{"total":52,"rows":[{"id":"2509.25149","title":"Pretraining Large Language Models with NVFP4","created":"2025-09-29","cited_by_count":76,"area":null},{"id":"2512.20856","title":"NVIDIA Nemotron 3: Efficient and Open Intelligence","created":"2025-12-24","cited_by_count":65,"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":"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":"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":"2509.24552","title":"Short window attention enables long-term memorization","created":"2025-09-29","cited_by_count":11,"area":null},{"id":"2510.27055","title":"Detecting Data Contamination in LLMs via In-Context Learning","created":"2025-10-30","cited_by_count":8,"area":null},{"id":"2504.11409","title":"Minitron-SSM: Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning","created":"2025-04-15","cited_by_count":7,"area":null},{"id":"2506.14123","title":"Sampling from Your Language Model One Byte at a Time","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2507.10178","title":"Pimba: A Processing-in-Memory Acceleration for Post-Transformer Large Language Model Serving","created":"2025-07-14","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":"2602.04852","title":"On State Reduction in Linear Attention","created":"2026-02-04","cited_by_count":6,"area":null},{"id":"2606.01774","title":"FLARE: Diffusion for Hybrid Language Model","created":"2026-06-01","cited_by_count":6,"area":null},{"id":"2607.20548","title":"SOAP, Muon, and Beyond: Pushing LLM Pretraining Scales","created":"2026-07-13","cited_by_count":6,"area":null},{"id":"2509.05276","title":"SpikingBrain: Spiking Brain-inspired Large Models","created":"2025-09-05","cited_by_count":5,"area":null},{"id":"2510.14826","title":"To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2603.08859","title":"Expressivity-Efficiency Tradeoffs for Hybrid Sequence Models","created":"2026-03-09","cited_by_count":4,"area":null},{"id":"2605.18753","title":"DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention","created":"2026-05-18","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":"2506.09507","title":"TransXSSM: A Hybrid Transformer State Space Model with Unified Rotary Position Embedding","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2507.03117","title":"BLaST: High Performance Inference and Pretraining using BLock Sparse Transformers","created":"2025-07-03","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":"2509.23722","title":"OctoPipe: Reducing Pipeline Bubbles for Heterogeneous Models via Co-Optimizing Partitioning, Placement, and Scheduling","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2512.09946","title":"ELANA: A Simple Energy and Latency Analyzer for LLMs","created":"2025-12-07","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":"2608.12149","title":"Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2609.02846","title":"UE5M3 FP4 Block Scaling for Stable Language Model Pretraining","created":"2026-09-02","cited_by_count":2,"area":null},{"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":"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":"2605.05066","title":"The Impossibility Triangle of Long-Context Modeling","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.07075","title":"ModelLens: Finding the Best for Your Task from Myriads of Models","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2608.05224","title":"Small Foundation Models of Human Cognition and Behaviour","created":"2026-08-05","cited_by_count":1,"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":"2511.23347","title":"Distributed Dynamic Associative Memory via Online Convex Optimization","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2601.17334","title":"Power-based Partial Attention: Bridging Linear-Complexity and Full Attention","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2601.18401","title":"Superlinear Multi-Step Attention","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2603.03517","title":"MMAI Gym for Science: Training Liquid Foundation Models for Drug Discovery","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2605.19150","title":"Flash PD-SSM: Memory-Optimized Structured Sparse State-Space Models","created":"2026-05-18","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":"2607.25529","title":"Are the High-weight Neurons the Important Ones in Image Classification Neural Networks?","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.33477","title":"Just Let Linear States Forget the Distant Past: Prefix Caching via Suffix Replay for Hybrid LLMs","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.37852","title":"Delta-Matching: Closing the Final Gap of Native 8-bit Training for LLMs","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38166","title":"LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization","created":"2026-09-29","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":"2610.01172","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":"2610.14754","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},{"id":"2610.15715","title":"History Replays Itself: Unleashing Long-Context Capability in Linear Attention","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}