{"total":60,"rows":[{"id":"2412.06464","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","created":"2024-12-09","cited_by_count":532,"area":null},{"id":"2603.15569","title":"Mamba-3: Improved Sequence Modeling using State Space Principles","created":"2026-03-16","cited_by_count":89,"area":"lr"},{"id":"2409.07146","title":"Gated Slot Attention for Efficient Linear-Time Sequence Modeling","created":"2024-09-11","cited_by_count":76,"area":null},{"id":"2412.10319","title":"SCBench: A KV Cache-Centric Analysis of Long-Context Methods","created":"2024-12-13","cited_by_count":60,"area":"inference"},{"id":"2407.14207","title":"Longhorn: State Space Models are Amortized Online Learners","created":"2024-07-19","cited_by_count":59,"area":"ssm"},{"id":"2410.05355","title":"Falcon Mamba: The First Competitive Attention-free 7B Language Model","created":"2024-10-07","cited_by_count":46,"area":"ssm"},{"id":"2512.17351","title":"Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers","created":"2025-12-19","cited_by_count":33,"area":null},{"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":"2512.20569","title":"Distilling to Hybrid Attention Models via KL-Guided Layer Selection","created":"2025-12-23","cited_by_count":20,"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":"2412.13328","title":"Expansion Span: Combining Fading Memory and Retrieval in Hybrid State Space Models","created":"2024-12-17","cited_by_count":11,"area":null},{"id":"2604.21100","title":"Preconditioned DeltaNet: Curvature-aware Sequence Modeling for Linear Recurrences","created":"2026-04-22","cited_by_count":7,"area":null},{"id":"2504.03101","title":"Single-Pass Document Scanning for Question Answering","created":"2025-04-04","cited_by_count":6,"area":null},{"id":"2602.04852","title":"On State Reduction in Linear Attention","created":"2026-02-04","cited_by_count":6,"area":null},{"id":"2510.26912","title":"Understanding and Enhancing Mamba-Transformer Hybrids for Memory Recall and Language Modeling","created":"2025-10-30","cited_by_count":5,"area":"ssm"},{"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":"2603.26380","title":"Switch Attention: Towards Dynamic and Fine-grained Hybrid Transformers","created":"2026-03-27","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":"2410.15678","title":"Revealing and Mitigating the Local Pattern Shortcuts of Mamba","created":"2024-10-21","cited_by_count":3,"area":"ssm"},{"id":"2510.19861","title":"Some Attention is All You Need for Retrieval","created":"2025-10-21","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":"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":"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":"2510.26083","title":"Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism","created":"2025-10-30","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":"2608.02032","title":"DART: Decoded Attention over Recurrent States for Efficient Long-Context Sequence Modeling","created":"2026-08-03","cited_by_count":2,"area":"ssm"},{"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":"2411.01030","title":"Birdie: Advancing State Space Models with Reward-Driven Objectives and Curricula","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2508.19242","title":"Autoregressive Universal Video Segmentation Model","created":"2025-08-26","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":"2601.12598","title":"Dissecting Linear Recurrent Models: How Different Gating Strategies Drive Selectivity and Generalization","created":"2026-01-18","cited_by_count":1,"area":null},{"id":"2605.03953","title":"Transformers with Selective Access to Early Representations","created":"2026-05-05","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":"2605.28769","title":"Multi-Mixer Models: Flexible Sequence Modeling with Shared Representations","created":"2026-05-27","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":"2606.25342","title":"Lifelong In-Context Learning with Transformers Requires Parametric Forms of Attention","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2608.21308","title":"Rethinking Expressivity and Efficiency in Test-Time Training","created":"2026-08-21","cited_by_count":1,"area":"lr"},{"id":"2608.29539","title":"LoGo: Token-Level Dynamic Local-Global Attention","created":"2026-08-30","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":"2502.20726","title":"Retrieval Backward Attention without Additional Training: Enhance Embeddings of Large Language Models via Repetition","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2506.15480","title":"Instruction Tuning with and without Context: Behavioral Shifts and Downstream Impact","created":"2025-06-18","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":"2606.08804","title":"Q-Delta: Beyond Key-Value Associative State Evolution","created":"2026-06-07","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":"2607.01792","title":"PARTREP: Learning What to Repeat for Decoder-only LLMs","created":"2026-07-02","cited_by_count":0,"area":"inference"},{"id":"2608.17896","title":"Dynamic Compression in Recurrent Networks","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.31036","title":"Normalized Low-Rank Adaptation","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.00103","title":"Good Memory Has ECC: Evaluating the Memory of Vision-Language Models Beyond Accuracy","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"id":"2609.31093","title":"Block Sparse Attention with Log-Linear Complexity","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32486","title":"Elastic Selective Spectral Hybrids for Train-Once, Export-Many Budgeted Inference","created":"2026-09-26","cited_by_count":0,"area":"ssm"},{"id":"2609.36259","title":"CyFA: Linear Sequence Modeling with Relative-Time-Partitioned Memory","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36314","title":"Fractional State Space Transition for Long Sequence Modeling","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.39034","title":"Switching Linear Attention","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39406","title":"Inferring Causal Relations between Two Sequences of Events with Language Models","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02816","title":"Gated Slot Attention-2: Two-Sided Associative Memory Correction in Linear Attention","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.06750","title":"Balancing Memory Pathways: Analyzing and Improving Memory Utilization in Hybrid LMs","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.15709","title":"Preserving Updates in Low-Bit Recurrent State Quantization","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.15715","title":"History Replays Itself: Unleashing Long-Context Capability in Linear Attention","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}