{"total":459,"rows":[{"id":"2310.02575","title":"AdaMerging: Adaptive Model Merging for Multi-Task Learning","created":"2023-10-04","cited_by_count":252,"area":null},{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"area":"alignment"},{"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":"2305.18459","title":"Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning","created":"2023-05-29","cited_by_count":115,"area":"diffusion"},{"id":"2111.10603","title":"Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning","created":"2021-11-20","cited_by_count":101,"area":null},{"id":"2402.02705","title":"Representation Surgery for Multi-Task Model Merging","created":"2024-02-05","cited_by_count":96,"area":null},{"id":"2311.01223","title":"Diffusion Models for Reinforcement Learning: A Survey","created":"2023-11-02","cited_by_count":91,"area":"diffusion"},{"id":"2306.03792","title":"FAMO: Fast Adaptive Multitask Optimization","created":"2023-06-06","cited_by_count":78,"area":null},{"id":"2202.03091","title":"Auto-Lambda: Disentangling Dynamic Task Relationships","created":"2022-02-07","cited_by_count":73,"area":null},{"id":"2305.19000","title":"Independent Component Alignment for Multi-Task Learning","created":"2023-05-30","cited_by_count":70,"area":null},{"id":"2201.04122","title":"In Defense of the Unitary Scalarization for Deep Multi-Task Learning","created":"2022-01-11","cited_by_count":67,"area":null},{"id":"2410.15067","title":"A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends","created":"2024-10-19","cited_by_count":60,"area":null},{"id":"2401.05779","title":"Erasing Undesirable Influence in Diffusion Models","created":"2024-01-11","cited_by_count":57,"area":"diffusion"},{"id":"2502.00604","title":"Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective","created":"2025-02-02","cited_by_count":56,"area":null},{"id":"2402.19078","title":"Smooth Tchebycheff Scalarization for Multi-Objective Optimization","created":"2024-02-29","cited_by_count":54,"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":"2302.11289","title":"Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learning","created":"2023-02-22","cited_by_count":51,"area":null},{"id":"2308.13985","title":"Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective","created":"2023-08-27","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":"2408.11104","title":"ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks","created":"2024-08-20","cited_by_count":46,"area":null},{"id":"2307.15324","title":"TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts","created":"2023-07-28","cited_by_count":45,"area":"moe"},{"id":"2403.20320","title":"MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning","created":"2024-03-29","cited_by_count":44,"area":null},{"id":"2203.00077","title":"One Model is All You Need: Multi-Task Learning Enables Simultaneous Histology Image Segmentation and Classification","created":"2022-02-28","cited_by_count":38,"area":null},{"id":"2303.05675","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","created":"2023-03-10","cited_by_count":38,"area":null},{"id":"2506.24086","title":"MotionGPT3: Human Motion as a Second Modality","created":"2025-06-30","cited_by_count":37,"area":null},{"id":"2305.20057","title":"Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance","created":"2023-05-31","cited_by_count":36,"area":null},{"id":"2402.15896","title":"Multimodal Instruction Tuning with Conditional Mixture of LoRA","created":"2024-02-24","cited_by_count":36,"area":"mllm"},{"id":"2402.15638","title":"Fair Resource Allocation in Multi-Task Learning","created":"2024-02-23","cited_by_count":35,"area":null},{"id":"2305.18409","title":"Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms","created":"2023-05-28","cited_by_count":34,"area":null},{"id":"2306.00354","title":"Addressing Negative Transfer in Diffusion Models","created":"2023-06-01","cited_by_count":33,"area":"diffusion"},{"id":"2211.15055","title":"AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learning","created":"2022-11-28","cited_by_count":31,"area":null},{"id":"2210.09759","title":"Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models","created":"2022-10-18","cited_by_count":29,"area":null},{"id":"2301.12618","title":"ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning","created":"2023-01-30","cited_by_count":28,"area":null},{"id":"2308.12029","title":"Dual-Balancing for Multi-Task Learning","created":"2023-08-23","cited_by_count":27,"area":null},{"id":"2203.14338","title":"LibMTL: A Python Library for Multi-Task Learning","created":"2022-03-27","cited_by_count":25,"area":null},{"id":"2412.12153","title":"Revisiting Weight Averaging for Model Merging","created":"2024-12-11","cited_by_count":25,"area":null},{"id":"2402.02009","title":"Robust Multi-Task Learning with Excess Risks","created":"2024-02-03","cited_by_count":24,"area":null},{"id":"2204.02744","title":"Universal Representations: A Unified Look at Multiple Task and Domain Learning","created":"2022-04-06","cited_by_count":23,"area":null},{"id":"2410.14972","title":"MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning","created":"2024-10-19","cited_by_count":23,"area":"moe"},{"id":"2503.08564","title":"MoE-Loco: Mixture of Experts for Multitask Locomotion","created":"2025-03-11","cited_by_count":23,"area":"moe"},{"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":"2505.23150","title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2310.00344","title":"HarmonyDream: Task Harmonization Inside World Models","created":"2023-09-30","cited_by_count":22,"area":"wm"},{"id":"2407.02228","title":"MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders","created":"2024-07-02","cited_by_count":22,"area":"ssm"},{"id":"2505.17847","title":"Time-o1: Time-Series Forecasting Needs Transformed Label Alignment","created":"2025-05-23","cited_by_count":22,"area":null},{"id":"2301.10923","title":"Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints","created":"2023-01-26","cited_by_count":21,"area":null},{"id":"2403.09323","title":"E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detection","created":"2024-03-14","cited_by_count":21,"area":null},{"id":"2405.01677","title":"Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation","created":"2024-05-02","cited_by_count":21,"area":"deeprl"},{"id":"2409.18426","title":"Dual Cone Gradient Descent for Training Physics-Informed Neural Networks","created":"2024-09-27","cited_by_count":21,"area":null},{"id":"2412.12442","title":"Multi-Task Reinforcement Learning for Quadrotors","created":"2024-12-17","cited_by_count":20,"area":"deeprl"},{"id":"2508.07768","title":"Pareto Multi-Objective Alignment for Language Models","created":"2025-08-11","cited_by_count":20,"area":"alignment"},{"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":"2308.13537","title":"STEM: Unleashing the Power of Embeddings for Multi-task Recommendation","created":"2023-08-16","cited_by_count":19,"area":null},{"id":"2310.08910","title":"Scalarization for Multi-Task and Multi-Domain Learning at Scale","created":"2023-10-13","cited_by_count":19,"area":null},{"id":"2403.15389","title":"DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data","created":"2024-03-22","cited_by_count":18,"area":"diffusion"},{"id":"2406.16232","title":"Jacobian Descent for Multi-Objective Optimization","created":"2024-06-23","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":"2311.13250","title":"FedHCA$^2$: Towards Hetero-Client Federated Multi-Task Learning","created":"2023-11-22","cited_by_count":17,"area":null},{"id":"2411.15537","title":"MUNBa: Machine Unlearning via Nash Bargaining","created":"2024-11-23","cited_by_count":17,"area":"safety"},{"id":"2502.11986","title":"Selective Task Group Updates for Multi-Task Optimization","created":"2025-02-17","cited_by_count":17,"area":null},{"id":"2405.19650","title":"Few for Many: Tchebycheff Set Scalarization for Many-Objective Optimization","created":"2024-05-30","cited_by_count":16,"area":null},{"id":"2406.18038","title":"MT2ST: Adaptive Multi-Task to Single-Task Learning","created":"2024-06-26","cited_by_count":16,"area":null},{"id":"2510.25970","title":"SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing","created":"2025-10-29","cited_by_count":16,"area":"diffusion"},{"id":"2211.13723","title":"Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective","created":"2022-11-24","cited_by_count":15,"area":null},{"id":"2407.17466","title":"Traversing Pareto Optimal Policies: Provably Efficient Multi-Objective Reinforcement Learning","created":"2024-07-24","cited_by_count":15,"area":"deeprl"},{"id":"2411.11188","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers","created":"2024-11-17","cited_by_count":15,"area":"deeprl"},{"id":"2505.24378","title":"Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer","created":"2025-05-30","cited_by_count":15,"area":"moe"},{"id":"2210.12624","title":"Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach","created":"2022-10-23","cited_by_count":14,"area":null},{"id":"2212.04821","title":"PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data","created":"2022-12-08","cited_by_count":14,"area":null},{"id":"2306.10155","title":"Fairness in Multi-Task Learning via Wasserstein Barycenters","created":"2023-06-16","cited_by_count":14,"area":null},{"id":"2405.18080","title":"HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning","created":"2024-05-28","cited_by_count":14,"area":"offlinerl"},{"id":"2502.05932","title":"Skill Expansion and Composition in Parameter Space","created":"2025-02-09","cited_by_count":14,"area":null},{"id":"2606.27377","title":"DanceOPD: On-Policy Generative Field Distillation","created":"2026-06-25","cited_by_count":14,"area":"diffusion"},{"id":"2306.00036","title":"Symmetry-Aware Robot Design with Structured Subgroups","created":"2023-05-31","cited_by_count":13,"area":null},{"id":"2407.08056","title":"Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences","created":"2024-07-10","cited_by_count":13,"area":null},{"id":"2410.06741","title":"CoBa: Convergence Balancer for Multitask Finetuning of Large Language Models","created":"2024-10-09","cited_by_count":13,"area":null},{"id":"2501.15065","title":"Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflicts","created":"2025-01-25","cited_by_count":13,"area":null},{"id":"2507.03298","title":"Dyn-O: Building Structured World Models with Object-Centric Representations","created":"2025-07-04","cited_by_count":13,"area":"wm"},{"id":"2301.13501","title":"Auxiliary Learning as an Asymmetric Bargaining Game","created":"2023-01-31","cited_by_count":12,"area":null},{"id":"2406.09679","title":"Exploring Training on Heterogeneous Data with Mixture of Low-rank Adapters","created":"2024-06-14","cited_by_count":12,"area":null},{"id":"2406.10667","title":"UniZero: Generalized and Efficient Planning with Scalable Latent World Models","created":"2024-06-15","cited_by_count":12,"area":"wm"},{"id":"2407.12273","title":"GRIDS: Grouped Multiple-Degradation Restoration with Image Degradation Similarity","created":"2024-07-17","cited_by_count":12,"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":"2410.15483","title":"Understanding Forgetting in LLM Supervised Fine-Tuning and Preference Learning -- A Convex Optimization Perspective","created":"2024-10-20","cited_by_count":12,"area":"alignment"},{"id":"2411.10606","title":"AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment","created":"2024-11-15","cited_by_count":12,"area":null},{"id":"2411.18615","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","created":"2024-11-27","cited_by_count":12,"area":null},{"id":"2305.15984","title":"Dynamic Inter-treatment Information Sharing for Individualized Treatment Effects Estimation","created":"2023-05-25","cited_by_count":11,"area":null},{"id":"2402.04005","title":"Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2404.06486","title":"GO4Align: Group Optimization for Multi-Task Alignment","created":"2024-04-09","cited_by_count":11,"area":null},{"id":"2406.02996","title":"Quantifying Task Priority for Multi-Task Optimization","created":"2024-06-05","cited_by_count":11,"area":null},{"id":"2506.14811","title":"Self-Composing Policies for Scalable Continual Reinforcement Learning","created":"2025-06-04","cited_by_count":11,"area":"deeprl"},{"id":"2507.23172","title":"Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks","created":"2025-07-31","cited_by_count":11,"area":"deeprl"},{"id":"2602.02495","title":"Reward-free Alignment for Conflicting Objectives","created":"2026-02-02","cited_by_count":11,"area":"alignment"},{"id":"2402.09492","title":"PMGDA: A Preference-based Multiple Gradient Descent Algorithm","created":"2024-02-14","cited_by_count":10,"area":"deeprl"},{"id":"2403.02695","title":"Controllable Prompt Tuning For Balancing Group Distributional Robustness","created":"2024-03-05","cited_by_count":10,"area":null},{"id":"2408.15101","title":"MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoders","created":"2024-08-27","cited_by_count":10,"area":"ssm"},{"id":"2506.08840","title":"MoRE: Mixture of Residual Experts for Humanoid Lifelike Gaits Learning on Complex Terrains","created":"2025-06-10","cited_by_count":10,"area":"deeprl"},{"id":"2605.29548","title":"Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention","created":"2026-05-28","cited_by_count":10,"area":null},{"id":"2302.10574","title":"MulGT: Multi-task Graph-Transformer with Task-aware Knowledge Injection and Domain Knowledge-driven Pooling for Whole Slide Image Analysis","created":"2023-02-21","cited_by_count":9,"area":null},{"id":"2307.15429","title":"Improvable Gap Balancing for Multi-Task Learning","created":"2023-07-28","cited_by_count":9,"area":null}],"next_cursor":"100"}