{"total":56,"rows":[{"id":"2406.18853","title":"Decoding-Time Language Model Alignment with Multiple Objectives","created":"2024-06-27","cited_by_count":94,"area":"alignment"},{"id":"2502.18036","title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","created":"2025-02-25","cited_by_count":86,"area":null},{"id":"2404.12715","title":"Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration","created":"2024-04-19","cited_by_count":67,"area":null},{"id":"2506.22716","title":"BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute","created":"2025-06-28","cited_by_count":67,"area":null},{"id":"2408.07990","title":"FuseChat: Knowledge Fusion of Chat Models","created":"2024-08-15","cited_by_count":55,"area":null},{"id":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44,"area":null},{"id":"2503.20083","title":"Universal Cross-Tokenizer Distillation via Approximate Likelihood Matching","created":"2025-03-25","cited_by_count":41,"area":"distill"},{"id":"2412.15797","title":"Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning","created":"2024-12-20","cited_by_count":40,"area":"lr"},{"id":"2412.04692","title":"Smoothie: Label Free Language Model Routing","created":"2024-12-06","cited_by_count":31,"area":null},{"id":"2502.04506","title":"When One LLM Drools, Multi-LLM Collaboration Rules","created":"2025-02-06","cited_by_count":28,"area":null},{"id":"2410.11163","title":"Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2502.00883","title":"SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters","created":"2025-02-02","cited_by_count":25,"area":"alignment"},{"id":"2502.04510","title":"Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems","created":"2025-02-06","cited_by_count":23,"area":null},{"id":"2504.00762","title":"Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute","created":"2025-04-01","cited_by_count":20,"area":"lr"},{"id":"2503.01155","title":"Nature-Inspired Population-Based Evolution of Large Language Models","created":"2025-03-03","cited_by_count":15,"area":null},{"id":"2505.07460","title":"A Survey on Collaborative Mechanisms Between Large and Small Language Models","created":"2025-05-12","cited_by_count":14,"area":null},{"id":"2505.10892","title":"Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models","created":"2025-05-16","cited_by_count":13,"area":"alignment"},{"id":"2407.19807","title":"Cool-Fusion: Fuse Large Language Models without Training","created":"2024-07-29","cited_by_count":12,"area":null},{"id":"2502.00245","title":"Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion","created":"2025-02-01","cited_by_count":11,"area":"synth"},{"id":"2510.09913","title":"Don't Throw Away Your Pretrained Model","created":"2025-10-10","cited_by_count":10,"area":"lr"},{"id":"2510.13855","title":"Harnessing Consistency for Robust Test-Time LLM Ensemble","created":"2025-10-12","cited_by_count":10,"area":null},{"id":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2503.13505","title":"Ensemble Learning for Large Language Models in Text and Code Generation: A Survey","created":"2025-03-13","cited_by_count":9,"area":null},{"id":"2505.14136","title":"Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging","created":"2025-05-20","cited_by_count":9,"area":"moe"},{"id":"2504.10724","title":"HELIOS: Adaptive Model And Early-Exit Selection for Efficient LLM Inference Serving","created":"2025-04-14","cited_by_count":8,"area":"inference"},{"id":"2412.06619","title":"Copyright-Protected Language Generation via Adaptive Model Fusion","created":"2024-12-09","cited_by_count":7,"area":null},{"id":"2506.00439","title":"RLAE: Reinforcement Learning-Assisted Ensemble for LLMs","created":"2025-05-31","cited_by_count":7,"area":null},{"id":"2506.14123","title":"Sampling from Your Language Model One Byte at a Time","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2505.21226","title":"Why Do More Experts Fail? A Theoretical Analysis of Model Merging","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2406.12527","title":"FuseGen: PLM Fusion for Data-generation based Zero-shot Learning","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2407.20105","title":"Strong Copyright Protection for Language Models via Adaptive Model Fusion","created":"2024-07-29","cited_by_count":4,"area":null},{"id":"2501.17479","title":"DFPE: A Diverse Fingerprint Ensemble for Enhancing LLM Performance","created":"2025-01-29","cited_by_count":4,"area":null},{"id":"2510.03930","title":"LLM Chemistry Estimation for Multi-LLM Recommendation","created":"2025-10-04","cited_by_count":3,"area":null},{"id":"2603.05432","title":"Ensembling Language Models with Sequential Monte Carlo","created":"2026-03-05","cited_by_count":3,"area":null},{"id":"2502.04492","title":"Dynamic Optimizations of LLM Ensembles with Two-Stage Reinforcement Learning Agents","created":"2025-02-06","cited_by_count":2,"area":"agents"},{"id":"2503.06138","title":"System 0/1/2/3: Quad-process theory for multi-timescale embodied collective cognitive systems","created":"2025-03-08","cited_by_count":2,"area":null},{"id":"2508.17669","title":"A Taxonomy of Transcendence","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2508.21762","title":"Reasoning-Intensive Regression","created":"2025-08-29","cited_by_count":2,"area":"lr"},{"id":"2510.06419","title":"Test-Time Efficient Pretrained Model Portfolios for Time Series Forecasting","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2510.08592","title":"Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models","created":"2025-10-04","cited_by_count":2,"area":"lr"},{"id":"2602.05182","title":"The Single-Multi Evolution Loop for Self-Improving Model Collaboration Systems","created":"2026-02-05","cited_by_count":2,"area":"synth"},{"id":"2602.05307","title":"MentorCollab: Large-to-Small Inference-Time Mentorship for Concise Reasoning in Language Models","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2604.01674","title":"Can Heterogeneous Language Models Be Fused?","created":"2026-04-02","cited_by_count":2,"area":null},{"id":"2604.25098","title":"Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling","created":"2026-04-28","cited_by_count":2,"area":"lr"},{"id":"2502.16055","title":"MedForge: Building Medical Foundation Models Like Open Source Software Development","created":"2025-02-22","cited_by_count":1,"area":null},{"id":"2504.09620","title":"Metropolis-Hastings Captioning Game: Knowledge Fusion of Vision Language Models via Decentralized Bayesian Inference","created":"2025-04-13","cited_by_count":1,"area":"mllm"},{"id":"2505.23844","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2510.19507","title":"Teaming LLMs to Detect and Mitigate Hallucinations","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2605.00419","title":"Rethinking LLM Ensembling from the Perspective of Mixture Models","created":"2026-05-01","cited_by_count":1,"area":"lr"},{"id":"2512.10601","title":"Multi-Objective Reward and Preference Optimization: Theory and Algorithms","created":"2025-12-11","cited_by_count":0,"area":"alignment"},{"id":"2604.18106","title":"Efficient Low-Resource Language Adaptation via Multi-Source Dynamic Logit Fusion","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2606.04378","title":"DLLG: Dynamic Logit-Level Gating of LLM Experts","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.28373","title":"Model Merging to Evolution: Parameter Space Exploration for Expert Models","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.04389","title":"Decentralized Aggregation of LLM Predictions via Wagering Mechanisms","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2609.05801","title":"Evidence-Aligned Local Composition of Discrete Experts for Sequence Restoration","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.37574","title":"MERGE: Multi-LLM Ensemble for Retrieval via Generative Enrichment","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}