{"total":86,"rows":[{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613,"area":null},{"id":"2202.01017","title":"Multi-Task Learning as a Bargaining Game","created":"2022-02-02","cited_by_count":215,"area":null},{"id":"2109.02934","title":"Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization","created":"2021-09-07","cited_by_count":186,"area":null},{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174,"area":null},{"id":"2105.10919","title":"Continual World: A Robotic Benchmark For Continual Reinforcement Learning","created":"2021-05-23","cited_by_count":116,"area":null},{"id":"2205.15659","title":"The CLRS Algorithmic Reasoning Benchmark","created":"2022-05-31","cited_by_count":106,"area":null},{"id":"2105.05612","title":"Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization","created":"2021-05-12","cited_by_count":83,"area":null},{"id":"2202.03091","title":"Auto-Lambda: Disentangling Dynamic Task Relationships","created":"2022-02-07","cited_by_count":73,"area":null},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57,"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":"2404.00986","title":"Make Continual Learning Stronger via C-Flat","created":"2024-04-01","cited_by_count":35,"area":null},{"id":"2203.06801","title":"MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks","created":"2022-03-14","cited_by_count":34,"area":null},{"id":"2109.06415","title":"Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction","created":"2021-09-14","cited_by_count":33,"area":null},{"id":"2107.08765","title":"Adaptive Transfer Learning on Graph Neural Networks","created":"2021-07-19","cited_by_count":31,"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":"2201.00042","title":"Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments","created":"2021-12-31","cited_by_count":25,"area":null},{"id":"2311.13209","title":"Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigation","created":"2023-11-22","cited_by_count":25,"area":null},{"id":"2203.17008","title":"It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher","created":"2022-03-31","cited_by_count":20,"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":"2203.06172","title":"Deep AutoAugment","created":"2022-03-11","cited_by_count":18,"area":null},{"id":"2306.02790","title":"Exploring the Relationship between Alignment and Cross-lingual Transfer in Multilingual Transformers","created":"2023-06-05","cited_by_count":18,"area":null},{"id":"2108.11346","title":"Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral","created":"2021-08-25","cited_by_count":17,"area":null},{"id":"2406.08811","title":"Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Models","created":"2024-06-13","cited_by_count":16,"area":null},{"id":"2203.04482","title":"Multi-Agent Policy Transfer via Task Relationship Modeling","created":"2022-03-09","cited_by_count":14,"area":null},{"id":"2302.00674","title":"Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data","created":"2023-02-01","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":"2208.11870","title":"Fix-A-Step: Semi-supervised Learning from Uncurated Unlabeled Data","created":"2022-08-25","cited_by_count":11,"area":null},{"id":"2502.07274","title":"Forget Forgetting: Continual Learning in a World of Abundant Memory","created":"2025-02-11","cited_by_count":11,"area":null},{"id":"2312.15127","title":"Gradient Shaping for Multi-Constraint Safe Reinforcement Learning","created":"2023-12-23","cited_by_count":10,"area":null},{"id":"2403.16137","title":"A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective","created":"2024-03-24","cited_by_count":9,"area":null},{"id":"2506.02011","title":"OASIS: Online Sample Selection for Continual Visual Instruction Tuning","created":"2025-05-27","cited_by_count":9,"area":null},{"id":"2205.10766","title":"Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey","created":"2022-05-22","cited_by_count":8,"area":null},{"id":"2404.03784","title":"A Layer Selection Approach to Test Time Adaptation","created":"2024-04-04","cited_by_count":7,"area":null},{"id":"2410.15143","title":"Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling","created":"2024-10-19","cited_by_count":7,"area":null},{"id":"2301.13465","title":"GDOD: Effective Gradient Descent using Orthogonal Decomposition for Multi-Task Learning","created":"2023-01-31","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":"2307.04887","title":"Measuring and Mitigating Interference in Reinforcement Learning","created":"2023-07-10","cited_by_count":5,"area":null},{"id":"2307.13337","title":"Overcoming Distribution Mismatch in Quantizing Image Super-Resolution Networks","created":"2023-07-25","cited_by_count":5,"area":null},{"id":"2501.07236","title":"CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental Learning","created":"2025-01-13","cited_by_count":5,"area":null},{"id":"2402.02998","title":"Careful with that Scalpel: Improving Gradient Surgery with an EMA","created":"2024-02-05","cited_by_count":4,"area":null},{"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":"2507.03175","title":"Understanding Knowledge Transferability for Transfer Learning: A Survey","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2110.03032","title":"Learning Multi-Objective Curricula for Robotic Policy Learning","created":"2021-10-06","cited_by_count":3,"area":null},{"id":"2209.04702","title":"Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification","created":"2022-09-10","cited_by_count":3,"area":null},{"id":"2306.01066","title":"Investigating Navigation Strategies in the Morris Water Maze through Deep Reinforcement Learning","created":"2023-06-01","cited_by_count":3,"area":null},{"id":"2107.07805","title":"Multiple Instance Learning with Auxiliary Task Weighting for Multiple Myeloma Classification","created":"2021-07-16","cited_by_count":2,"area":null},{"id":"2209.14742","title":"Learning Gradient-based Mixup with Extrapolation toward Flatter Minima for Domain Generalization","created":"2022-09-29","cited_by_count":2,"area":null},{"id":"2210.14361","title":"Auxiliary task discovery through generate-and-test","created":"2022-10-25","cited_by_count":2,"area":null},{"id":"2306.10164","title":"MultiWave: Multiresolution Deep Architectures through Wavelet Decomposition for Multivariate Time Series Prediction","created":"2023-06-16","cited_by_count":2,"area":null},{"id":"2307.06167","title":"Auxiliary-Tasks Learning for Physics-Informed Neural Network-Based Partial Differential Equations Solving","created":"2023-07-12","cited_by_count":2,"area":null},{"id":"2310.13746","title":"FairBranch: Mitigating Bias Transfer in Fair Multi-task Learning","created":"2023-10-20","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":"2601.05911","title":"Pantagruel: Unified Self-Supervised Encoders for French Text and Speech","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2103.10179","title":"Spectral Reconstruction and Disparity from Spatio-Spectrally Coded Light Fields via Multi-Task Deep Learning","created":"2021-03-18","cited_by_count":1,"area":null},{"id":"2206.08289","title":"Switchable Representation Learning Framework with Self-compatibility","created":"2022-06-16","cited_by_count":1,"area":null},{"id":"2311.16595","title":"D4AM: A General Denoising Framework for Downstream Acoustic Models","created":"2023-11-28","cited_by_count":1,"area":null},{"id":"2401.16299","title":"Enhancing Molecular Property Prediction with Auxiliary Learning and Task-Specific Adaptation","created":"2024-01-29","cited_by_count":1,"area":null},{"id":"2405.05695","title":"Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost","created":"2024-05-09","cited_by_count":1,"area":null},{"id":"2409.16651","title":"Learning Representation for Multitask learning through Self Supervised Auxiliary learning","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2412.19547","title":"Unprejudiced Training Auxiliary Tasks Makes Primary Better: A Multi-Task Learning Perspective","created":"2024-12-27","cited_by_count":1,"area":null},{"id":"2501.01114","title":"Generalized Task-Driven Medical Image Quality Enhancement with Gradient Promotion","created":"2025-01-02","cited_by_count":1,"area":null},{"id":"2505.24413","title":"Multi-task Learning for Heterogeneous Multi-source Block-Wise Missing Data","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2510.02215","title":"Improving Large-Scale Recommender Systems with Auxiliary Learning","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2603.02184","title":"MAC: A Conversion Rate Prediction Benchmark Featuring Labels Under Multiple Attribution Mechanisms","created":"2026-03-02","cited_by_count":1,"area":null},{"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":"2605.06462","title":"Measuring Structure in Graph Benchmark Datasets Using Graph Invariants","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2110.12696","title":"Self-Supervised Knowledge Transfer via Loosely Supervised Auxiliary Tasks","created":"2021-10-25","cited_by_count":0,"area":null},{"id":"2111.07279","title":"Auxiliary Loss Reweighting for Image Inpainting","created":"2021-11-14","cited_by_count":0,"area":null},{"id":"2203.02946","title":"On Steering Multi-Annotations per Sample for Multi-Task Learning","created":"2022-03-06","cited_by_count":0,"area":null},{"id":"2210.03331","title":"Resolving Class Imbalance for LiDAR-based Object Detector by Dynamic Weight Average and Contextual Ground Truth Sampling","created":"2022-10-07","cited_by_count":0,"area":null},{"id":"2211.06014","title":"Gradient Imitation Reinforcement Learning for General Low-Resource Information Extraction","created":"2022-11-11","cited_by_count":0,"area":null},{"id":"2303.14639","title":"CRRS: Concentric Rectangles Regression Strategy for Multi-point Representation on Fisheye Images","created":"2023-03-26","cited_by_count":0,"area":null},{"id":"2308.12949","title":"Label Budget Allocation in Multi-Task Learning","created":"2023-08-24","cited_by_count":0,"area":null},{"id":"2402.07119","title":"Two-Stage Multi-task Self-Supervised Learning for Medical Image Segmentation","created":"2024-02-11","cited_by_count":0,"area":null},{"id":"2402.08267","title":"Improving Image Coding for Machines through Optimizing Encoder via Auxiliary Loss","created":"2024-02-13","cited_by_count":0,"area":null},{"id":"2404.16917","title":"Grad Queue : A probabilistic framework to reinforce sparse gradients","created":"2024-04-25","cited_by_count":0,"area":null},{"id":"2405.07769","title":"$\\alpha$VIL: Learning to Leverage Auxiliary Tasks for Multitask Learning","created":"2024-05-13","cited_by_count":0,"area":null},{"id":"2505.03646","title":"Revealing Hidden Vulnerabilities in Autoencoders through Gradient Signal Restoration","created":"2025-05-06","cited_by_count":0,"area":null},{"id":"2508.20551","title":"Contrastive Learning through Auxiliary Branch for Video Object Detection","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2603.23799","title":"Resolving gradient pathology in physics-informed epidemiological models","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2604.16836","title":"Lorentz Framework for Semantic Segmentation","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.07756","title":"When Losses Align: Gradient-Based Composite Loss Weighting for Efficient Pretraining","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.25001","title":"Mitigating Gradient Pathology in PINNs through Aligned Constraint","created":"2026-05-24","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":"2609.38485","title":"Beyond Layers: Position-Resolved Gradient Conflict and Position-Aware Modulation for Unified Multimodal Models","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}