{"total":47,"rows":[{"id":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22,"area":null},{"id":"2604.16027","title":"Where does output diversity collapse in post-training?","created":"2026-04-17","cited_by_count":11,"area":null},{"id":"2606.01774","title":"FLARE: Diffusion for Hybrid Language Model","created":"2026-06-01","cited_by_count":6,"area":null},{"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":"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":"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":"2604.17141","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":"2606.20657","title":"A-Evolve-Training: Autonomous Post-Training of a 30B Model","created":"2026-06-09","cited_by_count":2,"area":null},{"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":"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":"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":"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":"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":"2605.26279","title":"MPMMine: Better Benchmarks for Constraint Acquisition","created":"2026-05-25","cited_by_count":0,"area":null},{"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":"2608.03675","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":"2609.33559","title":"Fine Until Fine-Tuned: Repeated Solutions Make Reasoning Fragile","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":"2610.12998","title":"Evaluating LLM Creativity through Long-Tail Performance","created":"2026-10-09","cited_by_count":0,"area":null},{"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},{"id":"2610.15894","title":"Make Every Expansion Count: Learning to Search Efficiently in LLM Code Repair","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}