{"total":99,"rows":[{"id":"2412.06464","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","created":"2024-12-09","cited_by_count":532,"area":null},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328,"area":"lr"},{"id":"2505.06708","title":"Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free","created":"2025-05-10","cited_by_count":283,"area":"moe"},{"id":"2506.02153","title":"Small Language Models are the Future of Agentic AI","created":"2025-06-02","cited_by_count":270,"area":"agents"},{"id":"2510.26692","title":"Kimi Linear: An Expressive, Efficient Attention Architecture","created":"2025-10-30","cited_by_count":196,"area":"deeprl"},{"id":"2504.16053","title":"LongMamba: Enhancing Mamba's Long Context Capabilities via Training-Free Receptive Field Enlargement","created":"2025-04-22","cited_by_count":42,"area":"ssm"},{"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":"2503.01496","title":"Liger: Linearizing Large Language Models to Gated Recurrent Structures","created":"2025-03-03","cited_by_count":33,"area":null},{"id":"2506.08889","title":"SeerAttention-R: Sparse Attention Adaptation for Long Reasoning","created":"2025-06-10","cited_by_count":30,"area":"lr"},{"id":"2502.11569","title":"Towards Reasoning Ability of Small Language Models","created":"2025-02-17","cited_by_count":29,"area":"lr"},{"id":"2603.05498","title":"The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks","created":"2026-03-05","cited_by_count":27,"area":null},{"id":"2503.18292","title":"Jenga: Effective Memory Management for Serving LLM with Heterogeneity","created":"2025-03-24","cited_by_count":25,"area":"inference"},{"id":"2601.22966","title":"A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training","created":"2026-01-30","cited_by_count":23,"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":"2505.17272","title":"Zebra-Llama: Towards Extremely Efficient Hybrid Models","created":"2025-05-22","cited_by_count":18,"area":"inference"},{"id":"2503.18893","title":"xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction","created":"2025-03-24","cited_by_count":16,"area":"inference"},{"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":"2505.07460","title":"A Survey on Collaborative Mechanisms Between Large and Small Language Models","created":"2025-05-12","cited_by_count":14,"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":"2601.02346","title":"Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling","created":"2026-01-05","cited_by_count":13,"area":"lr"},{"id":"2605.12357","title":"$\\delta$-mem: Efficient Online Memory for Large Language Models","created":"2026-05-12","cited_by_count":13,"area":null},{"id":"2505.23666","title":"LoLA: Low-Rank Linear Attention With Sparse Caching","created":"2025-05-29","cited_by_count":12,"area":null},{"id":"2506.00744","title":"Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers","created":"2025-05-31","cited_by_count":12,"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":"2601.14243","title":"Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow","created":"2026-01-20","cited_by_count":11,"area":"lr"},{"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":"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":"2604.24432","title":"Kwai Summary Attention Technical Report","created":"2026-04-27","cited_by_count":7,"area":"lr"},{"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":"2503.22913","title":"Resona: Improving Context Copying in Linear Recurrence Models with Retrieval","created":"2025-03-28","cited_by_count":5,"area":null},{"id":"2506.06579","title":"Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques","created":"2025-06-06","cited_by_count":5,"area":null},{"id":"2506.09613","title":"SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot","created":"2025-06-11","cited_by_count":5,"area":"ssm"},{"id":"2507.00449","title":"Overcoming Long-Context Limitations of State-Space Models via Context-Dependent Sparse Attention","created":"2025-07-01","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":"2605.15871","title":"Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design","created":"2026-05-15","cited_by_count":5,"area":"agents"},{"id":"2503.12167","title":"PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing","created":"2025-03-15","cited_by_count":4,"area":null},{"id":"2506.18145","title":"Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection","created":"2025-06-22","cited_by_count":4,"area":"moe"},{"id":"2511.16595","title":"TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding","created":"2025-11-20","cited_by_count":4,"area":"mllm"},{"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":"2607.25380","title":"Memory for Large Language Models","created":"2026-07-28","cited_by_count":4,"area":null},{"id":"2505.03320","title":"Recall with Reasoning: Chain-of-Thought Distillation for Mamba's Long-Context Memory and Extrapolation","created":"2025-05-06","cited_by_count":3,"area":"lr"},{"id":"2507.04416","title":"RAT: Bridging RNN Efficiency and Attention Accuracy via Chunk-based Sequence Modeling","created":"2025-07-06","cited_by_count":3,"area":null},{"id":"2601.22379","title":"SPLA: Block Sparse Plus Linear Attention for Long Context Modeling","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2602.03681","title":"Neural Attention Search Linear: Towards Adaptive Token-Level Hybrid Attention Models","created":"2026-02-03","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":"2603.15590","title":"Effective Distillation to Hybrid xLSTM Architectures","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2603.18017","title":"Frayed RoPE and Long Inputs: A Geometric Perspective","created":"2026-02-24","cited_by_count":3,"area":null},{"id":"2606.07464","title":"Planning-aligned Token Compression for Long-Context Autonomous Driving","created":"2026-06-05","cited_by_count":3,"area":"driving"},{"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":"2501.05465","title":"Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)","created":"2025-01-03","cited_by_count":2,"area":null},{"id":"2502.21309","title":"Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling","created":"2025-02-28","cited_by_count":2,"area":"lr"},{"id":"2504.19191","title":"WuNeng: Hybrid State with Attention","created":"2025-04-27","cited_by_count":2,"area":"inference"},{"id":"2507.06204","title":"Differential Mamba","created":"2025-07-08","cited_by_count":2,"area":"ssm"},{"id":"2509.04897","title":"PLaMo 2 Technical Report","created":"2025-09-05","cited_by_count":2,"area":null},{"id":"2510.00258","title":"Delayed Attention Training Improves Length Generalization in Transformer--RNN Hybrids","created":"2025-09-30","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":"2511.02651","title":"Apriel-H1: Towards Efficient Enterprise Reasoning Models","created":"2025-11-04","cited_by_count":2,"area":"lr"},{"id":"2601.01972","title":"Hidden State Poisoning Attacks against Mamba-based Language Models","created":"2026-01-05","cited_by_count":2,"area":"ssm"},{"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":"2604.13440","title":"A KL Lens on Quantization: Fast, Forward-Only Sensitivity for Mixed-Precision SSM-Transformer Models","created":"2026-04-15","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":"2606.31830","title":"PriorEye: Geospatial Visual Priors for End-to-End Autonomous Driving","created":"2026-06-30","cited_by_count":2,"area":"driving"},{"id":"2507.12442","title":"Characterizing State Space Model and Hybrid Language Model Performance with Long Context","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2509.00141","title":"Scaling Legal AI: Benchmarking Mamba and Transformers for Statutory Classification and Case Law Retrieval","created":"2025-08-29","cited_by_count":1,"area":null},{"id":"2509.04459","title":"Uncertainty-Aware Collaborative System of Large and Small Models for Multimodal Sentiment Analysis","created":"2025-08-27","cited_by_count":1,"area":null},{"id":"2601.14549","title":"QMC: Efficient SLM Edge Inference via Outlier-Aware Quantization and Emergent Memories Co-Design","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2603.02874","title":"Retrievit: In-context Retrieval Capabilities of Transformers, State Space Models, and Hybrid Architectures","created":"2026-03-03","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":"2603.12342","title":"MamTra: A Hybrid Mamba-Transformer Backbone for Speech Synthesis","created":"2026-03-12","cited_by_count":1,"area":"ssm"},{"id":"2603.22325","title":"Hybrid Associative Memories","created":"2026-03-20","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":"2607.06523","title":"DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression","created":"2026-07-07","cited_by_count":1,"area":"inference"},{"id":"2608.29539","title":"LoGo: Token-Level Dynamic Local-Global Attention","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2503.11373","title":"Exploring Performance-Complexity Trade-Offs in Sound Event Detection Models","created":"2025-03-14","cited_by_count":0,"area":null},{"id":"2505.19472","title":"Balancing Computation Load and Representation Expressivity in Parallel Hybrid Neural Networks","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2507.09378","title":"Context-Aware Regularization with Markovian Integration for Attention-Based Nucleotide Analysis","created":"2025-07-12","cited_by_count":0,"area":null},{"id":"2508.05199","title":"EvoGraph: Hybrid Directed Graph Evolution toward Software 3.0","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2509.25155","title":"Context-Driven Performance Modeling for Causal Inference Operators on Neural Processing Units","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2512.07884","title":"GSPN-2: Efficient Parallel Sequence Modeling","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2603.12206","title":"CLASP: Defending Hybrid Large Language Models Against Hidden State Poisoning Attacks","created":"2026-03-12","cited_by_count":0,"area":"ssm"},{"id":"2604.03263","title":"LPC-SM: Local Predictive Coding and Sparse Memory for Long-Context Language Modeling","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2605.10643","title":"A Single-Layer Model Can Do Language Modeling","created":"2026-05-11","cited_by_count":0,"area":"ssm"},{"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":"2606.02332","title":"Forget Attention: Importance-Aware Attention Is All You Need","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.06519","title":"FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference","created":"2026-07-07","cited_by_count":0,"area":"inference"},{"id":"2607.15271","title":"Online Neural Space Time Memory for Dynamic Novel View Synthesis","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.22613","title":"NOVA: Technology-Architecture Co-Design of Near-Memory Processing for Attention-SSM-MoE Hybrid LLM Inference","created":"2026-08-23","cited_by_count":0,"area":"moe"},{"id":"2609.28006","title":"Shared Global KV with Layer-Specific Local History","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.29397","title":"Baseline Shape Decides the Verdict: A Controlled Re-Examination of Ternary Language Models at 60K Parameters","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.29618","title":"An Exploratory Ablation of a Small MLA--SSM Hybrid Language Model","created":"2026-08-28","cited_by_count":0,"area":"moe"},{"id":"2609.31947","title":"On-Policy Attention Linearization","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2610.01172","title":"Learning Rate Transfer for Hybrid Transformer-SSM Architectures","created":"2026-10-01","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":"2610.10114","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":"2610.13735","title":"Orthros: Phase-Aware Heterogeneous Attention for Efficient Transformers","created":"2026-10-09","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"},{"id":"2610.19709","title":"Beyond State Capacity: Why Retrieval Breaks in Mamba","created":"2026-10-14","cited_by_count":0,"area":"ssm"}],"next_cursor":null}