{"total":73,"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":"2311.08105","title":"DiLoCo: Distributed Low-Communication Training of Language Models","created":"2023-11-14","cited_by_count":121,"area":null},{"id":"2402.02705","title":"Representation Surgery for Multi-Task Model Merging","created":"2024-02-05","cited_by_count":96,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2501.00274","title":"LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts","created":"2024-12-31","cited_by_count":87,"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":"2410.07471","title":"SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection","created":"2024-10-09","cited_by_count":64,"area":null},{"id":"2410.03617","title":"What Matters for Model Merging at Scale?","created":"2024-10-04","cited_by_count":55,"area":null},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45,"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":"2410.17146","title":"LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging","created":"2024-10-22","cited_by_count":41,"area":null},{"id":"2408.07362","title":"BadMerging: Backdoor Attacks Against Model Merging","created":"2024-08-14","cited_by_count":34,"area":null},{"id":"2501.18512","title":"Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch","created":"2025-01-30","cited_by_count":28,"area":null},{"id":"2401.09135","title":"Asynchronous Local-SGD Training for Language Modeling","created":"2024-01-17","cited_by_count":26,"area":null},{"id":"2406.07529","title":"MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation","created":"2024-06-11","cited_by_count":20,"area":null},{"id":"2410.03782","title":"DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation","created":"2024-10-03","cited_by_count":19,"area":null},{"id":"2408.15666","title":"StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements","created":"2024-08-28","cited_by_count":18,"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":"2507.12224","title":"Optimizers Qualitatively Alter Solutions And We Should Leverage This","created":"2025-07-16","cited_by_count":17,"area":null},{"id":"2403.06952","title":"SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data","created":"2024-03-11","cited_by_count":14,"area":null},{"id":"2402.14146","title":"Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation","created":"2024-02-21","cited_by_count":13,"area":null},{"id":"2406.03280","title":"FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion","created":"2024-06-05","cited_by_count":13,"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":"2410.14389","title":"SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery","created":"2024-10-18","cited_by_count":12,"area":null},{"id":"2506.00911","title":"Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models","created":"2025-06-01","cited_by_count":12,"area":null},{"id":"2406.12221","title":"On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation","created":"2024-06-18","cited_by_count":9,"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":"2406.18924","title":"Learning Pareto Set for Multi-Objective Continuous Robot Control","created":"2024-06-27","cited_by_count":8,"area":null},{"id":"2411.08243","title":"Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset","created":"2024-11-12","cited_by_count":8,"area":null},{"id":"2411.09263","title":"Rethinking Weight-Averaged Model-merging","created":"2024-11-14","cited_by_count":8,"area":null},{"id":"2511.05650","title":"Optimizing Diversity and Quality through Base-Aligned Model Collaboration","created":"2025-11-07","cited_by_count":8,"area":null},{"id":"2410.23630","title":"Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI","created":"2024-10-31","cited_by_count":6,"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":"2410.15557","title":"How to Find the Exact Pareto Front for Multi-Objective MDPs?","created":"2024-10-21","cited_by_count":5,"area":null},{"id":"2411.06710","title":"Model Fusion through Bayesian Optimization in Language Model Fine-Tuning","created":"2024-11-11","cited_by_count":5,"area":null},{"id":"2502.17340","title":"Low-rank bias, weight decay, and model merging in neural networks","created":"2025-02-24","cited_by_count":5,"area":null},{"id":"2511.21437","title":"A Systematic Study of In-the-Wild Model Merging for Large Language Models","created":"2025-11-26","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":"2404.07117","title":"Continuous Language Model Interpolation for Dynamic and Controllable Text Generation","created":"2024-04-10","cited_by_count":3,"area":null},{"id":"2406.08423","title":"State Soup: In-Context Skill Learning, Retrieval and Mixing","created":"2024-06-12","cited_by_count":3,"area":null},{"id":"2411.00524","title":"Comparison-based Active Preference Learning for Multi-dimensional Personalization","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2412.17023","title":"Parameter-Efficient Interventions for Enhanced Model Merging","created":"2024-12-22","cited_by_count":3,"area":null},{"id":"2502.01804","title":"Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging","created":"2025-02-03","cited_by_count":3,"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":"2405.21027","title":"Fusion-PSRO: Nash Policy Fusion for Policy Space Response Oracles","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2410.18841","title":"From Efficiency to Equity: Measuring Fairness in Preference Learning","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2506.07276","title":"Tokenized Bandit for LLM Decoding and Alignment","created":"2025-06-08","cited_by_count":2,"area":null},{"id":"2509.23689","title":"Merge Now, Regret Later: The Hidden Cost of Model Merging Is Adversarial Transferability","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2510.12121","title":"Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2504.11268","title":"Single-Input Multi-Output Model Merging: Leveraging Foundation Models for Dense Multi-Task Learning","created":"2025-04-15","cited_by_count":1,"area":null},{"id":"2504.14147","title":"Explainable Recommendation with Simulated Human Feedback","created":"2025-04-19","cited_by_count":1,"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":"2511.00220","title":"Iterative Foundation Model Fine-Tuning on Multiple Rewards","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2511.19561","title":"Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2602.02890","title":"Self-Soupervision: Cooking Model Soups without Labels","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2606.02252","title":"ResMerge: Residual-based Spectral Merging of Large Language Models","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2508.09228","title":"Objective Soups: Multilingual Multi-Task Modeling for Speech Processing","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2601.21690","title":"A Unified Generalization Framework for Model Merging: Trade-offs, Non-Linearity, and Scaling Laws","created":"2026-01-29","cited_by_count":0,"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":"2602.21565","title":"Routing by Reaching: Composition of Pre-trained GFlowNets for Multi-Objective Generation","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2606.30219","title":"EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.28814","title":"Rolling With Resistance: Preference-Optimized LLM Counselors Can Trade Goal Persistence for Relational Attunement in Motivational Interviewing","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.10090","title":"CHORUS: Complementary Experts for High-Coverage Testbench Stimulus Generation","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.16650","title":"PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.11291","title":"Off-Target Effects of Response-Style Alignment in a Korean 27B Language Model","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.13657","title":"Safety as a Constraint: Fine-Tuning a LLM Recommender to Explain Itself","created":"2026-09-12","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":"2609.39365","title":"Ready2Blend: From Natural-Language Instructions to Composable Alignment Prompts","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":"2610.03218","title":"VisionMX: Unlocking Microscaling Post-Training Quantization for Vision Models","created":"2026-10-02","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},{"id":"2610.13944","title":"InstantFusion: A Shared Latent Interface for Heterogeneous Image Generators","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}