{"total":108,"rows":[{"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":"2511.11793","title":"MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling","created":"2025-11-14","cited_by_count":81,"area":"lr"},{"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":"2512.13607","title":"Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models","created":"2025-12-15","cited_by_count":48,"area":"lr"},{"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":"2510.00695","title":"HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policy","created":"2025-10-01","cited_by_count":46,"area":"vla"},{"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":"2512.14067","title":"Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed","created":"2025-12-16","cited_by_count":33,"area":"diffusion"},{"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":"2602.15014","title":"Scaling Beyond Masked Diffusion Language Models","created":"2026-02-16","cited_by_count":27,"area":"diffusion"},{"id":"2510.01265","title":"RLP: Reinforcement as a Pretraining Objective","created":"2025-09-26","cited_by_count":25,"area":"lr"},{"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":"2601.20088","title":"Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery","created":"2026-01-27","cited_by_count":22,"area":"mllm"},{"id":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22,"area":null},{"id":"2510.04265","title":"Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation","created":"2025-10-05","cited_by_count":15,"area":"lr"},{"id":"2511.18890","title":"Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models","created":"2025-11-24","cited_by_count":15,"area":null},{"id":"2510.04800","title":"Hybrid Architectures for Language Models: Systematic Analysis and Design Insights","created":"2025-10-06","cited_by_count":14,"area":"ssm"},{"id":"2603.06638","title":"HEARTS: Benchmarking LLM Reasoning on Health Time Series","created":"2026-02-25","cited_by_count":11,"area":"lr"},{"id":"2606.06712","title":"Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation","created":"2026-06-04","cited_by_count":11,"area":"diffusion"},{"id":"2601.22076","title":"Where Do the Joules Go? Diagnosing Inference Energy Consumption","created":"2026-01-29","cited_by_count":10,"area":null},{"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":"2606.02091","title":"DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding","created":"2026-06-01","cited_by_count":9,"area":"inference"},{"id":"2508.18255","title":"Hermes 4 Technical Report","created":"2025-08-25","cited_by_count":8,"area":"lr"},{"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":"2601.15279","title":"MolecularIQ: Characterizing Chemical Reasoning Capabilities Through Symbolic Verification on Molecular Graphs","created":"2026-01-21","cited_by_count":8,"area":"lr"},{"id":"2605.08632","title":"PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding","created":"2026-05-09","cited_by_count":8,"area":"inference"},{"id":"2510.11713","title":"Are Large Reasoning Models Interruptible?","created":"2025-10-13","cited_by_count":7,"area":"lr"},{"id":"2511.16664","title":"Nemotron Elastic: Towards Efficient Many-in-One Reasoning LLMs","created":"2025-11-20","cited_by_count":6,"area":"lr"},{"id":"2512.20908","title":"Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation","created":"2025-12-24","cited_by_count":6,"area":"lr"},{"id":"2602.14763","title":"Unlocking Reasoning Capability on Machine Translation in Large Language Models","created":"2026-02-16","cited_by_count":6,"area":"lr"},{"id":"2605.06885","title":"Don't Retrain, Align: Adapting Autoregressive LMs to Diffusion LMs via Representation Alignment","created":"2026-05-07","cited_by_count":6,"area":"diffusion"},{"id":"2606.01774","title":"FLARE: Diffusion for Hybrid Language Model","created":"2026-06-01","cited_by_count":6,"area":null},{"id":"2608.04001","title":"Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility","created":"2026-08-04","cited_by_count":6,"area":"lr"},{"id":"2511.17384","title":"IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial Navigation","created":"2025-11-21","cited_by_count":5,"area":"lr"},{"id":"2605.08301","title":"Priming: Hybrid State Space Models From Pre-trained Transformers","created":"2026-05-08","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":"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":"2603.11881","title":"Bielik-Minitron-7B: Compressing Large Language Models via Structured Pruning and Knowledge Distillation for the Polish Language","created":"2026-03-12","cited_by_count":4,"area":"distill"},{"id":"2603.23638","title":"Can LLM Agents Be CFOs? Benchmarking Long-Horizon Resource Allocation in an Uncertain Enterprise Environment","created":"2026-03-24","cited_by_count":4,"area":"agents"},{"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":"2511.19333","title":"Learning to Reason: Training LLMs with GPT-OSS or DeepSeek R1 Reasoning Traces","created":"2025-11-24","cited_by_count":3,"area":"lr"},{"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":"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":"2605.07654","title":"Reliable Chain-of-Thought via Prefix Consistency","created":"2026-05-08","cited_by_count":3,"area":"lr"},{"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":"2608.13831","title":"VoiceChat-TTS: A Low-Latency Continuous Speech Synthesis Model for Interactive Agents","created":"2026-08-13","cited_by_count":3,"area":"agents"},{"id":"2511.02651","title":"Apriel-H1: Towards Efficient Enterprise Reasoning Models","created":"2025-11-04","cited_by_count":2,"area":"lr"},{"id":"2601.15394","title":"Memorization Dynamics in Knowledge Distillation for Language Models","created":"2026-01-21","cited_by_count":2,"area":"distill"},{"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":"2609.04531","title":"Distilled Continuous Diffusion Language Models Can Write Code in Few Steps---or One","created":"2026-09-03","cited_by_count":2,"area":"diffusion"},{"id":"2510.09389","title":"Design Principles for Sequence Models via Coefficient Dynamics","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2510.14516","title":"Vision Mamba for Permeability Prediction of Porous Media","created":"2025-10-16","cited_by_count":1,"area":"ssm"},{"id":"2510.20188","title":"TRUST: A Decentralized Framework for Auditing Large Language Model Reasoning","created":"2025-10-23","cited_by_count":1,"area":"lr"},{"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":"2603.10960","title":"Ranking Reasoning LLMs under Test-Time Scaling","created":"2026-03-11","cited_by_count":1,"area":"lr"},{"id":"2603.16430","title":"EngGPT2: Sovereign, Efficient and Open Intelligence","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2606.02001","title":"Scaling Agentic Capabilities via Grounded Interaction Synthesis","created":"2026-06-01","cited_by_count":1,"area":"agents"},{"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":"2607.09786","title":"Length Penalties Make Chain-of-Thought Less Monitorable","created":"2026-07-08","cited_by_count":1,"area":"lr"},{"id":"2607.20145","title":"SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD","created":"2026-07-22","cited_by_count":1,"area":"moe"},{"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":"2609.06469","title":"One Step, One Lead: Mitigating Higher-Order Interference in Multi-Domain Reinforcement Learning via Cross-Step Control","created":"2026-09-06","cited_by_count":1,"area":"lr"},{"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":"2601.01322","title":"LinMU: Multimodal Understanding Made Linear","created":"2026-01-04","cited_by_count":0,"area":"mllm"},{"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":"2602.05189","title":"Are Open-Weight LLMs Ready for Social Media Moderation? A Comparative Study on Bluesky","created":"2026-02-05","cited_by_count":0,"area":"safety"},{"id":"2602.11543","title":"Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm","created":"2026-02-12","cited_by_count":0,"area":"moe"},{"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":"2605.21299","title":"Tracing the ongoing emergence of human-like reasoning in Large Language Models","created":"2026-05-20","cited_by_count":0,"area":"lr"},{"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":"2605.31268","title":"Mellum2 Technical Report","created":"2026-05-29","cited_by_count":0,"area":"moe"},{"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":"2607.07740","title":"Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE","created":"2026-07-08","cited_by_count":0,"area":"rag"},{"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":"2609.00791","title":"Instella-MoE Technical Report","created":"2026-09-01","cited_by_count":0,"area":"moe"},{"id":"2609.09338","title":"Osprey: Target-agnostic Pre-training Makes Stronger Drafters in Speculative Decoding","created":"2026-09-08","cited_by_count":0,"area":"inference"},{"id":"2609.10445","title":"Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning","created":"2026-09-09","cited_by_count":0,"area":"lr"},{"id":"2609.11061","title":"Fork Where the Model Changes Its Mind: Belief-Shift Branching for Tree-Structured Reinforcement Learning","created":"2026-09-10","cited_by_count":0,"area":"lr"},{"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":"2609.20751","title":"dQwen3.5: Hybrid-Attention Diffusion Language Models","created":"2026-09-17","cited_by_count":0,"area":"diffusion"},{"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":"2609.34117","title":"SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving","created":"2026-09-28","cited_by_count":0,"area":"moe"},{"id":"2609.37170","title":"Interpolated Policy Distillation: A Controllable Continuum Between Off-Policy and On-Policy Distillation","created":"2026-09-29","cited_by_count":0,"area":"distill"}],"next_cursor":"100"}