{"total":67,"rows":[{"id":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198,"area":"moe"},{"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":"2408.15237","title":"The Mamba in the Llama: Distilling and Accelerating Hybrid Models","created":"2024-08-27","cited_by_count":122,"area":"ssm"},{"id":"2409.07146","title":"Gated Slot Attention for Efficient Linear-Time Sequence Modeling","created":"2024-09-11","cited_by_count":76,"area":null},{"id":"2507.07955","title":"Dynamic Chunking for End-to-End Hierarchical Sequence Modeling","created":"2025-07-10","cited_by_count":72,"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":"2508.15884","title":"Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search","created":"2025-08-21","cited_by_count":41,"area":null},{"id":"2502.14458","title":"Llamba: Scaling Distilled Recurrent Models for Efficient Language Processing","created":"2025-02-20","cited_by_count":35,"area":"ssm"},{"id":"2503.01496","title":"Liger: Linearizing Large Language Models to Gated Recurrent Structures","created":"2025-03-03","cited_by_count":33,"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":"2502.20339","title":"Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners","created":"2025-02-27","cited_by_count":22,"area":"lr"},{"id":"2504.10449","title":"M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models","created":"2025-04-14","cited_by_count":21,"area":"lr"},{"id":"2504.19449","title":"R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference","created":"2025-04-28","cited_by_count":21,"area":"inference"},{"id":"2505.17272","title":"Zebra-Llama: Towards Extremely Efficient Hybrid Models","created":"2025-05-22","cited_by_count":18,"area":"inference"},{"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":"2504.18574","title":"Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism","created":"2025-04-22","cited_by_count":15,"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":"2510.04800","title":"Hybrid Architectures for Language Models: Systematic Analysis and Design Insights","created":"2025-10-06","cited_by_count":14,"area":"ssm"},{"id":"2410.13846","title":"LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation","created":"2024-10-17","cited_by_count":12,"area":"lr"},{"id":"2502.13145","title":"Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear Distillation","created":"2025-02-18","cited_by_count":12,"area":"mllm"},{"id":"2505.23666","title":"LoLA: Low-Rank Linear Attention With Sparse Caching","created":"2025-05-29","cited_by_count":12,"area":null},{"id":"2506.05340","title":"Exploring Diffusion Transformer Designs via Grafting","created":"2025-06-05","cited_by_count":12,"area":"diffusion"},{"id":"2411.19455","title":"Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models","created":"2024-11-29","cited_by_count":9,"area":null},{"id":"2503.18970","title":"Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State-Space Architectures from S4 to Mamba","created":"2025-03-22","cited_by_count":9,"area":"ssm"},{"id":"2512.15586","title":"Bolmo: Byteifying the Next Generation of Language Models","created":"2025-12-17","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":"2502.15130","title":"TransMamba: Fast Universal Architecture Adaption from Transformers to Mamba","created":"2025-02-21","cited_by_count":6,"area":"ssm"},{"id":"2502.15612","title":"LaTIM: Measuring Latent Token-to-Token Interactions in Mamba Models","created":"2025-02-21","cited_by_count":6,"area":"ssm"},{"id":"2502.18886","title":"On Pruning State-Space LLMs","created":"2025-02-26","cited_by_count":6,"area":null},{"id":"2503.13440","title":"MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling","created":"2025-03-17","cited_by_count":6,"area":"mllm"},{"id":"2602.11374","title":"Retrieval-Aware Distillation for Transformer-SSM Hybrids","created":"2026-02-11","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":"2504.00037","title":"ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models","created":"2025-03-30","cited_by_count":5,"area":null},{"id":"2503.11132","title":"X-EcoMLA: Upcycling Pre-Trained Attention into MLA for Efficient and Extreme KV Compression","created":"2025-03-14","cited_by_count":4,"area":"inference"},{"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":"2411.15255","title":"OSMamba: Omnidirectional Spectral Mamba with Dual-Domain Prior Generator for Exposure Correction","created":"2024-11-22","cited_by_count":3,"area":"diffusion"},{"id":"2506.09316","title":"On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention","created":"2025-06-11","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":"2604.14191","title":"Attention to Mamba: A Recipe for Cross-Architecture Distillation","created":"2026-04-01","cited_by_count":3,"area":"ssm"},{"id":"2605.02772","title":"Linearizing Vision Transformer with Test-Time Training","created":"2026-05-04","cited_by_count":3,"area":null},{"id":"2607.20062","title":"Solar Open 2 Technical Report","created":"2026-07-22","cited_by_count":3,"area":"agents"},{"id":"2410.06846","title":"Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity","created":"2024-10-09","cited_by_count":2,"area":"ssm"},{"id":"2503.11224","title":"Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2507.03340","title":"Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency","created":"2025-07-04","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":"2608.28444","title":"Sliding-window beats linear attention","created":"2026-08-28","cited_by_count":2,"area":"inference"},{"id":"2504.14366","title":"What Matters in Linearizing Language Models? A Comparative Study of Architecture, Scale, and Task Adaptation","created":"2025-04-19","cited_by_count":1,"area":null},{"id":"2511.00576","title":"FlashEVA: Accelerating LLM inference via Efficient Attention","created":"2025-11-01","cited_by_count":1,"area":null},{"id":"2511.05560","title":"Sample-Efficient Language Modeling with Linear Attention and Lightweight Enhancements","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2603.12342","title":"MamTra: A Hybrid Mamba-Transformer Backbone for Speech Synthesis","created":"2026-03-12","cited_by_count":1,"area":"ssm"},{"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":"2606.12364","title":"On Subquadratic Architectures: From Applications to Principles","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.21562","title":"Compressing History into Memory: Distilling Transformers into Recurrent Transformers","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2503.18565","title":"Distil-xLSTM: Learning Attention Mechanisms through Recurrent Structures","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2506.12149","title":"Maximally-Informative Retrieval for State Space Model Generation","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2510.02361","title":"ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2512.04198","title":"Network of Theseus (like the ship)","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2512.12744","title":"Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity","created":"2025-12-14","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":"2605.17093","title":"HEED: Density-Weighted Residual Alignment for Hybrid Vision-Language Model Distillation","created":"2026-05-16","cited_by_count":0,"area":"mllm"},{"id":"2605.26099","title":"Do Language Models Need Sleep? Offline Recurrence for Improved Online Inference","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.19867","title":"PSCT-Net: Geometry-Aware Pediatric Skull CT Reconstruction via Differentiable Back-Projection and Attention-Guided Refinement","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2609.26590","title":"GTR: Gated Token Recurrence for Efficient Dense Prediction","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.31947","title":"On-Policy Attention Linearization","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.39034","title":"Switching Linear Attention","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.11214","title":"Bridging KV-Cache Quantization and Linear Attention: From Theory to Pretrained Weight Migration","created":"2026-10-08","cited_by_count":0,"area":"inference"},{"id":"2610.19210","title":"Titan-Llama: Retrofitting Pre-trained LLMs with External Neural Memory Modules","created":"2026-10-13","cited_by_count":0,"area":"inference"}],"next_cursor":null}