"},{"id":"2604.22575","title":"SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2605.06221","title":"UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification","created":"2026-05-07","cited_by_count":2,"area":"inference"},{"id":"2606.06467","title":"You Only Index Once: Cross-Layer Sparse Attention with Shared Routing","created":"2026-06-04","cited_by_count":2,"area":"inference"},{"id":"2606.28876","title":"MMLA: Memory-Mediated Learning Architecture for Predictive Dual-State Adaptation","created":"2026-06-27","cited_by_count":2,"area":null},{"id":"2606.30562","title":"Morphing into Hybrid Attention Models","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2607.21553","title":"SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation","created":"2026-07-23","cited_by_count":2,"area":"diffusion"},{"id":"2608.01672","title":"Learning What to Remember: Test-Time Training via Context Distillation","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.12149","title":"Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2608.30386","title":"DASC: Decay-Aware State Compression for Hybrid Linear-Attention Serving","created":"2026-08-31","cited_by_count":2,"area":null},{"id":"2608.30692","title":"Can Video World Models Track Unobserved World States?","created":"2026-08-31","cited_by_count":2,"area":"wm"},{"id":"2610.13778","title":"ReplaySSM: Cache SSM Inputs, Not State","created":"2026-10-09","cited_by_count":2,"area":"inference"},{"id":"2601.11164","title":"SoLA-Vision: Fine-grained Layer-wise Linear Softmax Hybrid Attention","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2602.01763","title":"A Provable Expressiveness Hierarchy in Hybrid Linear-Full Attention","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.03922","title":"Online Vector Quantized Attention","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2602.07599","title":"Rational Transductors","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2603.22325","title":"Hybrid Associative Memories","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2604.16950","title":"AutoPKG: An Automated Framework for Dynamic E-commerce Product-Attribute Knowledge Graph Construction","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2604.19021","title":"FG$^2$-GDN: Enhancing Long-Context Gated Delta Networks with Doubly Fine-Grained Control","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2604.25080","title":"CacheFlow: Efficient LLM Serving with 3D-Parallel KV Cache Restoration","created":"2026-04-28","cited_by_count":1,"area":"rag"},{"id":"2604.27351","title":"Heterogeneous Scientific Foundation Model Collaboration","created":"2026-04-30","cited_by_count":1,"area":"agents"},{"id":"2605.05066","title":"The Impossibility Triangle of Long-Context Modeling","created":"2026-05-06","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":"2605.13473","title":"OSDN: Improving Delta Rule with Provable Online Preconditioning in Linear Attention","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2606.06034","title":"When Good Enough Is Optimal: Multiplication-Only Matrix Inversion Approximation for Quantized Gated DeltaNet","created":"2026-06-04","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":"2606.09862","title":"Blurry Window Attention","created":"2026-05-31","cited_by_count":1,"area":"inference"},{"id":"2606.12364","title":"On Subquadratic Architectures: From Applications to Principles","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.16429","title":"Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation","created":"2026-06-15","cited_by_count":1,"area":"inference"},{"id":"2607.03055","title":"SHiPPO: Recurrent Memory with Transported Polynomial Projections","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2607.07706","title":"The Key to Going Linear: Analysis-Driven Transformer Linearization","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2607.07953","title":"Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing","created":"2026-07-08","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}],"next_cursor":"100"}