{"total":24,"rows":[{"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":"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":"2509.25182","title":"DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder","created":"2025-09-29","cited_by_count":16,"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":"2510.00379","title":"Composer: A Search Framework for Hybrid Neural Architecture Design","created":"2025-10-01","cited_by_count":7,"area":null},{"id":"2512.03383","title":"UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs","created":"2025-12-03","cited_by_count":6,"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":"2605.05838","title":"MDN: Parallelizing Stepwise Momentum for Delta Linear Attention","created":"2026-05-07","cited_by_count":4,"area":null},{"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":"2602.13215","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":"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":"2603.15954","title":"MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment","created":"2026-03-16","cited_by_count":1,"area":null},{"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":"2511.17205","title":"E$^3$-Pruner: Towards Efficient, Economical, and Effective Layer Pruning for Large Language Models","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2604.22050","title":"LayerBoost: Layer-Aware Attention Reduction for Efficient LLMs","created":"2026-04-23","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":"2605.17653","title":"LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models","created":"2026-05-17","cited_by_count":0,"area":null},{"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":"2605.26636","title":"JetViT: Efficient High-Resolution Vision Transformer with Post-Training Attention Search","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.03825","title":"Dynamic Short Convolutions Improve Transformers","created":"2026-06-02","cited_by_count":0,"area":null},{"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":"2610.14754","title":"GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMs","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}