{"total":83,"rows":[{"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":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"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":"2212.01378","title":"ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning","created":"2022-12-02","cited_by_count":52,"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":"2408.11104","title":"ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks","created":"2024-08-20","cited_by_count":46,"area":null},{"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":"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":"2410.22086","title":"Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate","created":"2024-10-29","cited_by_count":31,"area":"safety"},{"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":"2310.08910","title":"Scalarization for Multi-Task and Multi-Domain Learning at Scale","created":"2023-10-13","cited_by_count":19,"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":"2502.11986","title":"Selective Task Group Updates for Multi-Task Optimization","created":"2025-02-17","cited_by_count":17,"area":null},{"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":"2602.05547","title":"Multi-Task GRPO: Reliable LLM Reasoning Across Tasks","created":"2026-02-05","cited_by_count":14,"area":"lr"},{"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":"2306.14462","title":"Multi-task Item-attribute Graph Pre-training for Strict Cold-start Item Recommendation","created":"2023-06-26","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":"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":"2406.02996","title":"Quantifying Task Priority for Multi-Task Optimization","created":"2024-06-05","cited_by_count":11,"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":"2501.15556","title":"Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning","created":"2025-01-26","cited_by_count":9,"area":null},{"id":"2406.09353","title":"Enhancing Domain Adaptation through Prompt Gradient Alignment","created":"2024-06-13","cited_by_count":8,"area":"mllm"},{"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":"2308.05508","title":"Multi-domain Recommendation with Embedding Disentangling and Domain Alignment","created":"2023-08-10","cited_by_count":7,"area":null},{"id":"2410.14633","title":"Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning","created":"2024-10-18","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":"2212.06645","title":"Do Text-to-Text Multi-Task Learners Suffer from Task Conflict?","created":"2022-12-13","cited_by_count":6,"area":null},{"id":"2306.04519","title":"Sample-Level Weighting for Multi-Task Learning with Auxiliary Tasks","created":"2023-06-07","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":"2408.07985","title":"Analytical Uncertainty-Based Loss Weighting in Multi-Task Learning","created":"2024-08-15","cited_by_count":6,"area":null},{"id":"2511.07106","title":"HENet++: Hybrid Encoding and Multi-task Learning for 3D Perception and End-to-end Autonomous Driving","created":"2025-11-10","cited_by_count":6,"area":"driving"},{"id":"2303.06679","title":"RotoGBML: Towards Out-of-Distribution Generalization for Gradient-Based Meta-Learning","created":"2023-03-12","cited_by_count":5,"area":null},{"id":"2309.17450","title":"Multi-task View Synthesis with Neural Radiance Fields","created":"2023-09-29","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":"2510.22124","title":"Efficient Utility-Preserving Machine Unlearning with Implicit Gradient Surgery","created":"2025-10-25","cited_by_count":5,"area":"safety"},{"id":"2210.09496","title":"CEIP: Combining Explicit and Implicit Priors for Reinforcement Learning with Demonstrations","created":"2022-10-18","cited_by_count":4,"area":null},{"id":"2504.06664","title":"SEE: Continual Fine-tuning with Sequential Ensemble of Experts","created":"2025-04-09","cited_by_count":4,"area":null},{"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":"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":"2308.11928","title":"OFVL-MS: Once for Visual Localization across Multiple Indoor Scenes","created":"2023-08-23","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":"2410.02845","title":"Towards Layer-Wise Personalized Federated Learning: Adaptive Layer Disentanglement via Conflicting Gradients","created":"2024-10-03","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":"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":"2311.04698","title":"Examining Common Paradigms in Multi-Task Learning","created":"2023-11-08","cited_by_count":2,"area":null},{"id":"2408.14677","title":"Can Optimization Trajectories Explain Multi-Task Transfer?","created":"2024-08-26","cited_by_count":2,"area":null},{"id":"2411.11871","title":"MultiBalance: Multi-Objective Gradient Balancing in Industrial-Scale Multi-Task Recommendation System","created":"2024-11-03","cited_by_count":2,"area":null},{"id":"2412.07980","title":"TTVD: Towards a Geometric Framework for Test-Time Adaptation Based on Voronoi Diagram","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2412.08922","title":"Nested Hash Layer: A Plug-and-play Module for Multiple-length Hash Code Learning","created":"2024-12-12","cited_by_count":2,"area":null},{"id":"2505.23595","title":"DeepChest: Dynamic Gradient-Free Task Weighting for Effective Multi-Task Learning in Chest X-ray Classification","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2507.21049","title":"Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning","created":"2025-07-28","cited_by_count":2,"area":null},{"id":"2510.18258","title":"NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2105.03923","title":"CASA: Bridging the Gap between Policy Improvement and Policy Evaluation with Conflict Averse Policy Iteration","created":"2021-05-09","cited_by_count":1,"area":null},{"id":"2111.10601","title":"Deep Safe Multi-Task Learning","created":"2021-11-20","cited_by_count":1,"area":null},{"id":"2205.02979","title":"Explaining the Effectiveness of Multi-Task Learning for Efficient Knowledge Extraction from Spine MRI Reports","created":"2022-05-06","cited_by_count":1,"area":null},{"id":"2209.11892","title":"Highly Scalable Task Grouping for Deep Multi-Task Learning in Prediction of Epigenetic Events","created":"2022-09-24","cited_by_count":1,"area":null},{"id":"2402.03557","title":"Robust Analysis of Multi-Task Learning Efficiency: New Benchmarks on Light-Weighed Backbones and Effective Measurement of Multi-Task Learning Challenges by Feature Disentanglement","created":"2024-02-05","cited_by_count":1,"area":null},{"id":"2412.12092","title":"No More Tuning: Prioritized Multi-Task Learning with Lagrangian Differential Multiplier Methods","created":"2024-12-16","cited_by_count":1,"area":null},{"id":"2503.03438","title":"Gradient Deconfliction via Orthogonal Projections onto Subspaces For Multi-task Learning","created":"2025-03-05","cited_by_count":1,"area":null},{"id":"2507.07883","title":"SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation","created":"2025-07-10","cited_by_count":1,"area":null},{"id":"2601.10779","title":"Unified Optimization of Source Weights and Transfer Quantities in Multi-Source Transfer Learning: An Asymptotic Framework","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2603.00978","title":"EraseAnything++: Enabling Concept Erasure in Rectified Flow Transformers Leveraging Multi-Object Optimization","created":"2026-03-01","cited_by_count":1,"area":"diffusion"},{"id":"2605.01420","title":"Artificial Jagged Intelligence as Uneven Optimization Energy Allocation Capability Concentration, Redistribution, and Optimization Governance","created":"2026-05-02","cited_by_count":1,"area":null},{"id":"2605.10136","title":"Per-Loss Adapters for Gradient Conflict in Physics-Informed Neural Networks","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2302.10437","title":"Two-in-one Knowledge Distillation for Efficient Facial Forgery Detection","created":"2023-02-21","cited_by_count":0,"area":"distill"},{"id":"2308.12949","title":"Label Budget Allocation in Multi-Task Learning","created":"2023-08-24","cited_by_count":0,"area":null},{"id":"2404.05393","title":"PAT: Pixel-wise Adaptive Training for Long-tailed Segmentation","created":"2024-04-08","cited_by_count":0,"area":null},{"id":"2410.15875","title":"Enabling Asymmetric Knowledge Transfer in Multi-Task Learning with Self-Auxiliaries","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2503.09144","title":"Efficient UAV Swarm-Based Multi-Task Federated Learning with Dynamic Task Knowledge Sharing","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2505.06630","title":"Dynamic Domain Information Modulation Algorithm for Multi-domain Sentiment Analysis","created":"2025-05-10","cited_by_count":0,"area":null},{"id":"2505.10347","title":"Uniform Loss vs. Specialized Optimization: A Comparative Analysis in Multi-Task Learning","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2605.05660","title":"From Dual Tracking to Clipping: Provably Faster Distributionally Robust Multi-Objective Optimization","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.12752","title":"Low-Rank Adapters Initialization via Gradient Surgery for Continual Learning","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.03904","title":"MAdam: Metric-Aware Multi-Objective Adam","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.05107","title":"Who Needs Labels? Adapting Vision Foundation Models With the Metadata You Already Have","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.30011","title":"T3R: Deeper Test-Time Adaptation for Graph Neural Networks via Gradient Rotation","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2606.30370","title":"MUSE: Unlocking Timestep as Native Task Steering for One-Step Dense Prediction","created":"2026-06-29","cited_by_count":0,"area":"diffusion"},{"id":"2610.13693","title":"Calibration in One Go: Jointly Learning Accurate and Calibrated Neural Networks","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}