{"total":100,"rows":[{"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":"2508.14444","title":"NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model","created":"2025-08-20","cited_by_count":108,"area":"lr"},{"id":"2512.20848","title":"Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2025-12-23","cited_by_count":104,"area":"lr"},{"id":"2603.15569","title":"Mamba-3: Improved Sequence Modeling using State Space Principles","created":"2026-03-16","cited_by_count":89,"area":"lr"},{"id":"2506.06266","title":"Cartridges: Lightweight and general-purpose long context representations via self-study","created":"2025-06-06","cited_by_count":86,"area":"inference"},{"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":"2506.17238","title":"Training a Scientific Reasoning Model for Chemistry","created":"2025-06-04","cited_by_count":56,"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":"2604.12374","title":"Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-04-14","cited_by_count":38,"area":"agents"},{"id":"2507.11407","title":"EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes","created":"2025-07-15","cited_by_count":32,"area":"lr"},{"id":"2504.13941","title":"Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning","created":"2025-04-15","cited_by_count":31,"area":"lr"},{"id":"2603.12201","title":"IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse","created":"2026-03-12","cited_by_count":31,"area":"agents"},{"id":"2510.03264","title":"Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data","created":"2025-09-26","cited_by_count":27,"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":"2510.23569","title":"EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT","created":"2025-10-27","cited_by_count":16,"area":"lr"},{"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":"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":"2509.24552","title":"Short window attention enables long-term memorization","created":"2025-09-29","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":"2512.08829","title":"InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models","created":"2025-12-09","cited_by_count":10,"area":"mllm"},{"id":"2602.03560","title":"HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache Sharing","created":"2026-02-03","cited_by_count":10,"area":"moe"},{"id":"2510.27055","title":"Detecting Data Contamination in LLMs via In-Context Learning","created":"2025-10-30","cited_by_count":8,"area":null},{"id":"2601.07226","title":"Lost in the Noise: How Reasoning Models Fail with Contextual Distractors","created":"2026-01-12","cited_by_count":8,"area":"lr"},{"id":"2603.05484","title":"Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline","created":"2026-03-05","cited_by_count":8,"area":"agents"},{"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":"2505.16322","title":"AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners","created":"2025-05-22","cited_by_count":6,"area":"lr"},{"id":"2511.15927","title":"DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbone","created":"2025-11-19","cited_by_count":6,"area":"diffusion"},{"id":"2511.16664","title":"Nemotron Elastic: Towards Efficient Many-in-One Reasoning LLMs","created":"2025-11-20","cited_by_count":6,"area":"lr"},{"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":"2507.20984","title":"SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment","created":"2025-07-28","cited_by_count":5,"area":"lr"},{"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":"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":"2505.22425","title":"Scaling Reasoning without Attention","created":"2025-05-28","cited_by_count":3,"area":"lr"},{"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":"2509.24118","title":"HyMaTE: A Hybrid Mamba and Transformer Model for EHR Representation Learning","created":"2025-09-28","cited_by_count":3,"area":"ssm"},{"id":"2601.22275","title":"VMonarch: Efficient Video Diffusion Transformers with Structured Attention","created":"2026-01-29","cited_by_count":3,"area":"diffusion"},{"id":"2603.15590","title":"Effective Distillation to Hybrid xLSTM Architectures","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2604.25578","title":"Marco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient Upcycling","created":"2026-04-28","cited_by_count":3,"area":"moe"},{"id":"2605.07182","title":"Star Elastic: Many-in-One Reasoning LLMs with Efficient Budget Control","created":"2026-05-08","cited_by_count":3,"area":"lr"},{"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":"2511.02651","title":"Apriel-H1: Towards Efficient Enterprise Reasoning Models","created":"2025-11-04","cited_by_count":2,"area":"lr"},{"id":"2512.09946","title":"ELANA: A Simple Energy and Latency Analyzer for LLMs","created":"2025-12-07","cited_by_count":2,"area":null},{"id":"2601.01972","title":"Hidden State Poisoning Attacks against Mamba-based Language Models","created":"2026-01-05","cited_by_count":2,"area":"ssm"},{"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":"2602.11937","title":"Extending Puzzle for Mixture-of-Experts Reasoning Models with Application to GPT-OSS Acceleration","created":"2026-02-12","cited_by_count":1,"area":"lr"},{"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":"2603.20578","title":"Context Cartography: Toward Structured Governance of Contextual Space in Large Language Model Systems","created":"2026-03-21","cited_by_count":1,"area":"lr"},{"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":"2607.09424","title":"A Sovereign, Open-Source Foundation Model for German and English","created":"2026-07-10","cited_by_count":1,"area":"moe"},{"id":"2608.05224","title":"Small Foundation Models of Human Cognition and Behaviour","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.17286","title":"Abra: Scaling Diffusion Image Training","created":"2026-08-18","cited_by_count":1,"area":"diffusion"},{"id":"2608.27882","title":"SOMTab: Set-Order Mamba for Efficient Tabular In-Context Learning","created":"2026-08-28","cited_by_count":1,"area":"ssm"},{"id":"2608.30310","title":"Tail-Replay: Escaping the Curse of Linear Attention in Prefix Caching for Hybrid LLMs","created":"2026-08-31","cited_by_count":1,"area":"inference"},{"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":"2602.09173","title":"$n$-Musketeers: Reinforcement Learning Shapes Collaboration Among Language Models","created":"2026-02-09","cited_by_count":0,"area":"lr"},{"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":"2603.06938","title":"Swimba: Switch Mamba Model Scales State Space Models","created":"2026-03-06","cited_by_count":0,"area":"moe"},{"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":"2604.08050","title":"ABMAMBA: Multimodal Large Language Model with Aligned Hierarchical Bidirectional Scan for Efficient Video Captioning","created":"2026-04-09","cited_by_count":0,"area":"mllm"},{"id":"2605.17093","title":"HEED: Density-Weighted Residual Alignment for Hybrid Vision-Language Model Distillation","created":"2026-05-16","cited_by_count":0,"area":"mllm"},{"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":"2606.11634","title":"Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"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":"2608.15943","title":"KV-Pipe: On the Relation Between KV Sharing and Pipeline Parallel Efficiency in LLMs","created":"2026-08-16","cited_by_count":0,"area":"inference"},{"id":"2608.17744","title":"Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See","created":"2026-08-18","cited_by_count":0,"area":"moe"},{"id":"2608.19395","title":"HYDRA: A Heterogeneous Chiplet DSE Framework for Serving Dynamic Hybrid LLM Workloads","created":"2026-08-19","cited_by_count":0,"area":"inference"},{"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":"2609.34049","title":"Thinking Outside the Box: Retention and Transmission of Information in Sliding-Window KV Inference","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"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":"2610.09051","title":"A Self-Pruning Transformer: Extreme KV-Cache Compression with Universal Attention","created":"2026-10-06","cited_by_count":0,"area":"inference"},{"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}