{"list":"other","total":143,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1706.07522","title":"Deep Hashing Network for Unsupervised Domain Adaptation","created":"2017-06-22","cited_by_count":1188},{"id":"1609.09106","title":"HyperNetworks","created":"2016-09-27","cited_by_count":1027},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"2003.11080","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","created":"2020-03-24","cited_by_count":742},{"id":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"1608.04471","title":"Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm","created":"2016-08-16","cited_by_count":507},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459},{"id":"2306.01693","title":"Fine-Grained Human Feedback Gives Better Rewards for Language Model Training","created":"2023-06-02","cited_by_count":401},{"id":"1905.07553","title":"Which Tasks Should Be Learned Together in Multi-task Learning?","created":"2019-05-18","cited_by_count":375},{"id":"2009.09796","title":"Multi-Task Learning with Deep Neural Networks: A Survey","created":"2020-09-10","cited_by_count":375},{"id":"2310.11564","title":"Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging","created":"2023-10-17","cited_by_count":280},{"id":"2406.15513","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference","created":"2024-06-20","cited_by_count":261},{"id":"2006.02903","title":"A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions","created":"2020-06-01","cited_by_count":254},{"id":"2303.09556","title":"Efficient Diffusion Training via Min-SNR Weighting Strategy","created":"2023-03-16","cited_by_count":246},{"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},{"id":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237},{"id":"2406.08673","title":"HelpSteer2: Open-source dataset for training top-performing reward models","created":"2024-06-12","cited_by_count":236},{"id":"1912.12854","title":"Pareto Multi-Task Learning","created":"2019-12-30","cited_by_count":224},{"id":"2202.01017","title":"Multi-Task Learning as a Bargaining Game","created":"2022-02-02","cited_by_count":215},{"id":"2010.06808","title":"Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout","created":"2020-10-14","cited_by_count":201},{"id":"2006.05078","title":"Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization","created":"2020-06-09","cited_by_count":179},{"id":"2402.10207","title":"Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment","created":"2024-02-15","cited_by_count":175},{"id":"2010.05874","title":"Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models","created":"2020-10-12","cited_by_count":169},{"id":"2011.01821","title":"Minimax Pareto Fairness: A Multi Objective Perspective","created":"2020-11-03","cited_by_count":153},{"id":"2310.20708","title":"Unexpected Improvements to Expected Improvement for Bayesian Optimization","created":"2023-10-31","cited_by_count":149},{"id":"2402.18571","title":"Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards","created":"2024-02-28","cited_by_count":148},{"id":"2010.04104","title":"Learning the Pareto Front with Hypernetworks","created":"2020-10-08","cited_by_count":125},{"id":"2310.03708","title":"Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization","created":"2023-10-05","cited_by_count":124},{"id":"2105.08195","title":"Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvement","created":"2021-05-17","cited_by_count":118},{"id":"2402.19085","title":"Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment","created":"2024-02-29","cited_by_count":107},{"id":"2111.10603","title":"Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning","created":"2021-11-20","cited_by_count":101},{"id":"2210.12765","title":"Multi-Objective GFlowNets","created":"2022-10-23","cited_by_count":101},{"id":"1805.12168","title":"A Flexible Framework for Multi-Objective Bayesian Optimization using Random Scalarizations","created":"2018-05-30","cited_by_count":99},{"id":"2406.18853","title":"Decoding-Time Language Model Alignment with Multiple Objectives","created":"2024-06-27","cited_by_count":94},{"id":"1906.02386","title":"Deep Reinforcement Learning for Multi-objective Optimization","created":"2019-06-06","cited_by_count":90},{"id":"2203.07997","title":"InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding","created":"2022-03-15","cited_by_count":89},{"id":"1511.05467","title":"Predictive Entropy Search for Multi-objective Bayesian Optimization","created":"2015-11-17","cited_by_count":88},{"id":"2109.10964","title":"Multi-Objective Bayesian Optimization over High-Dimensional Search Spaces","created":"2021-09-22","cited_by_count":87},{"id":"2009.01721","title":"Max-value Entropy Search for Multi-Objective Bayesian Optimization with Constraints","created":"2020-09-01","cited_by_count":81},{"id":"2402.02030","title":"Panacea: Pareto Alignment via Preference Adaptation for LLMs","created":"2024-02-03","cited_by_count":80},{"id":"2306.03792","title":"FAMO: Fast Adaptive Multitask Optimization","created":"2023-06-06","cited_by_count":78},{"id":"2202.03091","title":"Auto-Lambda: Disentangling Dynamic Task Relationships","created":"2022-02-07","cited_by_count":73},{"id":"2011.09011","title":"AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling","created":"2020-11-18","cited_by_count":66},{"id":"2109.09138","title":"Multi-Task Learning in Natural Language Processing: An Overview","created":"2021-09-19","cited_by_count":62},{"id":"2006.04655","title":"Random Hypervolume Scalarizations for Provable Multi-Objective Black Box Optimization","created":"2020-06-08","cited_by_count":60},{"id":"2106.07991","title":"A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization","created":"2021-06-15","cited_by_count":60},{"id":"2208.07914","title":"PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm","created":"2022-08-16","cited_by_count":58},{"id":"1906.00127","title":"Multi-objective Bayesian Optimization using Pareto-frontier Entropy","created":"2019-06-01","cited_by_count":57},{"id":"2006.16434","title":"Efficient Continuous Pareto Exploration in Multi-Task Learning","created":"2020-06-29","cited_by_count":57},{"id":"2203.15386","title":"Pareto Set Learning for Neural Multi-objective Combinatorial Optimization","created":"2022-03-29","cited_by_count":56},{"id":"2206.04771","title":"Joint Entropy Search for Maximally-Informed Bayesian Optimization","created":"2022-06-09","cited_by_count":55},{"id":"2402.19078","title":"Smooth Tchebycheff Scalarization for Multi-Objective Optimization","created":"2024-02-29","cited_by_count":54},{"id":"2006.11489","title":"Federated Learning Meets Multi-objective Optimization","created":"2020-06-20","cited_by_count":53},{"id":"2010.06313","title":"Controllable Pareto Multi-Task Learning","created":"2020-10-13","cited_by_count":51},{"id":"2210.08495","title":"Pareto Set Learning for Expensive Multi-Objective Optimization","created":"2022-10-16","cited_by_count":51},{"id":"2308.13985","title":"Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective","created":"2023-08-27","cited_by_count":51},{"id":"2106.09017","title":"Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation","created":"2021-06-16","cited_by_count":50},{"id":"2302.04040","title":"Sample-efficient Multi-objective Molecular Optimization with GFlowNets","created":"2023-02-08","cited_by_count":50},{"id":"2104.10753","title":"Multi-task Learning with Attention for End-to-end Autonomous Driving","created":"2021-04-21","cited_by_count":49},{"id":"1907.04472","title":"The stochastic multi-gradient algorithm for multi-objective optimization and its application to supervised machine learning","created":"2019-07-10","cited_by_count":46},{"id":"2408.11104","title":"ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks","created":"2024-08-20","cited_by_count":46},{"id":"2103.13392","title":"Scalable Pareto Front Approximation for Deep Multi-Objective Learning","created":"2021-03-24","cited_by_count":45},{"id":"2210.02905","title":"Joint Entropy Search for Multi-objective Bayesian Optimization","created":"2022-10-06","cited_by_count":45},{"id":"2204.05944","title":"Uncertainty-Aware Search Framework for Multi-Objective Bayesian Optimization","created":"2022-04-12","cited_by_count":44},{"id":"2306.01264","title":"Convex and Non-convex Optimization Under Generalized Smoothness","created":"2023-06-02","cited_by_count":44},{"id":"2102.07121","title":"Multi-Objective Meta Learning","created":"2021-02-14","cited_by_count":39},{"id":"2305.00567","title":"Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL","created":"2023-04-30","cited_by_count":36},{"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},{"id":"2402.15638","title":"Fair Resource Allocation in Multi-Task Learning","created":"2024-02-23","cited_by_count":35},{"id":"2305.18409","title":"Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms","created":"2023-05-28","cited_by_count":34},{"id":"2306.00354","title":"Addressing Negative Transfer in Diffusion Models","created":"2023-06-01","cited_by_count":33},{"id":"2311.12495","title":"Multi-Objective Reinforcement Learning Based on Decomposition: A Taxonomy and Framework","created":"2023-11-21","cited_by_count":31},{"id":"2201.00140","title":"Toward Pareto Efficient Fairness-Utility Trade-off inRecommendation through Reinforcement Learning","created":"2022-01-01","cited_by_count":29},{"id":"2210.09759","title":"Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models","created":"2022-10-18","cited_by_count":29},{"id":"2308.12029","title":"Dual-Balancing for Multi-Task Learning","created":"2023-08-23","cited_by_count":27},{"id":"2404.18961","title":"Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Eras","created":"2024-04-29","cited_by_count":26},{"id":"1904.12672","title":"Efficient Computation of Expected Hypervolume Improvement Using Box Decomposition Algorithms","created":"2019-04-26","cited_by_count":24},{"id":"2204.02744","title":"Universal Representations: A Unified Look at Multiple Task and Domain Learning","created":"2022-04-06","cited_by_count":23},{"id":"2407.02228","title":"MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders","created":"2024-07-02","cited_by_count":22},{"id":"2203.14949","title":"Controllable Dynamic Multi-Task Architectures","created":"2022-03-28","cited_by_count":21},{"id":"2310.15196","title":"Efficient Meta Neural Heuristic for Multi-Objective Combinatorial Optimization","created":"2023-10-22","cited_by_count":21},{"id":"2409.18426","title":"Dual Cone Gradient Descent for Training Physics-Informed Neural Networks","created":"2024-09-27","cited_by_count":21},{"id":"2001.00846","title":"Multi-Gradient Descent for Multi-Objective Recommender Systems","created":"2019-12-09","cited_by_count":20},{"id":"2501.06773","title":"Pareto Set Learning for Multi-Objective Reinforcement Learning","created":"2025-01-12","cited_by_count":20},{"id":"2406.16232","title":"Jacobian Descent for Multi-Objective Optimization","created":"2024-06-23","cited_by_count":18}],"next_cursor":"100"}