{"total":141,"rows":[{"id":"2510.26692","title":"Kimi Linear: An Expressive, Efficient Attention Architecture","created":"2025-10-30","cited_by_count":196,"area":"deeprl"},{"id":"2607.24653","title":"Kimi K3: Open Frontier Intelligence","created":"2026-07-27","cited_by_count":138,"area":"agents"},{"id":"2503.21614","title":"A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond","created":"2025-03-27","cited_by_count":132,"area":"lr"},{"id":"2512.24695","title":"Nested Learning: The Illusion of Deep Learning Architectures","created":"2025-12-31","cited_by_count":72,"area":null},{"id":"2505.23735","title":"ATLAS: Learning to Optimally Memorize the Context at Test Time","created":"2025-05-29","cited_by_count":66,"area":null},{"id":"2504.13173","title":"It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization","created":"2025-04-17","cited_by_count":64,"area":null},{"id":"2510.17800","title":"Glyph: Scaling Context Windows via Visual-Text Compression","created":"2025-10-20","cited_by_count":49,"area":null},{"id":"2508.15884","title":"Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search","created":"2025-08-21","cited_by_count":41,"area":null},{"id":"2506.04761","title":"Log-Linear Attention","created":"2025-06-05","cited_by_count":40,"area":null},{"id":"2505.16381","title":"PaTH Attention: Position Encoding via Accumulating Householder Transformations","created":"2025-05-22","cited_by_count":34,"area":null},{"id":"2505.19488","title":"Understanding Transformer from the Perspective of Associative Memory","created":"2025-05-26","cited_by_count":34,"area":null},{"id":"2511.16652","title":"Evolution Strategies at the Hyperscale","created":"2025-11-20","cited_by_count":25,"area":null},{"id":"2505.03005","title":"RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale","created":"2025-05-05","cited_by_count":24,"area":null},{"id":"2507.19595","title":"Efficient Attention Mechanisms for Large Language Models: A Survey","created":"2025-07-25","cited_by_count":22,"area":null},{"id":"2504.05646","title":"Lattice: Learning to Efficiently Compress the Memory","created":"2025-04-08","cited_by_count":19,"area":null},{"id":"2505.17761","title":"Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models","created":"2025-05-23","cited_by_count":18,"area":null},{"id":"2601.22156","title":"Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts","created":"2026-01-29","cited_by_count":18,"area":null},{"id":"2510.25502","title":"TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting","created":"2025-10-29","cited_by_count":17,"area":null},{"id":"2509.22284","title":"Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models","created":"2025-09-26","cited_by_count":16,"area":null},{"id":"2506.02475","title":"Comba: Improving Bilinear RNNs with Closed-loop Control","created":"2025-06-03","cited_by_count":15,"area":null},{"id":"2511.18890","title":"Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models","created":"2025-11-24","cited_by_count":15,"area":null},{"id":"2510.04800","title":"Hybrid Architectures for Language Models: Systematic Analysis and Design Insights","created":"2025-10-06","cited_by_count":14,"area":"ssm"},{"id":"2507.16577","title":"Scaling Linear Attention with Sparse State Expansion","created":"2025-07-22","cited_by_count":13,"area":null},{"id":"2601.00671","title":"Fast-weight Product Key Memory","created":"2026-01-02","cited_by_count":13,"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":"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":"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":"2507.02591","title":"AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2511.17388","title":"Selective Rotary Position Embedding","created":"2025-11-21","cited_by_count":9,"area":null},{"id":"2505.22135","title":"RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding","created":"2025-05-28","cited_by_count":8,"area":"inference"},{"id":"2506.10918","title":"Sequential-Parallel Duality in Prefix Scannable Models","created":"2025-06-12","cited_by_count":8,"area":"ssm"},{"id":"2508.08435","title":"Fast weight programming and linear transformers: from machine learning to neurobiology","created":"2025-08-11","cited_by_count":8,"area":null},{"id":"2511.07343","title":"TNT: Improving Chunkwise Training for Test-Time Memorization","created":"2025-11-10","cited_by_count":8,"area":null},{"id":"2603.03612","title":"Why Are Linear RNNs More Parallelizable?","created":"2026-03-04","cited_by_count":8,"area":null},{"id":"2504.21463","title":"RWKV-X: A Linear Complexity Hybrid Language Model","created":"2025-04-30","cited_by_count":6,"area":null},{"id":"2507.23632","title":"On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective","created":"2025-07-31","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":"2606.01774","title":"FLARE: Diffusion for Hybrid Language Model","created":"2026-06-01","cited_by_count":6,"area":null},{"id":"2606.15378","title":"Rethinking the Role of Efficient Attention in Hybrid Architectures","created":"2026-06-13","cited_by_count":5,"area":"lr"},{"id":"2606.26560","title":"Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention","created":"2026-06-25","cited_by_count":5,"area":"moe"},{"id":"2508.16745","title":"Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling","created":"2025-08-22","cited_by_count":4,"area":"lr"},{"id":"2510.01450","title":"Local Linear Attention: An Optimal Interpolation of Linear and Softmax Attention For Test-Time Regression","created":"2025-10-01","cited_by_count":4,"area":null},{"id":"2510.05364","title":"The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2510.19266","title":"Data Efficient Any Transformer-to-Mamba Distillation via Attention Bridge","created":"2025-10-22","cited_by_count":4,"area":"ssm"},{"id":"2603.19606","title":"Beyond Quadratic: Linear-Time Change Detection with RWKV","created":"2026-03-20","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":"2607.25380","title":"Memory for Large Language Models","created":"2026-07-28","cited_by_count":4,"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":"2602.12601","title":"HyperMLP: An Integrated Perspective for Sequence Modeling","created":"2026-02-13","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":"2604.17121","title":"The Topological Trouble With Transformers","created":"2026-04-18","cited_by_count":3,"area":null},{"id":"2608.07110","title":"Modular TTT: Rethinking Test-Time Training as Composable Modules","created":"2026-08-07","cited_by_count":3,"area":null},{"id":"2504.19191","title":"WuNeng: Hybrid State with Attention","created":"2025-04-27","cited_by_count":2,"area":"inference"},{"id":"2505.16256","title":"DualComp: End-to-End Learning of a Unified Dual-Modality Lossless Compressor","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2506.13001","title":"Adaptable Symbolic Music Infilling with MIDI-RWKV","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2510.05901","title":"Untangling Component Imbalance in Hybrid Linear Attention Conversion Methods","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2510.11602","title":"Deconstructing Attention: Investigating Design Principles for Effective Language Modeling","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2510.26083","title":"Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2510.27258","title":"Higher-order Linear Attention","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2602.09893","title":"TaCo: A Benchmark for Lossless and Lossy Codecs of Heterogeneous Tactile Data","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":"2602.22286","title":"OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2606.23670","title":"Tapered Language Models","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":"2608.28444","title":"Sliding-window beats linear attention","created":"2026-08-28","cited_by_count":2,"area":"inference"},{"id":"2506.11305","title":"Don't Pay Attention","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2507.19353","title":"Smooth Reading: Bridging the Gap of Recurrent LLM to Self-Attention LLM on Long-Context Tasks","created":"2025-07-25","cited_by_count":1,"area":null},{"id":"2509.22630","title":"StateX: Enhancing RNN Recall via Post-training State Expansion","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2512.07539","title":"FRWKV:Frequency-Domain Linear Attention for Long-Term Time Series Forecasting","created":"2025-12-08","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":"2603.09221","title":"Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2603.19567","title":"Efficiency Follows Global-Local Decoupling","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2603.20578","title":"Context Cartography: Toward Structured Governance of Contextual Space in Large Language Model Systems","created":"2026-03-21","cited_by_count":1,"area":"lr"},{"id":"2603.26556","title":"When Perplexity Lies: Generation-Focused Distillation of Hybrid Sequence Models","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2604.07658","title":"Optimal Decay Spectra for Linear Recurrences","created":"2026-04-08","cited_by_count":1,"area":"ssm"},{"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":"2605.12770","title":"WriteSAE: Sparse Autoencoders for Recurrent State","created":"2026-05-12","cited_by_count":1,"area":"ssm"},{"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":"2605.21070","title":"Towards Understanding Self-Pretraining for Sequence Classification","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2605.25969","title":"Triplet-Block Diffusion RWKV","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2605.29453","title":"Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs","created":"2026-05-28","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":"2606.20936","title":"Comparing Transformers and Hybrid Models at the Token Level","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2608.16844","title":"Proteus: Incremental Memory Activation for Long-Context Sequence Modeling","created":"2026-08-17","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":"2609.16183","title":"Anatomy of Associative Recall in Fixed-State Recurrences: A Matched-State Decomposition, an Interference Wall, and a Curriculum That Breaks It","created":"2026-09-14","cited_by_count":1,"area":"ssm"},{"id":"2504.03289","title":"RWKVTTS: Yet another TTS based on RWKV-7","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2504.05097","title":"State Tuning: State-based Test-Time Scaling on RWKV-7","created":"2025-04-07","cited_by_count":0,"area":"lr"},{"id":"2504.08247","title":"Millions of States: Designing a Scalable MoE Architecture with RWKV-7 Meta-learner","created":"2025-04-11","cited_by_count":0,"area":"moe"},{"id":"2504.14260","title":"Cross-attention for State-based model RWKV-7","created":"2025-04-19","cited_by_count":0,"area":null},{"id":"2505.14505","title":"ModRWKV: Transformer Multimodality in Linear Time","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2506.14541","title":"Exploring Diffusion with Test-Time Training on Efficient Image Restoration","created":"2025-06-17","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":"2509.12267","title":"A Traditional Approach to Symbolic Piano Continuation","created":"2025-09-13","cited_by_count":0,"area":null},{"id":"2509.25223","title":"Enhancing Linear Attention with Residual Learning","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2512.15038","title":"LADY: Linear Attention for Autonomous Driving Efficiency without Transformers","created":"2025-12-17","cited_by_count":0,"area":"driving"},{"id":"2601.07861","title":"EmbeddingRWKV: State-Centric Retrieval with Reusable States","created":"2026-01-10","cited_by_count":0,"area":"rag"},{"id":"2601.19221","title":"DREAMSTATE: Diffusing States and Parameters for Recurrent Large Language Models","created":"2026-01-27","cited_by_count":0,"area":null}],"next_cursor":"100"}