{"total":31,"rows":[{"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":"2502.11528","title":"A Survey of Personalized Large Language Models: Progress and Future Directions","created":"2025-02-17","cited_by_count":71,"area":null},{"id":"2502.12446","title":"Multi-Attribute Steering of Language Models via Targeted Intervention","created":"2025-02-18","cited_by_count":46,"area":null},{"id":"2407.15762","title":"Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuning","created":"2024-07-22","cited_by_count":43,"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":"2501.10945","title":"Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond","created":"2025-01-19","cited_by_count":18,"area":null},{"id":"2510.11686","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2502.10762","title":"Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation","created":"2025-02-15","cited_by_count":14,"area":null},{"id":"2507.04756","title":"CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering","created":"2025-07-07","cited_by_count":13,"area":null},{"id":"2502.01662","title":"Fast Large Language Model Collaborative Decoding via Speculation","created":"2025-02-01","cited_by_count":12,"area":null},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"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":"2601.05106","title":"Token-Level LLM Collaboration via FusionRoute","created":"2026-01-08","cited_by_count":9,"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":"2510.13890","title":"A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2511.02966","title":"Inference-Time Personalized Alignment with a Few User Preference Queries","created":"2025-11-04","cited_by_count":6,"area":null},{"id":"2505.02579","title":"EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuning","created":"2025-05-05","cited_by_count":4,"area":null},{"id":"2601.04963","title":"Text as a Universal Interface for Transferable Personalization","created":"2026-01-08","cited_by_count":3,"area":null},{"id":"2604.15383","title":"Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2506.07276","title":"Tokenized Bandit for LLM Decoding and Alignment","created":"2025-06-08","cited_by_count":2,"area":null},{"id":"2506.21887","title":"Interactive Multi-Objective Probabilistic Preference Learning with Soft and Hard Bounds","created":"2025-06-27","cited_by_count":2,"area":null},{"id":"2509.21613","title":"Multi-Objective Reinforcement Learning for Large Language Model Optimization: Visionary Perspective","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2510.14106","title":"Generating Fair Consensus Statements with Social Choice on Token-Level MDPs","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2601.02908","title":"TA-Prompting: Enhancing Video Large Language Models for Dense Video Captioning via Temporal Anchors","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2605.27117","title":"Position: AI Safety Requires Effective Controllability","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2605.07162","title":"CLIPer: Tailoring Diverse User Preference via Classifier-Guided Inference-Time Personalization","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2608.00175","title":"Inference-Time Policy Alignment for Fair Reinforcement Learning","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.28942","title":"From Static Personal Values to Contextualized Personalization: Bayesian Personalized Value Alignment for LLMs","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.39055","title":"The Missing Coefficients: Bayesian Pairwise Merging for Model Personalization","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02353","title":"Does Every User Need a Private LoRA? Decoupling Personalization from Per-User Adaptation","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.05898","title":"Collaborative Personalized Preference Alignment for LLMs under Data Deficiency","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}