{"total":24,"rows":[{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386,"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":"2404.04925","title":"Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers","created":"2024-04-07","cited_by_count":51,"area":"lr"},{"id":"2412.13736","title":"MedCoT: Medical Chain of Thought via Hierarchical Expert","created":"2024-12-18","cited_by_count":46,"area":"lr"},{"id":"2501.17974","title":"Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization","created":"2025-01-29","cited_by_count":29,"area":"lr"},{"id":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2502.20395","title":"R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts","created":"2025-02-27","cited_by_count":12,"area":"lr"},{"id":"2405.00557","title":"Mixture of insighTful Experts (MoTE): The Synergy of Thought Chains and Expert Mixtures in Self-Alignment","created":"2024-05-01","cited_by_count":10,"area":"lr"},{"id":"2502.09955","title":"Diverse Inference and Verification for Advanced Reasoning","created":"2025-02-14","cited_by_count":6,"area":"lr"},{"id":"2603.08113","title":"SAMoE-VLA: A Scene Adaptive Mixture-of-Experts Vision-Language-Action Model for Autonomous Driving","created":"2026-03-09","cited_by_count":4,"area":"lr"},{"id":"2210.11265","title":"Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformers","created":"2022-10-20","cited_by_count":3,"area":"lr"},{"id":"2503.11486","title":"A Review of DeepSeek Models' Key Innovative Techniques","created":"2025-03-14","cited_by_count":3,"area":"lr"},{"id":"2604.27201","title":"Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation","created":"2026-04-29","cited_by_count":3,"area":"lr"},{"id":"2505.04075","title":"Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress","created":"2025-05-07","cited_by_count":2,"area":"lr"},{"id":"2606.22798","title":"Does the Same Token Mean the Same State? MoE Routing as Signal for Reasoning Control","created":"2026-06-22","cited_by_count":2,"area":"lr"},{"id":"2508.18672","title":"Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks","created":"2025-08-26","cited_by_count":1,"area":"lr"},{"id":"2510.05125","title":"Catalog-Native LLM: Speaking Item-ID Dialect with Less Entanglement for Recommendation","created":"2025-09-30","cited_by_count":1,"area":"lr"},{"id":"2510.06005","title":"MASA: Rethinking the Representational Bottleneck in LoRA with Multi-A Shared Adaptation","created":"2025-10-07","cited_by_count":1,"area":"lr"},{"id":"2605.19762","title":"What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure Code","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2512.21651","title":"Rethinking Output Alignment For 1-bit Post-Training Quantization of Large Language Models","created":"2025-12-25","cited_by_count":0,"area":"lr"},{"id":"2602.01466","title":"Rethinking Multinomial Logistic Mixture of Experts with Sigmoid Gating Function","created":"2026-02-01","cited_by_count":0,"area":"lr"},{"id":"2607.20427","title":"Is MoE Routing a Huffman Code? Discovering the Frequency-Diversity Law in Chain-of-Thought","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2607.21291","title":"Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs","created":"2026-07-23","cited_by_count":0,"area":"lr"},{"id":"2609.06403","title":"From Concentration to Differentiation and Back: Routing Effective Rank in MoE Reasoning Cohorts","created":"2026-09-06","cited_by_count":0,"area":"lr"}],"next_cursor":null}