{"total":57,"rows":[{"id":"2510.26692","title":"Kimi Linear: An Expressive, Efficient Attention Architecture","created":"2025-10-30","cited_by_count":196,"area":"deeprl"},{"id":"2511.07384","title":"Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence","created":"2025-11-10","cited_by_count":47,"area":"lr"},{"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":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22,"area":null},{"id":"2509.22067","title":"The Rogue Scalpel: Activation Steering Compromises LLM Safety","created":"2025-09-26","cited_by_count":21,"area":"safety"},{"id":"2510.19093","title":"Weight Decay may matter more than muP for Learning Rate Transfer in Practice","created":"2025-10-21","cited_by_count":20,"area":null},{"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":"2510.04800","title":"Hybrid Architectures for Language Models: Systematic Analysis and Design Insights","created":"2025-10-06","cited_by_count":14,"area":"ssm"},{"id":"2602.17004","title":"Arcee Trinity Large Technical Report","created":"2026-02-19","cited_by_count":11,"area":"moe"},{"id":"2510.03871","title":"Optimal Scaling Needs Optimal Norm","created":"2025-10-04","cited_by_count":8,"area":null},{"id":"2511.15927","title":"DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbone","created":"2025-11-19","cited_by_count":6,"area":"diffusion"},{"id":"2509.05276","title":"SpikingBrain: Spiking Brain-inspired Large Models","created":"2025-09-05","cited_by_count":5,"area":null},{"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":"2509.25049","title":"Efficient Hyperparameter Tuning via Trajectory Invariance Principle","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2510.09426","title":"KORMo: Korean Open Reasoning Model for Everyone","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"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":"2603.22473","title":"Component Ablation for Efficient Hybrid Language Model Architectures: Performance, Resilience, and Compression Implications","created":"2026-03-23","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":"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":"2607.01977","title":"OntoLearner: A Modular Python Library for Ontology Learning with Large Language Models","created":"2026-07-02","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":"2509.25380","title":"Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2601.04890","title":"Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2601.21000","title":"UrduBench: An Urdu Reasoning Benchmark using Contextually Ensembled Translations with Human-in-the-Loop","created":"2026-01-28","cited_by_count":2,"area":"lr"},{"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":"2604.01168","title":"S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models","created":"2026-04-01","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":"2605.05662","title":"XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity","created":"2026-05-07","cited_by_count":2,"area":"safety"},{"id":"2606.30562","title":"Morphing into Hybrid Attention Models","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2602.13033","title":"Buy versus Build an LLM: A Decision Framework for Governments","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2603.01691","title":"Building a Strong Instruction Language Model for a Less-Resourced Language","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.22325","title":"Hybrid Associative Memories","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2604.19877","title":"Super Apriel: One Checkpoint, Many Speeds","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.01106","title":"Component-Aware Self-Speculative Decoding in Hybrid Language Models","created":"2026-05-01","cited_by_count":1,"area":"inference"},{"id":"2606.16429","title":"Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation","created":"2026-06-15","cited_by_count":1,"area":"inference"},{"id":"2607.04969","title":"Train Smarter, Not Longer: Memorization-Guided Data Reuse for Efficient LLM Training","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2608.11247","title":"Conformity Mitigations in Large Language Models Lie on a Single Resistance-Receptivity Frontier","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2608.27370","title":"Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2608.29539","title":"LoGo: Token-Level Dynamic Local-Global Attention","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2609.29102","title":"ELF-REG: Scaling Continuous Diffusion Language Models to Reasoning Tasks","created":"2026-09-24","cited_by_count":1,"area":"lr"},{"id":"2601.13588","title":"TREX: Tokenizer Regression for Optimal Data Mixture","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2602.21144","title":"Scaling State-Space Models on Multiple GPUs with Tensor Parallelism","created":"2026-02-24","cited_by_count":0,"area":"ssm"},{"id":"2603.03508","title":"Raising Bars, Not Parameters: LilMoo Compact Language Model for Hindi","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2604.22127","title":"Where Should LoRA Go? Component-Type Placement in Hybrid Language Models","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.06028","title":"Multi-agent decision making: A Blackwell's informativeness approach","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"id":"2605.22880","title":"How Far Will They Go? Red-Teaming Online Influence with Large Language Models","created":"2026-05-20","cited_by_count":0,"area":"safety"},{"id":"2606.02332","title":"Forget Attention: Importance-Aware Attention Is All You Need","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2608.10010","title":"CurveFP: Co-Designing Numerical Representation and Product Arithmetic for Language Models","created":"2026-08-08","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":"2609.22169","title":"Monocultural Biases: Correlated biases in large language models lead to unequal systemic exclusion rates in hiring","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.27510","title":"Uncheatable Eval: Dynamic Compression-Based Evaluation of Language Models","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.28150","title":"Exact Feedback Is Not Control: Evaluating Text-based Closed-Loop Revision in LLMs","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.35378","title":"Multilinguality in Hybrid Attention LLMs","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.38712","title":"Staying on Task: Testing the Foundations of Long-Horizon Agent Reliability","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2609.39661","title":"The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01172","title":"Learning Rate Transfer for Hybrid Transformer-SSM Architectures","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.13895","title":"Task Context Shapes Component Roles in Language Models","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}