{"total":43,"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":"2607.05722","title":"Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding","created":"2026-07-07","cited_by_count":24,"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":"2511.18890","title":"Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models","created":"2025-11-24","cited_by_count":15,"area":null},{"id":"2601.22076","title":"Where Do the Joules Go? Diagnosing Inference Energy Consumption","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2606.01774","title":"FLARE: Diffusion for Hybrid Language Model","created":"2026-06-01","cited_by_count":6,"area":null},{"id":"2605.08301","title":"Priming: Hybrid State Space Models From Pre-trained Transformers","created":"2026-05-08","cited_by_count":5,"area":null},{"id":"2604.09258","title":"Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima","created":"2026-04-10","cited_by_count":4,"area":null},{"id":"2604.22782","title":"Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing","created":"2026-04-03","cited_by_count":4,"area":null},{"id":"2609.21967","title":"NemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilities","created":"2026-09-18","cited_by_count":4,"area":null},{"id":"2509.21091","title":"Best-of-$\\infty$ -- Asymptotic Performance of Test-Time LLM Ensembling","created":"2025-09-25","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":"2604.15180","title":"AdaSplash-2: Faster Differentiable Sparse Attention","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2608.03624","title":"LoopMTP: A looped transformer guided by latent multi-token prediction","created":"2026-08-04","cited_by_count":3,"area":null},{"id":"2602.00747","title":"Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training","created":"2026-01-31","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":"2605.01417","title":"Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2510.09389","title":"Design Principles for Sequence Models via Coefficient Dynamics","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2601.10457","title":"NSR-Boost: A Neuro-Symbolic Residual Boosting Framework for Industrial Legacy Models","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2602.09843","title":"Kelix Technical Report","created":"2026-02-10","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":"2603.16430","title":"EngGPT2: Sovereign, Efficient and Open Intelligence","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2607.07708","title":"Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2607.08665","title":"Resample or Reroute? Recoverable Stopping Debt Without Identified Action Selection","created":"2026-07-09","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":"2609.15759","title":"Enabling Streaming User Transcription in Full-Duplex Speech-to-Speech Models","created":"2026-09-14","cited_by_count":1,"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":"2603.26511","title":"AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2603.27164","title":"daVinci-LLM:Towards the Science of Pretraining","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2604.03361","title":"The limits of bio-molecular modeling with large language models : a cross-scale evaluation","created":"2026-04-03","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":"2607.16777","title":"JOR-Bench: Japanese Operations Research Benchmarks for Large Language Models","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2607.22468","title":"Learning to Prepare Molecular Ground States with Transformer Models","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.23525","title":"EarthVerse: Benchmarking Scientific Agents Across Dynamic Earth Systems and Natural Hazards","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.16501","title":"Beyond the Name: Demographic Leakage in De-Identified R\\'esum\\'es and Evaluation Artifacts in LLM Bias Audits","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.16540","title":"On the Importance of Gating: Memorization vs. In-Context Learning in State Space Models","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.32942","title":"The Key Handoff: Retrieval in Hybrid Language Models","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33047","title":"Cost-free Spectral Estimation for Adaptive Newton--Schulz in Matrix Optimizers","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.38274","title":"Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selection","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":"2610.03109","title":"Emergent Structure in the Marginal Attention Space of Language Models","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.15415","title":"Sensitivity or Criterion? Measuring and Moving When Language Models Act","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}