{"total":215,"rows":[{"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":"2402.02705","title":"Representation Surgery for Multi-Task Model Merging","created":"2024-02-05","cited_by_count":96,"area":null},{"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":"2305.19229","title":"FedDisco: Federated Learning with Discrepancy-Aware Collaboration","created":"2023-05-30","cited_by_count":67,"area":null},{"id":"2402.19078","title":"Smooth Tchebycheff Scalarization for Multi-Objective Optimization","created":"2024-02-29","cited_by_count":54,"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":"2408.11104","title":"ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks","created":"2024-08-20","cited_by_count":46,"area":null},{"id":"2303.02483","title":"FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks","created":"2023-03-04","cited_by_count":38,"area":"mllm"},{"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":"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":"2310.07138","title":"Denoising Task Routing for Diffusion Models","created":"2023-10-11","cited_by_count":28,"area":"diffusion"},{"id":"2308.12029","title":"Dual-Balancing for Multi-Task Learning","created":"2023-08-23","cited_by_count":27,"area":null},{"id":"2402.02009","title":"Robust Multi-Task Learning with Excess Risks","created":"2024-02-03","cited_by_count":24,"area":null},{"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":"2310.00344","title":"HarmonyDream: Task Harmonization Inside World Models","created":"2023-09-30","cited_by_count":22,"area":"wm"},{"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":"2409.18426","title":"Dual Cone Gradient Descent for Training Physics-Informed Neural Networks","created":"2024-09-27","cited_by_count":21,"area":null},{"id":"2403.16092","title":"Are NeRFs ready for autonomous driving? Towards closing the real-to-simulation gap","created":"2024-03-24","cited_by_count":20,"area":"driving"},{"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":"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":"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":"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":"2306.10155","title":"Fairness in Multi-Task Learning via Wasserstein Barycenters","created":"2023-06-16","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":"2407.08056","title":"Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences","created":"2024-07-10","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":"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":"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":"2411.18615","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","created":"2024-11-27","cited_by_count":12,"area":null},{"id":"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":"2505.05279","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2307.15429","title":"Improvable Gap Balancing for Multi-Task Learning","created":"2023-07-28","cited_by_count":9,"area":null},{"id":"2405.16390","title":"Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning","created":"2024-05-26","cited_by_count":9,"area":"deeprl"},{"id":"2407.20734","title":"Efficient Pareto Manifold Learning with Low-Rank Structure","created":"2024-07-30","cited_by_count":9,"area":null},{"id":"2501.15556","title":"Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning","created":"2025-01-26","cited_by_count":9,"area":null},{"id":"2606.24993","title":"The Geometry of Sequential Learning: Lie-Bracket Prediction of Transfer Order","created":"2026-06-23","cited_by_count":9,"area":"alignment"},{"id":"2401.09257","title":"A First-Order Multi-Gradient Algorithm for Multi-Objective Bi-Level Optimization","created":"2024-01-17","cited_by_count":8,"area":null},{"id":"2502.06244","title":"PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2506.00569","title":"AutoMixAlign: Adaptive Data Mixing for Multi-Task Preference Optimization in LLMs","created":"2025-05-31","cited_by_count":8,"area":"alignment"},{"id":"2601.08462","title":"M3-BENCH: Process-Aware Evaluation of LLM Agents' Social Behaviors in Mixed-Motive Games","created":"2026-01-13","cited_by_count":8,"area":"agents"},{"id":"2307.03544","title":"Roman Numeral Analysis with Graph Neural Networks: Onset-wise Predictions from Note-wise Features","created":"2023-07-07","cited_by_count":7,"area":null},{"id":"2405.19440","title":"MGDA Converges under Generalized Smoothness, Provably","created":"2024-05-29","cited_by_count":7,"area":null},{"id":"2502.08585","title":"LDC-MTL: Balancing Multi-Task Learning through Scalable Loss Discrepancy Control","created":"2025-02-12","cited_by_count":7,"area":null},{"id":"2503.02312","title":"Go Beyond Your Means: Unlearning with Per-Sample Gradient Orthogonalization","created":"2025-03-04","cited_by_count":7,"area":"safety"},{"id":"2305.06361","title":"Efficient Training of Multi-task Neural Solver for Combinatorial Optimization","created":"2023-05-10","cited_by_count":6,"area":null},{"id":"2307.14382","title":"When Multi-Task Learning Meets Partial Supervision: A Computer Vision Review","created":"2023-07-25","cited_by_count":6,"area":null},{"id":"2403.10971","title":"Task-Aware Low-Rank Adaptation of Segment Anything Model","created":"2024-03-16","cited_by_count":6,"area":null},{"id":"2404.01976","title":"Joint-Task Regularization for Partially Labeled Multi-Task Learning","created":"2024-04-02","cited_by_count":6,"area":null},{"id":"2406.07029","title":"Fairness-Aware Meta-Learning via Nash Bargaining","created":"2024-06-11","cited_by_count":6,"area":null},{"id":"2408.07985","title":"Analytical Uncertainty-Based Loss Weighting in Multi-Task Learning","created":"2024-08-15","cited_by_count":6,"area":null},{"id":"2412.01566","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","created":"2024-12-02","cited_by_count":6,"area":null},{"id":"2412.02693","title":"Diffusion-based Visual Anagram as Multi-task Learning","created":"2024-12-03","cited_by_count":6,"area":null},{"id":"2603.04772","title":"TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings","created":"2026-03-05","cited_by_count":6,"area":"lr"},{"id":"2403.00282","title":"Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning","created":"2024-03-01","cited_by_count":5,"area":"deeprl"},{"id":"2407.10876","title":"RepVF: A Unified Vector Fields Representation for Multi-task 3D Perception","created":"2024-07-15","cited_by_count":5,"area":null},{"id":"2412.10961","title":"PSMGD: Periodic Stochastic Multi-Gradient Descent for Fast Multi-Objective Optimization","created":"2024-12-14","cited_by_count":5,"area":"deeprl"},{"id":"2502.20161","title":"Balanced Rate-Distortion Optimization in Learned Image Compression","created":"2025-02-27","cited_by_count":5,"area":null},{"id":"2506.06130","title":"Gradient Similarity Surgery in Multi-Task Deep Learning","created":"2025-06-06","cited_by_count":5,"area":null},{"id":"2507.04790","title":"Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planning","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2507.07778","title":"Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Training","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2510.21978","title":"Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models","created":"2025-10-24","cited_by_count":5,"area":"lr"},{"id":"2206.02786","title":"(Im)possibility of Collective Intelligence","created":"2022-06-05","cited_by_count":4,"area":null},{"id":"2304.02780","title":"A Transformer-Based Deep Learning Approach for Fairly Predicting Post-Liver Transplant Risk Factors","created":"2023-04-05","cited_by_count":4,"area":null},{"id":"2310.09276","title":"Transformer-based Multimodal Change Detection with Multitask Consistency Constraints","created":"2023-10-13","cited_by_count":4,"area":null},{"id":"2403.04343","title":"Adaptive Task Balancing for Visual Instruction Tuning via Inter-Task Contribution and Intra-Task Difficulty","created":"2024-03-07","cited_by_count":4,"area":"mllm"},{"id":"2409.18267","title":"Using dynamic loss weighting to boost improvements in forecast stability","created":"2024-09-26","cited_by_count":4,"area":null},{"id":"2505.20380","title":"GRAPE: Optimize Data Mixture for Group Robust Multi-target Adaptive Pretraining","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2507.02714","title":"FairHuman: Boosting Hand and Face Quality in Human Image Generation with Minimum Potential Delay Fairness in Diffusion Models","created":"2025-07-03","cited_by_count":4,"area":"diffusion"},{"id":"2507.07485","title":"Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2510.22031","title":"Differentiable Constraint-Based Causal Discovery","created":"2025-10-24","cited_by_count":4,"area":null},{"id":"2605.06507","title":"MARBLE: Multi-Aspect Reward Balance for Diffusion RL","created":"2026-05-07","cited_by_count":4,"area":"diffusion"},{"id":"2305.19844","title":"Learning Task-preferred Inference Routes for Gradient De-conflict in Multi-output DNNs","created":"2023-05-31","cited_by_count":3,"area":null},{"id":"2308.11646","title":"Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Data","created":"2023-08-17","cited_by_count":3,"area":null},{"id":"2402.15328","title":"Towards Principled Task Grouping for Multi-Task Learning","created":"2024-02-23","cited_by_count":3,"area":null},{"id":"2501.17265","title":"Giving the Old a Fresh Spin: Quality Estimation-Assisted Constrained Decoding for Automatic Post-Editing","created":"2025-01-28","cited_by_count":3,"area":null},{"id":"2502.03571","title":"A Multi-Task Learning Approach to Linear Multivariate Forecasting","created":"2025-02-05","cited_by_count":3,"area":null},{"id":"2502.14096","title":"Aligned Multi Objective Optimization","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2503.04046","title":"Continual Optimization with Symmetry Teleportation for Multi-Task Learning","created":"2025-03-06","cited_by_count":3,"area":null},{"id":"2503.14321","title":"COPA: Comparing the incomparable in multi-objective model evaluation","created":"2025-03-18","cited_by_count":3,"area":null},{"id":"2506.15563","title":"Control and Realism: Best of Both Worlds in Layout-to-Image without Training","created":"2025-06-18","cited_by_count":3,"area":null},{"id":"2509.23915","title":"Revisit the Imbalance Optimization in Multi-task Learning: An Experimental Analysis","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2510.16138","title":"Expert Merging in Sparse Mixture of Experts with Nash Bargaining","created":"2025-10-17","cited_by_count":3,"area":"moe"},{"id":"2604.05629","title":"A Unified Foundation Model for All-in-One Multi-Modal Remote Sensing Image Restoration and Fusion with Language Prompting","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2606.07705","title":"SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models","created":"2026-06-05","cited_by_count":3,"area":"alignment"},{"id":"2311.04698","title":"Examining Common Paradigms in Multi-Task Learning","created":"2023-11-08","cited_by_count":2,"area":null}],"next_cursor":"100"}