{"total":818,"rows":[{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364,"area":null},{"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":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200,"area":null},{"id":"2503.10460","title":"Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond","created":"2025-03-13","cited_by_count":175,"area":"lr"},{"id":"2412.00081","title":"Task Singular Vectors: Reducing Task Interference in Model Merging","created":"2024-11-26","cited_by_count":147,"area":null},{"id":"2312.06795","title":"Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks","created":"2023-12-11","cited_by_count":133,"area":null},{"id":"2405.07813","title":"Localizing Task Information for Improved Model Merging and Compression","created":"2024-05-13","cited_by_count":131,"area":null},{"id":"2412.04261","title":"Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier","created":"2024-12-05","cited_by_count":129,"area":null},{"id":"2403.08763","title":"Simple and Scalable Strategies to Continually Pre-train Large Language Models","created":"2024-03-13","cited_by_count":127,"area":null},{"id":"2405.14366","title":"MiniCache: KV Cache Compression in Depth Dimension for Large Language Models","created":"2024-05-23","cited_by_count":125,"area":"inference"},{"id":"2410.19735","title":"Model merging with SVD to tie the Knots","created":"2024-10-25","cited_by_count":122,"area":null},{"id":"2406.15479","title":"Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging","created":"2024-06-17","cited_by_count":116,"area":null},{"id":"2405.17461","title":"EMR-Merging: Tuning-Free High-Performance Model Merging","created":"2024-05-23","cited_by_count":110,"area":null},{"id":"2502.04959","title":"No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces","created":"2025-02-07","cited_by_count":96,"area":null},{"id":"2403.19522","title":"Model Stock: All we need is just a few fine-tuned models","created":"2024-03-28","cited_by_count":92,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2404.14387","title":"A Survey on Self-Evolution of Large Language Models","created":"2024-04-22","cited_by_count":91,"area":null},{"id":"2405.11157","title":"Towards Modular LLMs by Building and Reusing a Library of LoRAs","created":"2024-05-18","cited_by_count":72,"area":null},{"id":"2410.02396","title":"Parameter Competition Balancing for Model Merging","created":"2024-10-03","cited_by_count":72,"area":null},{"id":"2606.30406","title":"MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training","created":"2026-06-29","cited_by_count":72,"area":"distill"},{"id":"2407.06322","title":"MagMax: Leveraging Model Merging for Seamless Continual Learning","created":"2024-07-08","cited_by_count":67,"area":null},{"id":"2402.05859","title":"Learning to Route Among Specialized Experts for Zero-Shot Generalization","created":"2024-02-08","cited_by_count":65,"area":null},{"id":"2503.08099","title":"Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors","created":"2025-03-11","cited_by_count":62,"area":null},{"id":"2409.16167","title":"Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering","created":"2024-09-24","cited_by_count":59,"area":null},{"id":"2503.20641","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","created":"2025-03-26","cited_by_count":58,"area":"lr"},{"id":"2408.07990","title":"FuseChat: Knowledge Fusion of Chat Models","created":"2024-08-15","cited_by_count":55,"area":null},{"id":"2410.03617","title":"What Matters for Model Merging at Scale?","created":"2024-10-04","cited_by_count":55,"area":null},{"id":"2406.11385","title":"MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic","created":"2024-06-17","cited_by_count":53,"area":null},{"id":"2408.07057","title":"A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning","created":"2024-08-13","cited_by_count":52,"area":null},{"id":"2410.13025","title":"LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks","created":"2024-10-16","cited_by_count":52,"area":null},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2408.13656","title":"Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic","created":"2024-08-24","cited_by_count":50,"area":null},{"id":"2505.11711","title":"Reinforcement Learning Finetunes Small Subnetworks in Large Language Models","created":"2025-05-16","cited_by_count":49,"area":null},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2509.06888","title":"mmBERT: A Modern Multilingual Encoder with Annealed Language Learning","created":"2025-09-08","cited_by_count":45,"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":"2404.05590","title":"MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answering","created":"2024-04-08","cited_by_count":43,"area":"rag"},{"id":"2406.14563","title":"Model Merging and Safety Alignment: One Bad Model Spoils the Bunch","created":"2024-06-20","cited_by_count":43,"area":"alignment"},{"id":"2405.09055","title":"A safety realignment framework via subspace-oriented model fusion for large language models","created":"2024-05-15","cited_by_count":41,"area":"safety"},{"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":"2602.09082","title":"UI-Venus-1.5 Technical Report","created":"2026-02-09","cited_by_count":41,"area":"agents"},{"id":"2505.05464","title":"Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging","created":"2025-05-08","cited_by_count":40,"area":"lr"},{"id":"2501.01230","title":"Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent","created":"2025-01-02","cited_by_count":39,"area":null},{"id":"2504.10957","title":"When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers","created":"2025-04-15","cited_by_count":38,"area":"safety"},{"id":"2505.19797","title":"The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants","created":"2025-05-26","cited_by_count":38,"area":null},{"id":"2312.06173","title":"Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion","created":"2023-12-11","cited_by_count":37,"area":null},{"id":"2407.02880","title":"Knowledge Composition using Task Vectors with Learned Anisotropic Scaling","created":"2024-07-03","cited_by_count":37,"area":null},{"id":"2505.12082","title":"Model Merging in Pre-training of Large Language Models","created":"2025-05-17","cited_by_count":37,"area":"moe"},{"id":"2508.02120","title":"Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models","created":"2025-08-04","cited_by_count":37,"area":"lr"},{"id":"2407.08699","title":"Mitigating Catastrophic Forgetting in Language Transfer via Model Merging","created":"2024-07-11","cited_by_count":36,"area":null},{"id":"2410.08589","title":"Retraining-Free Merging of Sparse MoE via Hierarchical Clustering","created":"2024-10-11","cited_by_count":35,"area":"moe"},{"id":"2510.08396","title":"FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts","created":"2025-10-09","cited_by_count":35,"area":"moe"},{"id":"2510.15110","title":"DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning","created":"2025-10-16","cited_by_count":35,"area":"lr"},{"id":"2408.07362","title":"BadMerging: Backdoor Attacks Against Model Merging","created":"2024-08-14","cited_by_count":34,"area":null},{"id":"2405.16281","title":"ConStat: Performance-Based Contamination Detection in Large Language Models","created":"2024-05-25","cited_by_count":33,"area":null},{"id":"2502.17298","title":"Delta Decompression for MoE-based LLMs Compression","created":"2025-02-24","cited_by_count":33,"area":"moe"},{"id":"2505.10833","title":"MergeBench: A Benchmark for Merging Domain-Specialized LLMs","created":"2025-05-16","cited_by_count":33,"area":null},{"id":"2406.11801","title":"Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations","created":"2024-06-17","cited_by_count":32,"area":"alignment"},{"id":"2405.07883","title":"Zero-Shot Tokenizer Transfer","created":"2024-05-13","cited_by_count":31,"area":null},{"id":"2406.16797","title":"Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs","created":"2024-06-24","cited_by_count":31,"area":null},{"id":"2412.19726","title":"Position: Theory of Mind Benchmarks are Broken for Large Language Models","created":"2024-12-27","cited_by_count":31,"area":null},{"id":"2509.17786","title":"Accurate and Efficient Low-Rank Model Merging in Core Space","created":"2025-09-22","cited_by_count":29,"area":null},{"id":"2311.09344","title":"Language and Task Arithmetic with Parameter-Efficient Layers for Zero-Shot Summarization","created":"2023-11-15","cited_by_count":28,"area":null},{"id":"2405.17931","title":"Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment","created":"2024-05-28","cited_by_count":28,"area":"alignment"},{"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":"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":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2402.03660","title":"On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm","created":"2024-02-06","cited_by_count":26,"area":null},{"id":"2502.17159","title":"RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness","created":"2025-02-24","cited_by_count":26,"area":null},{"id":"2412.12153","title":"Revisiting Weight Averaging for Model Merging","created":"2024-12-11","cited_by_count":25,"area":null},{"id":"2503.10633","title":"We Should Chart an Atlas of All the World's Models","created":"2025-03-13","cited_by_count":25,"area":null},{"id":"2503.17239","title":"SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging","created":"2025-03-21","cited_by_count":25,"area":"alignment"},{"id":"2503.23733","title":"AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization","created":"2025-03-31","cited_by_count":25,"area":"mllm"},{"id":"2407.00066","title":"Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead","created":"2024-06-17","cited_by_count":24,"area":null},{"id":"2512.05117","title":"The Universal Weight Subspace Hypothesis","created":"2025-12-04","cited_by_count":24,"area":null},{"id":"2406.12034","title":"Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts","created":"2024-06-17","cited_by_count":23,"area":"moe"},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2410.21804","title":"Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging","created":"2024-10-29","cited_by_count":23,"area":"moe"},{"id":"2412.06712","title":"How to Merge Your Multimodal Models Over Time?","created":"2024-12-09","cited_by_count":23,"area":null},{"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":"2502.11191","title":"Primus: A Pioneering Collection of Open-Source Datasets for Cybersecurity LLM Training","created":"2025-02-16","cited_by_count":23,"area":"distill"},{"id":"2505.06977","title":"CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging","created":"2025-05-11","cited_by_count":23,"area":null},{"id":"2410.17961","title":"Closed-form merging of parameter-efficient modules for Federated Continual Learning","created":"2024-10-23","cited_by_count":22,"area":null},{"id":"2411.18729","title":"Multi-Task Model Merging via Adaptive Weight Disentanglement","created":"2024-11-27","cited_by_count":22,"area":null},{"id":"2509.18883","title":"Introducing LongCat-Flash-Thinking: A Technical Report","created":"2025-09-23","cited_by_count":22,"area":"lr"},{"id":"2512.08333","title":"Robust Finetuning of Vision-Language-Action Robot Policies via Parameter Merging","created":"2025-12-09","cited_by_count":22,"area":"vla"},{"id":"2410.01335","title":"Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models","created":"2024-10-02","cited_by_count":21,"area":null},{"id":"2505.14827","title":"Text Generation Beyond Discrete Token Sampling","created":"2025-05-20","cited_by_count":21,"area":null},{"id":"2505.16270","title":"Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning","created":"2025-05-22","cited_by_count":21,"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":"2412.10493","title":"AlignGuard: Scalable Safety Alignment for Text-to-Image Generation","created":"2024-12-13","cited_by_count":20,"area":"alignment"},{"id":"2505.10717","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","created":"2025-05-15","cited_by_count":20,"area":"alignment"},{"id":"2508.11548","title":"Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends","created":"2025-08-15","cited_by_count":20,"area":"safety"},{"id":"2511.05408","title":"Steering Language Models with Weight Arithmetic","created":"2025-11-07","cited_by_count":20,"area":null},{"id":"2404.05188","title":"Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging","created":"2024-04-08","cited_by_count":19,"area":"safety"},{"id":"2407.03994","title":"Unlocking the Potential of Model Merging for Low-Resource Languages","created":"2024-07-04","cited_by_count":19,"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":"2412.05148","title":"LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation","created":"2024-12-06","cited_by_count":19,"area":null},{"id":"2503.15842","title":"FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors","created":"2025-03-20","cited_by_count":19,"area":null}],"next_cursor":"100"}