{"total":122,"rows":[{"id":"2410.17891","title":"Scaling Diffusion Language Models via Adaptation from Autoregressive Models","created":"2024-10-23","cited_by_count":274,"area":"diffusion"},{"id":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198,"area":"moe"},{"id":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146,"area":null},{"id":"2505.23884","title":"Test-Time Training Done Right","created":"2025-05-29","cited_by_count":130,"area":"diffusion"},{"id":"2409.02889","title":"LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture","created":"2024-09-04","cited_by_count":102,"area":"mllm"},{"id":"2409.07146","title":"Gated Slot Attention for Efficient Linear-Time Sequence Modeling","created":"2024-09-11","cited_by_count":76,"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":"2503.04130","title":"STORM: Token-Efficient Long Video Understanding for Multimodal LLMs","created":"2025-03-06","cited_by_count":49,"area":"mllm"},{"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":"2502.06975","title":"Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents","created":"2025-02-10","cited_by_count":36,"area":"agents"},{"id":"2502.14458","title":"Llamba: Scaling Distilled Recurrent Models for Efficient Language Processing","created":"2025-02-20","cited_by_count":35,"area":"ssm"},{"id":"2410.10254","title":"LoLCATs: On Low-Rank Linearizing of Large Language Models","created":"2024-10-14","cited_by_count":27,"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":"2502.19732","title":"Speculative Decoding and Beyond: An In-Depth Survey of Techniques","created":"2025-02-27","cited_by_count":23,"area":"inference"},{"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":"2512.20569","title":"Distilling to Hybrid Attention Models via KL-Guided Layer Selection","created":"2025-12-23","cited_by_count":20,"area":null},{"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":"2602.23361","title":"VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale","created":"2026-02-26","cited_by_count":18,"area":null},{"id":"2509.19633","title":"Mamba Modulation: On the Length Generalization of Mamba","created":"2025-09-23","cited_by_count":16,"area":"ssm"},{"id":"2509.24899","title":"Attention Surgery: An Efficient Recipe to Linearize Your Video Diffusion Transformer","created":"2025-09-29","cited_by_count":15,"area":"diffusion"},{"id":"2603.03251","title":"Speculative Speculative Decoding","created":"2026-03-03","cited_by_count":15,"area":"inference"},{"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":"2506.10915","title":"M4V: Multimodal Mamba for Efficient Text-to-Video Generation","created":"2025-06-12","cited_by_count":12,"area":"ssm"},{"id":"2510.07318","title":"Artificial Hippocampus Networks for Efficient Long-Context Modeling","created":"2025-10-08","cited_by_count":11,"area":null},{"id":"2412.14354","title":"State Space Models are Strong Text Rerankers","created":"2024-12-18","cited_by_count":10,"area":"ssm"},{"id":"2505.14969","title":"STree: Speculative Tree Decoding for Hybrid State-Space Models","created":"2025-05-20","cited_by_count":10,"area":"inference"},{"id":"2506.17121","title":"Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?","created":"2025-06-20","cited_by_count":10,"area":null},{"id":"2510.07019","title":"Native Hybrid Attention for Efficient Sequence Modeling","created":"2025-10-08","cited_by_count":10,"area":null},{"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":"2501.15570","title":"ARWKV: Pretrain is not what we need, an RNN-Attention-Based Language Model Born from Transformer","created":"2025-01-26","cited_by_count":9,"area":"safety"},{"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":"2508.01700","title":"DeepVIS: Bridging Natural Language and Data Visualization Through Step-wise Reasoning","created":"2025-08-03","cited_by_count":8,"area":"lr"},{"id":"2503.24067","title":"TransMamba: A Sequence-Level Hybrid Transformer-Mamba Language Model","created":"2025-03-31","cited_by_count":7,"area":"ssm"},{"id":"2601.04342","title":"ReHyAt: Recurrent Hybrid Attention for Video Diffusion Transformers","created":"2026-01-07","cited_by_count":7,"area":"diffusion"},{"id":"2502.15130","title":"TransMamba: Fast Universal Architecture Adaption from Transformers to Mamba","created":"2025-02-21","cited_by_count":6,"area":"ssm"},{"id":"2502.18886","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":"2507.09025","title":"Lizard: An Efficient Linearization Framework for Large Language Models","created":"2025-07-11","cited_by_count":6,"area":null},{"id":"2510.17196","title":"Understanding and Improving Length Generalization in Hierarchical Sparse Attention Models","created":"2025-10-20","cited_by_count":6,"area":null},{"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":"2509.05276","title":"SpikingBrain: Spiking Brain-inspired Large Models","created":"2025-09-05","cited_by_count":5,"area":null},{"id":"2509.19873","title":"SpecMamba: Accelerating Mamba Inference on FPGA with Speculative Decoding","created":"2025-09-24","cited_by_count":5,"area":"inference"},{"id":"2602.11761","title":"MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2603.17946","title":"CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention","created":"2026-03-18","cited_by_count":5,"area":"inference"},{"id":"2606.06479","title":"Pretraining Recurrent Networks without Recurrence","created":"2026-06-04","cited_by_count":5,"area":null},{"id":"2410.17477","title":"Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2502.01578","title":"ReGLA: Refining Gated Linear Attention","created":"2025-02-03","cited_by_count":4,"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":"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":"2607.14144","title":"The Capability Convergence Hypothesis: Capability from Access Structure, Not Scale","created":"2026-07-14","cited_by_count":4,"area":null},{"id":"2506.01206","title":"Mamba Drafters for Speculative Decoding","created":"2025-06-01","cited_by_count":3,"area":"ssm"},{"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":"2506.18999","title":"Diffusion Transformer-to-Mamba Distillation for High-Resolution Image Generation","created":"2025-06-23","cited_by_count":3,"area":"diffusion"},{"id":"2509.18467","title":"LAWCAT: Efficient Distillation from Quadratic to Linear Attention with Convolution across Tokens for Long Context Modeling","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2510.04595","title":"SpikingMamba: Towards Energy-Efficient Large Language Models via Knowledge Distillation from Mamba","created":"2025-10-06","cited_by_count":3,"area":"ssm"},{"id":"2510.10160","title":"SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation","created":"2025-10-11","cited_by_count":3,"area":"ssm"},{"id":"2601.11667","title":"Distill-then-Replace: Efficient Task-Specific Hybrid Attention Model Construction","created":"2026-01-16","cited_by_count":3,"area":null},{"id":"2602.06932","title":"When RL Meets Adaptive Speculative Training: A Unified Training-Serving System","created":"2026-02-06","cited_by_count":3,"area":"inference"},{"id":"2603.15590","title":"Effective Distillation to Hybrid xLSTM Architectures","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2603.17484","title":"Learning When to Attend: Conditional Memory Access for Long-Context LLMs","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2605.02772","title":"Linearizing Vision Transformer with Test-Time Training","created":"2026-05-04","cited_by_count":3,"area":null},{"id":"2607.06763","title":"Trees from Marginals: Autoregressive drafting with factorized priors","created":"2026-07-07","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":"2410.03292","title":"Demystifying the Token Dynamics of Deep Selective State Space Models","created":"2024-10-04","cited_by_count":2,"area":"ssm"},{"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":"2602.13680","title":"AllMem: A Memory-centric Recipe for Efficient Long-context Modeling","created":"2026-02-14","cited_by_count":2,"area":null},{"id":"2604.22575","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":"2606.30562","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":"2610.13778","title":"ReplaySSM: Cache SSM Inputs, Not State","created":"2026-10-09","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":"2505.11837","title":"On Membership Inference Attacks in Knowledge Distillation","created":"2025-05-17","cited_by_count":1,"area":"safety"},{"id":"2505.21077","title":"Efficient Large Language Model Inference with Neural Block Linearization","created":"2025-05-27","cited_by_count":1,"area":"inference"},{"id":"2510.12026","title":"Mamba Can Learn Low-Dimensional Targets In-Context via Test-Time Feature Learning","created":"2025-10-14","cited_by_count":1,"area":"ssm"},{"id":"2510.22881","title":"Offline Preference Optimization via Maximum Marginal Likelihood Estimation","created":"2025-10-27","cited_by_count":1,"area":"alignment"},{"id":"2511.00576","title":"FlashEVA: Accelerating LLM inference via Efficient Attention","created":"2025-11-01","cited_by_count":1,"area":null},{"id":"2601.20357","title":"TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs","created":"2026-01-28","cited_by_count":1,"area":"inference"},{"id":"2603.12342","title":"MamTra: A Hybrid Mamba-Transformer Backbone for Speech Synthesis","created":"2026-03-12","cited_by_count":1,"area":"ssm"},{"id":"2606.10820","title":"K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language Modeling","created":"2026-06-09","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":"2606.16429","title":"Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation","created":"2026-06-15","cited_by_count":1,"area":"inference"},{"id":"2608.22368","title":"DiD It in 87 Minutes: A Label-Free Softmax-to-Linear Adaptation of Vision Transformers for Object Detection","created":"2026-08-23","cited_by_count":1,"area":null},{"id":"2502.06189","title":"Multi-Level Decoupled Relational Distillation for Heterogeneous Architectures","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2505.21535","title":"FAR: Function-preserving Attention Replacement for IMC-friendly Inference","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2509.00935","title":"SCOUT: Toward Sub-Quadratic Attention via Segment Compression for Optimized Utility in Transformers","created":"2025-08-31","cited_by_count":0,"area":"ssm"},{"id":"2509.18691","title":"An overview of neural architectures for self-supervised audio representation learning from masked spectrograms","created":"2025-09-23","cited_by_count":0,"area":"ssm"},{"id":"2510.02361","title":"ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2510.09088","title":"MambaH-Fit: Rethinking Hyper-surface Fitting-based Point Cloud Normal Estimation via State Space Modelling","created":"2025-10-10","cited_by_count":0,"area":"ssm"},{"id":"2511.00315","title":"Language Modeling With Factorization Memory","created":"2025-10-31","cited_by_count":0,"area":"ssm"}],"next_cursor":"100"}