{"total":64,"rows":[{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336,"area":"ssm"},{"id":"2406.06484","title":"Parallelizing Linear Transformers with the Delta Rule over Sequence Length","created":"2024-06-10","cited_by_count":396,"area":null},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328,"area":"lr"},{"id":"2406.07522","title":"Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling","created":"2024-06-11","cited_by_count":174,"area":"ssm"},{"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":"2406.07933","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","created":"2024-06-12","cited_by_count":116,"area":"safety"},{"id":"2501.15089","title":"LongReason: A Synthetic Long-Context Reasoning Benchmark via Context Expansion","created":"2025-01-25","cited_by_count":50,"area":"lr"},{"id":"2405.11804","title":"(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts","created":"2024-05-20","cited_by_count":49,"area":"agents"},{"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":"2407.01527","title":"KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches","created":"2024-07-01","cited_by_count":42,"area":"inference"},{"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":"2507.06457","title":"A Systematic Analysis of Hybrid Linear Attention","created":"2025-07-08","cited_by_count":39,"area":null},{"id":"2411.19379","title":"Marconi: Prefix Caching for the Era of Hybrid LLMs","created":"2024-11-28","cited_by_count":31,"area":null},{"id":"2504.06225","title":"Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation","created":"2025-04-08","cited_by_count":28,"area":null},{"id":"2606.18206","title":"Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers","created":"2026-06-16","cited_by_count":28,"area":null},{"id":"2409.15156","title":"Rethinking Conventional Wisdom in Machine Learning: From Generalization to Scaling","created":"2024-09-23","cited_by_count":23,"area":"lr"},{"id":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22,"area":null},{"id":"2412.18603","title":"Long-Form Speech Generation with Spoken Language Models","created":"2024-12-24","cited_by_count":19,"area":null},{"id":"2503.13427","title":"xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference","created":"2025-03-17","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":"2407.12397","title":"Mamba-PTQ: Outlier Channels in Recurrent Large Language Models","created":"2024-07-17","cited_by_count":15,"area":"ssm"},{"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":"2505.23666","title":"LoLA: Low-Rank Linear Attention With Sparse Caching","created":"2025-05-29","cited_by_count":12,"area":null},{"id":"2409.11798","title":"The Factuality of Large Language Models in the Legal Domain","created":"2024-09-18","cited_by_count":10,"area":null},{"id":"2407.08112","title":"How Well Can a Long Sequence Model Model Long Sequences? Comparing Architechtural Inductive Biases on Long-Context Abilities","created":"2024-07-11","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":"2410.06718","title":"MatMamba: A Matryoshka State Space Model","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2604.24432","title":"Kwai Summary Attention Technical Report","created":"2026-04-27","cited_by_count":7,"area":"lr"},{"id":"2410.06577","title":"Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2505.07793","title":"Overflow Prevention Enhances Long-Context Recurrent LLMs","created":"2025-05-12","cited_by_count":6,"area":"ssm"},{"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":"2502.21112","title":"Optimizing Large Language Models for ESG Activity Detection in Financial Texts","created":"2025-02-28","cited_by_count":5,"area":null},{"id":"2602.10097","title":"Step-resolved data attribution for looped transformers","created":"2026-02-10","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":"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":"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":"2407.09503","title":"PARSE-Ego4D: Personal Action Recommendation Suggestions for Egocentric Videos","created":"2024-06-14","cited_by_count":3,"area":null},{"id":"2503.06519","title":"Can Small Language Models Reliably Resist Jailbreak Attacks? A Comprehensive Evaluation","created":"2025-03-09","cited_by_count":3,"area":"safety"},{"id":"2510.19861","title":"Some Attention is All You Need for Retrieval","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2406.00894","title":"Pretrained Hybrids with MAD Skills","created":"2024-06-02","cited_by_count":2,"area":null},{"id":"2605.18826","title":"The Routing and Filtering Structure of Attention","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2406.18125","title":"ResumeAtlas: Revisiting Resume Classification with Large-Scale Datasets and Large Language Models","created":"2024-06-26","cited_by_count":1,"area":null},{"id":"2411.08909","title":"Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers","created":"2024-10-29","cited_by_count":1,"area":"ssm"},{"id":"2508.07185","title":"DySK-Attn: A Framework for Efficient, Real-Time Knowledge Updating in Large Language Models via Dynamic Sparse Knowledge Attention","created":"2025-08-10","cited_by_count":1,"area":null},{"id":"2509.04226","title":"LISM: Long-range Integrative State space Models via Input-Latent State Interactions","created":"2025-09-04","cited_by_count":1,"area":"ssm"},{"id":"2509.12720","title":"HistoryBankQA: Multilingual Temporal Question Answering on Historical Events","created":"2025-09-16","cited_by_count":1,"area":"lr"},{"id":"2604.03199","title":"Learning the Signature of Memorization in Autoregressive Language Models","created":"2026-04-03","cited_by_count":1,"area":"safety"},{"id":"2608.22876","title":"The Mask Is Not the Model: Auditing Prefix Invariance in Attention, State-Space, and Hybrid Sequence Models","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2406.01424","title":"Universal In-Context Approximation By Prompting Fully Recurrent Models","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2406.06571","title":"SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2510.02401","title":"Linear RNNs for autoregressive generation of long music samples","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2605.05488","title":"A Robust In-Context Model for Conservation Laws: Injecting Context into Flux Neural Operators via Recurrent Vision Transformers","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.22416","title":"Asymmetric Virtual Memory Paging for Hybrid Mamba-Transformer Inference","created":"2026-05-21","cited_by_count":0,"area":"ssm"},{"id":"2606.00930","title":"A Circuit, Not The Circuit: Non-Unique Causal Localisation of the Mamba-2 State Sink","created":"2026-05-30","cited_by_count":0,"area":"ssm"},{"id":"2606.02332","title":"Forget Attention: Importance-Aware Attention Is All You Need","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.21000","title":"Naju: A Native Discrete State-Space Model with Independent Retention and Writing for Long-Sequence Memory","created":"2026-07-23","cited_by_count":0,"area":"ssm"},{"id":"2609.20269","title":"Placement Is Free, Composition Is Not: The Latin Square as a Provably-Balanced Construction for Heterogeneous Sequence-Mixer Stacks","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.21139","title":"TinyCeNN-LM: Quality-Gated Conversion of Pretrained Attention with CeNN-Inspired Cellular-Recurrent Layers","created":"2026-09-17","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":"2609.39082","title":"Shared Phase and Retention Control for Efficient Adaptive Spectral Recurrence","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.10114","title":"Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.10118","title":"YANchor-4B: Effective Long-Horizon Reasoning in O(N) Time with O(1) Memory","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.18654","title":"Kwai Summary Attention V2 Technical Report","created":"2026-10-13","cited_by_count":0,"area":"inference"}],"next_cursor":null}