{"total":104,"rows":[{"id":"2606.15007","title":"Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-06-12","cited_by_count":42,"area":"lr"},{"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":"2603.20278","title":"OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis","created":"2026-03-17","cited_by_count":37,"area":"agents"},{"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":"2601.09088","title":"Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning","created":"2026-01-14","cited_by_count":17,"area":"lr"},{"id":"2602.12566","title":"To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2602.22603","title":"SideQuest: Model-Driven KV Cache Management for Long-Horizon Agentic Reasoning","created":"2026-02-26","cited_by_count":11,"area":"lr"},{"id":"2604.15039","title":"Prefill-as-a-Service: KVCache of Next-Generation Models Could Go Cross-Datacenter","created":"2026-04-16","cited_by_count":11,"area":"inference"},{"id":"2604.16027","title":"Where does output diversity collapse in post-training?","created":"2026-04-17","cited_by_count":11,"area":null},{"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":"2607.16051","title":"Loop the Loopies!","created":"2026-07-17","cited_by_count":8,"area":"moe"},{"id":"2603.00540","title":"LOGIGEN: Logic-Driven Generation of Verifiable Agentic Tasks","created":"2026-02-28","cited_by_count":7,"area":"agents"},{"id":"2606.01774","title":"FLARE: Diffusion for Hybrid Language Model","created":"2026-06-01","cited_by_count":6,"area":null},{"id":"2606.05688","title":"Value-and-Structure Alignment for Routing-Consistent Quantization of Mixture-of-Experts Models","created":"2026-06-04","cited_by_count":6,"area":"moe"},{"id":"2606.26080","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents","created":"2026-06-24","cited_by_count":6,"area":"lr"},{"id":"2607.25357","title":"Raven: High-Recall Sequence Modeling with Sparse Memory Routing","created":"2026-07-28","cited_by_count":6,"area":null},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"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":"2605.08301","title":"Priming: Hybrid State Space Models From Pre-trained Transformers","created":"2026-05-08","cited_by_count":5,"area":null},{"id":"2606.00408","title":"Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism","created":"2026-05-29","cited_by_count":5,"area":null},{"id":"2606.19257","title":"DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models","created":"2026-06-17","cited_by_count":5,"area":"lr"},{"id":"2605.05365","title":"ZAYA1-8B Technical Report","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2606.09659","title":"End-to-End Context Compression at Scale","created":"2026-06-08","cited_by_count":4,"area":"inference"},{"id":"2608.27409","title":"Consolidating RLVR Capabilities Across Domains: A Deep Dive into Fusion Paradigms","created":"2026-08-27","cited_by_count":4,"area":null},{"id":"2602.17445","title":"ABCD: All Biases Come Disguised","created":"2026-02-19","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":"2603.21877","title":"P^2O: Joint Policy and Prompt Optimization","created":"2026-03-23","cited_by_count":3,"area":"lr"},{"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":"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":"2603.10035","title":"TriageSim: A Conversational Emergency Triage Simulation Framework from Structured Electronic Health Records","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2603.23443","title":"Evaluating LLM-Based Test Generation Under Software Evolution","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2604.07190","title":"The ATOM Report: Measuring the Open Language Model Ecosystem","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2604.16813","title":"PersonalHomeBench: Evaluating Agents in Personalized Smart Homes","created":"2026-04-18","cited_by_count":2,"area":"agents"},{"id":"2604.17141","title":"SciImpact: A Multi-Dimensional, Multi-Field Benchmark for Scientific Impact Prediction","created":"2026-04-18","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":"2605.06067","title":"Normalized Architectures are Natively 4-Bit","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.07905","title":"CoCoReviewBench: A Completeness- and Correctness-Oriented Benchmark for AI Reviewers","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2606.16140","title":"VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models","created":"2026-06-15","cited_by_count":2,"area":"lr"},{"id":"2606.20657","title":"A-Evolve-Training: Autonomous Post-Training of a 30B Model","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2608.16211","title":"BaT: Towards Self-Evolving Medical Research Agent with Stage Rubrics","created":"2026-08-17","cited_by_count":2,"area":"agents"},{"id":"2609.19334","title":"A frontend-backend architecture for tool calls in full-duplex speech models","created":"2026-09-16","cited_by_count":2,"area":"agents"},{"id":"2601.06891","title":"CLIMP: Contrastive Language-Image Mamba Pretraining","created":"2026-01-11","cited_by_count":1,"area":"ssm"},{"id":"2602.00161","title":"LLM Compression by Block Removal with Constrained Binary Optimization","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2602.09843","title":"Kelix Technical Report","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2602.15327","title":"Prescriptive Scaling Reveals the Evolution of Language Model Capabilities","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2603.08281","title":"Evaluating LLM-Based Grant Proposal Review via Structured Perturbations","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2604.07749","title":"Beyond Social Pressure: Benchmarking Epistemic Attack in Large Language Models","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2605.27605","title":"Laguna M.1/XS.2 Technical Report","created":"2026-05-26","cited_by_count":1,"area":"agents"},{"id":"2606.12364","title":"On Subquadratic Architectures: From Applications to Principles","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.13100","title":"LEDGER: A Long-Context Benchmark of Corporate Annual Reports for Grounded Financial Retrieval and Extraction","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.13782","title":"MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analysis","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.18699","title":"TW-LegalBench: Measuring Taiwanese Legal Understanding","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2606.21884","title":"A Verifiable Search Is Not a Learnable Chain-of-Thought","created":"2026-06-20","cited_by_count":1,"area":"lr"},{"id":"2607.04371","title":"Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs","created":"2026-07-05","cited_by_count":1,"area":"moe"},{"id":"2607.05001","title":"TACTIC-KG: Toward Small Agent Teams for Cyber Threat Intelligence Knowledge Graph Construction","created":"2026-07-06","cited_by_count":1,"area":"agents"},{"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":"2607.16204","title":"Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL","created":"2026-05-07","cited_by_count":1,"area":"wm"},{"id":"2608.11247","title":"Conformity Mitigations in Large Language Models Lie on a Single Resistance-Receptivity Frontier","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2608.20314","title":"MidTool: Mid-training Data Synthesis for Agentic Tool Use","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"id":"2608.24306","title":"Who is the Agent to Blame? Localizing Faithfulness and Citation Mistakes in Agentic Deep Research","created":"2026-08-25","cited_by_count":1,"area":"agents"},{"id":"2609.17699","title":"NeMo Data Designer: An Extensible Framework for Multimodal Synthetic Data Generation","created":"2026-09-15","cited_by_count":1,"area":null},{"id":"2609.32610","title":"KV-Lingo: Learning KV-Cache Translators with Distillation","created":"2026-09-26","cited_by_count":1,"area":"inference"},{"id":"2604.23539","title":"MetaGAI: A Large-Scale and High-Quality Benchmark for Generative AI Model and Data Card Generation","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2604.23705","title":"Can an MLP Absorb Its Own Skip Connection Exactly?","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2604.25774","title":"CGU-ILALab at FoodBench-QA 2026: Comparing Traditional and LLM-based Approaches for Recipe Nutrient Estimation","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.20982","title":"Diagnosing Overhead in Dispatch Operations: Cross-architecture Observatory","created":"2026-05-20","cited_by_count":0,"area":"moe"},{"id":"2605.26279","title":"MPMMine: Better Benchmarks for Constraint Acquisition","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2605.30052","title":"REPOT: Recoverable Program-of-Thought via Checkpoint Repair","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2606.01045","title":"Child-directed speech facilitates production, not comprehension, in BabyLMs","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2607.05198","title":"Noisy-Channel Minimum Bayes Risk Decoding","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.01284","title":"Training nGPT","created":"2026-08-02","cited_by_count":0,"area":"moe"},{"id":"2608.03675","title":"VetScore: Risk-Weighted Fact Verification for Veterinary Long-Form QA with Citations","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.07316","title":"Natural Language Processing Psychometrics","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.11022","title":"Workflow Cards: Structured Summaries of Workflow Executions Using Provenance Data","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.20953","title":"Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.25311","title":"Prefix-Denoising Consistency: Test-Time Verification for Diffusion Language Models","created":"2026-08-26","cited_by_count":0,"area":"diffusion"},{"id":"2608.29151","title":"WoE Wrote It? Watermarking Mixture-of-Experts LLMs for Black-Box Text Provenance","created":"2026-08-29","cited_by_count":0,"area":"safety"},{"id":"2608.29590","title":"Guardrail-Agnostic Societal Bias Evaluation in Large Vision-Language Models","created":"2026-08-30","cited_by_count":0,"area":"mllm"},{"id":"2609.00590","title":"CRAFT: Fine-Tuning Pre-hoc Explainability in AI-native 6G RAN","created":"2026-09-01","cited_by_count":0,"area":"lr"},{"id":"2609.02849","title":"Post-Training Language Models for Gold-Medal Performance in Coding Competitions","created":"2026-09-02","cited_by_count":0,"area":"lr"},{"id":"2609.15242","title":"Empirical Evaluation of Open-Source Large Language Models for Retrieval-Augmented Generation in ESG Domain","created":"2026-09-14","cited_by_count":0,"area":"rag"},{"id":"2609.20751","title":"dQwen3.5: Hybrid-Attention Diffusion Language Models","created":"2026-09-17","cited_by_count":0,"area":"diffusion"},{"id":"2609.31947","title":"On-Policy Attention Linearization","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.33559","title":"Fine Until Fine-Tuned: Repeated Solutions Make Reasoning Fragile","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33885","title":"Prospective Interpretation Risk: Principled Communication Control Between LLMs","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.34718","title":"Quality Determines Direction, Length Shapes Magnitude: Length Control for Open-Ended Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2609.34745","title":"No Pain, More Gain: Iterative Merging for Effective Multi-Teacher On-Policy Distillation","created":"2026-09-28","cited_by_count":0,"area":"distill"},{"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":"2609.39154","title":"DAGent: Evaluate-then-Grow Planning for Deep Research Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.00979","title":"RISED: RubrIcs for agentic multi-environment Selection and sElf-Distillation","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.01509","title":"Sharpening Tax in Post-Training","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.06366","title":"Correct Verdicts, Flawed Reasoning: Structured Auditing of LLM-based Vulnerability Reasoning","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.10478","title":"Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.12582","title":"One Model to Loop Them All: Elastic Latent Recurrence for Language Models","created":"2026-10-08","cited_by_count":0,"area":"moe"},{"id":"2610.12998","title":"Evaluating LLM Creativity through Long-Tail Performance","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.13479","title":"A Local Agentic AI Framework to Generate Edge Case Scenarios for Safety Assurance","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.15373","title":"In-Place Indic Tokenizer Expansion and Continual Pretraining of Nemotron-3-Nano-30B-A3B","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":"100"}