{"total":1256,"rows":[{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613,"area":null},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532,"area":null},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478,"area":"wm"},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459,"area":null},{"id":"2205.14865","title":"Prompt-aligned Gradient for Prompt Tuning","created":"2022-05-30","cited_by_count":341,"area":"mllm"},{"id":"2111.02387","title":"An Empirical Study of Training End-to-End Vision-and-Language Transformers","created":"2021-11-03","cited_by_count":271,"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":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253,"area":null},{"id":"2310.02575","title":"AdaMerging: Adaptive Model Merging for Multi-Task Learning","created":"2023-10-04","cited_by_count":252,"area":null},{"id":"2109.13396","title":"Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets","created":"2021-09-27","cited_by_count":250,"area":null},{"id":"2303.09556","title":"Efficient Diffusion Training via Min-SNR Weighting Strategy","created":"2023-03-16","cited_by_count":246,"area":"diffusion"},{"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":"2104.08212","title":"MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale","created":"2021-04-16","cited_by_count":229,"area":null},{"id":"2109.04617","title":"Efficiently Identifying Task Groupings for Multi-Task Learning","created":"2021-09-10","cited_by_count":222,"area":null},{"id":"2202.01017","title":"Multi-Task Learning as a Bargaining Game","created":"2022-02-02","cited_by_count":215,"area":null},{"id":"2205.09743","title":"BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving","created":"2022-05-19","cited_by_count":191,"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":"2309.01918","title":"RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking","created":"2023-09-05","cited_by_count":169,"area":null},{"id":"2105.03790","title":"Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study","created":"2021-05-08","cited_by_count":168,"area":null},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161,"area":null},{"id":"2408.10075","title":"Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning","created":"2024-08-19","cited_by_count":155,"area":"alignment"},{"id":"2406.08394","title":"VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks","created":"2024-06-12","cited_by_count":137,"area":"mllm"},{"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":"2107.00644","title":"Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation","created":"2021-07-01","cited_by_count":105,"area":null},{"id":"2302.06600","title":"Task-Specific Skill Localization in Fine-tuned Language Models","created":"2023-02-13","cited_by_count":105,"area":null},{"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":"2210.14793","title":"M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design","created":"2022-10-26","cited_by_count":98,"area":"moe"},{"id":"2310.02994","title":"Multiple Physics Pretraining for Physical Surrogate Models","created":"2023-10-04","cited_by_count":98,"area":null},{"id":"2402.02705","title":"Representation Surgery for Multi-Task Model Merging","created":"2024-02-05","cited_by_count":96,"area":null},{"id":"2104.11203","title":"Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention","created":"2021-04-22","cited_by_count":95,"area":null},{"id":"2311.01223","title":"Diffusion Models for Reinforcement Learning: A Survey","created":"2023-11-02","cited_by_count":91,"area":"diffusion"},{"id":"2104.05489","title":"Continual Learning for Text Classification with Information Disentanglement Based Regularization","created":"2021-04-12","cited_by_count":86,"area":null},{"id":"2108.11353","title":"Multi-Task Self-Training for Learning General Representations","created":"2021-08-25","cited_by_count":85,"area":null},{"id":"2103.02631","title":"RotoGrad: Gradient Homogenization in Multitask Learning","created":"2021-03-03","cited_by_count":83,"area":null},{"id":"2406.11011","title":"Data Shapley in One Training Run","created":"2024-06-16","cited_by_count":81,"area":null},{"id":"2306.03792","title":"FAMO: Fast Adaptive Multitask Optimization","created":"2023-06-06","cited_by_count":78,"area":null},{"id":"2210.11435","title":"Learning and Retrieval from Prior Data for Skill-based Imitation Learning","created":"2022-10-20","cited_by_count":77,"area":"offlinerl"},{"id":"2202.03091","title":"Auto-Lambda: Disentangling Dynamic Task Relationships","created":"2022-02-07","cited_by_count":73,"area":null},{"id":"2211.15144","title":"Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes","created":"2022-11-28","cited_by_count":73,"area":"offlinerl"},{"id":"2405.17730","title":"MMPareto: Boosting Multimodal Learning with Innocent Unimodal Assistance","created":"2024-05-28","cited_by_count":73,"area":null},{"id":"2209.08776","title":"NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes","created":"2022-09-19","cited_by_count":71,"area":null},{"id":"2305.19000","title":"Independent Component Alignment for Multi-Task Learning","created":"2023-05-30","cited_by_count":70,"area":null},{"id":"2405.15304","title":"Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient","created":"2024-05-24","cited_by_count":69,"area":"diffusion"},{"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":"2207.11707","title":"Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes","created":"2022-07-24","cited_by_count":67,"area":null},{"id":"2109.08128","title":"Conservative Data Sharing for Multi-Task Offline Reinforcement Learning","created":"2021-09-16","cited_by_count":64,"area":"offlinerl"},{"id":"2507.22062","title":"Meta CLIP 2: A Worldwide Scaling Recipe","created":"2025-07-29","cited_by_count":64,"area":"mllm"},{"id":"2311.04661","title":"Massive Editing for Large Language Models via Meta Learning","created":"2023-11-08","cited_by_count":63,"area":null},{"id":"2109.09138","title":"Multi-Task Learning in Natural Language Processing: An Overview","created":"2021-09-19","cited_by_count":62,"area":null},{"id":"2104.14937","title":"Federated Learning with Fair Averaging","created":"2021-04-30","cited_by_count":61,"area":null},{"id":"2108.01621","title":"Domain Generalization via Gradient Surgery","created":"2021-08-03","cited_by_count":60,"area":null},{"id":"2209.11379","title":"Do Current Multi-Task Optimization Methods in Deep Learning Even Help?","created":"2022-09-23","cited_by_count":60,"area":null},{"id":"2401.01219","title":"Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyond","created":"2024-01-02","cited_by_count":60,"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":"2205.03346","title":"Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection","created":"2022-05-06","cited_by_count":59,"area":null},{"id":"2111.01872","title":"Towards Fairness-Aware Federated Learning","created":"2021-11-02","cited_by_count":58,"area":null},{"id":"2111.12993","title":"PolyViT: Co-training Vision Transformers on Images, Videos and Audio","created":"2021-11-25","cited_by_count":58,"area":null},{"id":"2206.04674","title":"Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs","created":"2022-06-09","cited_by_count":58,"area":"moe"},{"id":"2103.13841","title":"Universal Representation Learning from Multiple Domains for Few-shot Classification","created":"2021-03-25","cited_by_count":56,"area":null},{"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":"2212.01378","title":"ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning","created":"2022-12-02","cited_by_count":52,"area":null},{"id":"2406.09406","title":"4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities","created":"2024-06-13","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":"2308.13985","title":"Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective","created":"2023-08-27","cited_by_count":51,"area":null},{"id":"2111.03062","title":"Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning","created":"2021-11-04","cited_by_count":50,"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":"2203.08392","title":"Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?","created":"2022-03-16","cited_by_count":49,"area":null},{"id":"2311.11385","title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts","created":"2023-11-19","cited_by_count":49,"area":null},{"id":"2303.04222","title":"SemEval-2023 Task 10: Explainable Detection of Online Sexism","created":"2023-03-07","cited_by_count":48,"area":null},{"id":"2210.11653","title":"PaCo: Parameter-Compositional Multi-Task Reinforcement Learning","created":"2022-10-21","cited_by_count":46,"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":"2106.02940","title":"Same State, Different Task: Continual Reinforcement Learning without Interference","created":"2021-06-05","cited_by_count":43,"area":null},{"id":"2505.11289","title":"Meta-World+: An Improved, Standardized, RL Benchmark","created":"2025-05-16","cited_by_count":43,"area":"deeprl"},{"id":"2111.14893","title":"Learning Multiple Dense Prediction Tasks from Partially Annotated Data","created":"2021-11-29","cited_by_count":42,"area":null},{"id":"2306.03805","title":"The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter","created":"2023-06-06","cited_by_count":42,"area":null},{"id":"2211.02219","title":"Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models","created":"2022-11-04","cited_by_count":40,"area":"mllm"},{"id":"2312.03731","title":"MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphs","created":"2023-11-28","cited_by_count":40,"area":null},{"id":"2102.07121","title":"Multi-Objective Meta Learning","created":"2021-02-14","cited_by_count":39,"area":null},{"id":"2310.16802","title":"From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Prediction","created":"2023-10-25","cited_by_count":39,"area":null},{"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":"2509.17940","title":"DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving","created":"2025-09-22","cited_by_count":39,"area":"driving"},{"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":"2101.08578","title":"MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks","created":"2021-01-21","cited_by_count":36,"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":"2110.12257","title":"Game of Gradients: Mitigating Irrelevant Clients in Federated Learning","created":"2021-10-23","cited_by_count":35,"area":null},{"id":"2304.07987","title":"Chinese Open Instruction Generalist: A Preliminary Release","created":"2023-04-17","cited_by_count":35,"area":null},{"id":"2402.15638","title":"Fair Resource Allocation in Multi-Task Learning","created":"2024-02-23","cited_by_count":35,"area":null},{"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":"2106.02705","title":"Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learning","created":"2021-06-04","cited_by_count":34,"area":null},{"id":"2109.09180","title":"Lifelong Robotic Reinforcement Learning by Retaining Experiences","created":"2021-09-19","cited_by_count":34,"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":"2305.18409","title":"Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms","created":"2023-05-28","cited_by_count":34,"area":null},{"id":"2107.12931","title":"Autonomous Reinforcement Learning via Subgoal Curricula","created":"2021-07-27","cited_by_count":33,"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}],"next_cursor":"100"}