{"total":120,"rows":[{"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":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22,"area":null},{"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":"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":"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":"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":"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":"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":"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":"2604.05688","title":"Attention Editing: A Versatile Framework for Cross-Architecture Attention Conversion","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2604.22575","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":"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":"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":"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":"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":"2606.12364","title":"On Subquadratic Architectures: From Applications to Principles","created":"2026-06-10","cited_by_count":1,"area":null},{"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},{"id":"2608.13668","title":"The Query Knows What to Forget: A Second Erase Direction for Linear Attention","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2608.29539","title":"LoGo: Token-Level Dynamic Local-Global Attention","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2609.00092","title":"Safin-1: Safety from Within through Memory-Native State Evolution","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2609.07816","title":"Kalman Delta Networks: Uncertainty-aware Associative Memory","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2511.23347","title":"Distributed Dynamic Associative Memory via Online Convex Optimization","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2601.06463","title":"Gecko: An Efficient Neural Architecture Inherently Processing Sequences with Arbitrary Lengths","created":"2026-01-10","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":"2601.18401","title":"Superlinear Multi-Step Attention","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2601.22852","title":"Hierarchical Shift Mixing -- Beyond Dense Attention in Transformers","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.10796","title":"PRISM: Parallel Residual Iterative Sequence Model","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2604.24715","title":"Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.07588","title":"Revisiting Transformer Layer Parameterization Through Causal Energy Minimization","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.10537","title":"Mela: Test-Time Memory Consolidation based on Transformation Hypothesis","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.31163","title":"Memory by Design: Bayesian Layers for Sequence Modeling","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.00472","title":"CodeCytos: AI-assisted spatial molecular imaging analysis via code-augmented agent action space","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.27229","title":"CARVE: Content-Aware Recurrent with Value Efficiency for Chunk-Parallel Linear Attention","created":"2026-06-25","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":"2608.01034","title":"Opt.Gear Technical Report","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.02689","title":"Stuck on \"A\": Diagnosing and Repairing Interface Injury in Attention-to-KDA Linearization of a 0.6B Language Model","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.09307","title":"Linearized 2-Simplicial Attention","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.09432","title":"ZetaGPT: A Reference Implementation of Positional--Encoding--Free State--Space--Attention Language Models","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.20172","title":"Ask Self, Ask Others: Relation Is All You Need","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.22354","title":"SANE: State Anomaly Neutralization for Stable Extreme-Context Delta-Rule Models","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.06872","title":"Exact Record Omission in Delta Attention: A Transport Criterion, Its Cost, and a Replay Certificate","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.08574","title":"Do New Attention Mechanisms Actually Fix Attention Sinks at Million-Token Context?","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.09157","title":"Learning Length-Extrapolatable Recurrent Models","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.14320","title":"SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.15545","title":"The Token Before the Value Is the Key: How Hybrid Architectures Organize Induction Circuits","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.18407","title":"TERN: A Delta-rule Memory with a Seasonal Reference and Online Adaptation for Epidemic Forecasting","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.25802","title":"Latest Exact Match Attention","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.30950","title":"Low-Bit Recurrent States in Hybrid Language Models","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32114","title":"Empowering Hybrid Attention Models on NPUs","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32447","title":"Length-Independent State Tracking Under a Parallel Scan","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33268","title":"LSTMem: Hierarchical Long Short-Term Online Memory for Large Language Models","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33477","title":"Just Let Linear States Forget the Distant Past: Prefix Caching via Suffix Replay for Hybrid LLMs","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34034","title":"ADPTNet: Adaptive with Prescriptive Timescales Non-Linear SSM for Sequence Modelling","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34292","title":"Pre-registered tests of solid-state-physics-inspired LLM compression: a cluster-level negative result at small-language-model scale","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35200","title":"ReCAT: Remember, Count, and Time: Structured Recurrent Memory for Robot Manipulation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35263","title":"WavePP: High-Throughput Pipeline Parallel LLM Prefill under Prefix Reuse","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35416","title":"When Should the Count Change? Learning State Maintenance for Causal Video Counting","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35551","title":"BaRe-Mem: Bayesian Reliability Memory for Robust and Adaptive Agent Consultation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36259","title":"CyFA: Linear Sequence Modeling with Relative-Time-Partitioned Memory","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36760","title":"QuantMLA: Function-Aligned Dual-Path Quantization for Low-Bit MLA KV Caching","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.36860","title":"IronLLM: Forging Compact Edge-Native Language Models for Real-Time Embodied Intelligence","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":"100"}