{"total":11,"rows":[{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254,"area":null},{"id":"2510.19178","title":"Imbalanced Gradients in RL Post-Training of Multi-Task LLMs","created":"2025-10-22","cited_by_count":20,"area":null},{"id":"2410.06084","title":"Diversity-Rewarded CFG Distillation","created":"2024-10-08","cited_by_count":9,"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":"2512.04068","title":"Learning Steerable Clarification Policies with Collaborative Self-play","created":"2025-12-03","cited_by_count":5,"area":null},{"id":"2410.11221","title":"Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2603.06748","title":"Property-driven Protein Inverse Folding With Multi-Objective Preference Alignment","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2509.05811","title":"Simple Optimizers for Convex Aligned Multi-Objective Optimization","created":"2025-09-06","cited_by_count":1,"area":null},{"id":"2609.08064","title":"Risk-Conditioned Fine-Tuning of Large Language Models","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2602.19041","title":"Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning","created":"2026-02-22","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}],"next_cursor":null}