{"total":731,"rows":[{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780,"area":null},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459,"area":null},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454,"area":null},{"id":"2307.14334","title":"Towards Generalist Biomedical AI","created":"2023-07-26","cited_by_count":289,"area":null},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284,"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":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","cited_by_count":209,"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":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174,"area":null},{"id":"2302.02318","title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","created":"2023-02-05","cited_by_count":164,"area":null},{"id":"2101.11517","title":"Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond","created":"2021-01-27","cited_by_count":153,"area":null},{"id":"2409.20537","title":"Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers","created":"2024-09-30","cited_by_count":148,"area":null},{"id":"2303.02861","title":"Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning","created":"2023-03-06","cited_by_count":115,"area":null},{"id":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110,"area":null},{"id":"2302.00883","title":"Synthesizing Physical Character-Scene Interactions","created":"2023-02-02","cited_by_count":104,"area":null},{"id":"2106.03598","title":"SciFive: a text-to-text transformer model for biomedical literature","created":"2021-05-28","cited_by_count":99,"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":"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":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2104.12668","title":"Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark","created":"2021-04-26","cited_by_count":82,"area":null},{"id":"2111.12933","title":"ML-Decoder: Scalable and Versatile Classification Head","created":"2021-11-25","cited_by_count":79,"area":null},{"id":"2101.11427","title":"One Model to Serve All: Star Topology Adaptive Recommender for Multi-Domain CTR Prediction","created":"2021-01-27","cited_by_count":78,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2206.02096","title":"PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding","created":"2022-06-05","cited_by_count":77,"area":null},{"id":"2111.06719","title":"On Transferability of Prompt Tuning for Natural Language Processing","created":"2021-11-12","cited_by_count":75,"area":null},{"id":"2305.14961","title":"Deep Learning for Survival Analysis: A Review","created":"2023-05-24","cited_by_count":75,"area":null},{"id":"2104.04132","title":"Replay in Deep Learning: Current Approaches and Missing Biological Elements","created":"2021-04-01","cited_by_count":72,"area":null},{"id":"2305.19000","title":"Independent Component Alignment for Multi-Task Learning","created":"2023-05-30","cited_by_count":70,"area":null},{"id":"2203.02910","title":"Exploring Dual-task Correlation for Pose Guided Person Image Generation","created":"2022-03-06","cited_by_count":68,"area":null},{"id":"2302.01838","title":"vMAP: Vectorised Object Mapping for Neural Field SLAM","created":"2023-02-03","cited_by_count":67,"area":null},{"id":"2312.06505","title":"Grounded Question-Answering in Long Egocentric Videos","created":"2023-12-11","cited_by_count":64,"area":null},{"id":"2109.12068","title":"AraT5: Text-to-Text Transformers for Arabic Language Generation","created":"2021-08-31","cited_by_count":63,"area":null},{"id":"2204.13861","title":"Where in the World is this Image? Transformer-based Geo-localization in the Wild","created":"2022-04-29","cited_by_count":58,"area":null},{"id":"2307.05845","title":"PIGEON: Predicting Image Geolocations","created":"2023-07-11","cited_by_count":56,"area":null},{"id":"2309.01429","title":"Adapting Segment Anything Model for Change Detection in HR Remote Sensing Images","created":"2023-09-04","cited_by_count":56,"area":null},{"id":"2101.12002","title":"Copula-based conformal prediction for Multi-Target Regression","created":"2021-01-28","cited_by_count":53,"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":"2106.09017","title":"Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation","created":"2021-06-16","cited_by_count":50,"area":null},{"id":"2202.01889","title":"Generalizing to New Physical Systems via Context-Informed Dynamics Model","created":"2022-02-01","cited_by_count":50,"area":null},{"id":"2202.06689","title":"CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences","created":"2022-02-14","cited_by_count":50,"area":null},{"id":"2301.13868","title":"PADL: Language-Directed Physics-Based Character Control","created":"2023-01-31","cited_by_count":48,"area":null},{"id":"2109.03465","title":"A Survey of Sound Source Localization with Deep Learning Methods","created":"2021-09-08","cited_by_count":46,"area":null},{"id":"2204.08997","title":"A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets","created":"2022-04-19","cited_by_count":45,"area":null},{"id":"2205.10475","title":"DeepStruct: Pretraining of Language Models for Structure Prediction","created":"2022-05-21","cited_by_count":45,"area":null},{"id":"2111.14893","title":"Learning Multiple Dense Prediction Tasks from Partially Annotated Data","created":"2021-11-29","cited_by_count":42,"area":null},{"id":"2204.03508","title":"A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods","created":"2022-04-07","cited_by_count":42,"area":null},{"id":"2402.02511","title":"PoCo: Policy Composition from and for Heterogeneous Robot Learning","created":"2024-02-04","cited_by_count":42,"area":null},{"id":"2105.08489","title":"Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising","created":"2021-05-18","cited_by_count":39,"area":null},{"id":"2301.10034","title":"Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction","created":"2023-01-21","cited_by_count":39,"area":null},{"id":"2203.00077","title":"One Model is All You Need: Multi-Task Learning Enables Simultaneous Histology Image Segmentation and Classification","created":"2022-02-28","cited_by_count":38,"area":null},{"id":"2408.09446","title":"Parameterized Physics-informed Neural Networks for Parameterized PDEs","created":"2024-08-18","cited_by_count":38,"area":null},{"id":"2104.01785","title":"Annotating Columns with Pre-trained Language Models","created":"2021-04-05","cited_by_count":37,"area":null},{"id":"2207.10430","title":"The Neural Race Reduction: Dynamics of Abstraction in Gated Networks","created":"2022-07-21","cited_by_count":37,"area":null},{"id":"2302.12692","title":"Language Models are Few-shot Learners for Prognostic Prediction","created":"2023-02-24","cited_by_count":37,"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":"2210.02016","title":"Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization","created":"2022-10-05","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":"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":"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":"2206.02659","title":"Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees","created":"2022-06-06","cited_by_count":34,"area":null},{"id":"2209.05310","title":"On the Factory Floor: ML Engineering for Industrial-Scale Ads Recommendation Models","created":"2022-09-12","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":"2310.18955","title":"Optimal Algorithms for Online Convex Optimization with Adversarial Constraints","created":"2023-10-29","cited_by_count":34,"area":null},{"id":"2301.02657","title":"TarViS: A Unified Approach for Target-based Video Segmentation","created":"2023-01-06","cited_by_count":33,"area":null},{"id":"2305.16373","title":"DeepGate2: Functionality-Aware Circuit Representation Learning","created":"2023-05-25","cited_by_count":33,"area":null},{"id":"2310.07365","title":"GraphControl: Adding Conditional Control to Universal Graph Pre-trained Models for Graph Domain Transfer Learning","created":"2023-10-11","cited_by_count":33,"area":null},{"id":"2403.05890","title":"Towards Efficient Replay in Federated Incremental Learning","created":"2024-03-09","cited_by_count":33,"area":null},{"id":"2202.12891","title":"Combining Observational and Randomized Data for Estimating Heterogeneous Treatment Effects","created":"2022-02-25","cited_by_count":32,"area":null},{"id":"2206.04496","title":"Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization","created":"2022-06-09","cited_by_count":32,"area":null},{"id":"2212.11696","title":"Reversible Column Networks","created":"2022-12-22","cited_by_count":32,"area":null},{"id":"2309.07835","title":"Learning to Warm-Start Fixed-Point Optimization Algorithms","created":"2023-09-14","cited_by_count":32,"area":null},{"id":"2109.04778","title":"Improving Multilingual Translation by Representation and Gradient Regularization","created":"2021-09-10","cited_by_count":31,"area":null},{"id":"2203.01311","title":"High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning","created":"2022-03-02","cited_by_count":31,"area":null},{"id":"2206.09262","title":"Motley: Benchmarking Heterogeneity and Personalization in Federated Learning","created":"2022-06-18","cited_by_count":31,"area":null},{"id":"2406.16797","title":"Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs","created":"2024-06-24","cited_by_count":31,"area":null},{"id":"2112.08619","title":"Call for Customized Conversation: Customized Conversation Grounding Persona and Knowledge","created":"2021-12-16","cited_by_count":30,"area":null},{"id":"2305.07348","title":"A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospects","created":"2023-05-12","cited_by_count":30,"area":null},{"id":"2308.12241","title":"LLMRec: Benchmarking Large Language Models on Recommendation Task","created":"2023-08-23","cited_by_count":30,"area":null},{"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":"2301.02152","title":"L-HYDRA: Multi-Head Physics-Informed Neural Networks","created":"2023-01-05","cited_by_count":29,"area":null},{"id":"2104.02443","title":"CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computing","created":"2021-04-06","cited_by_count":28,"area":null},{"id":"2106.08657","title":"Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion","created":"2021-06-16","cited_by_count":28,"area":null},{"id":"2401.13544","title":"Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?","created":"2024-01-24","cited_by_count":28,"area":null},{"id":"2503.18211","title":"SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction","created":"2025-03-23","cited_by_count":27,"area":null},{"id":"2109.07437","title":"Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative","created":"2021-09-15","cited_by_count":26,"area":null},{"id":"2210.16822","title":"Towards Versatile Embodied Navigation","created":"2022-10-30","cited_by_count":26,"area":null},{"id":"2105.04051","title":"Aggregating From Multiple Target-Shifted Sources","created":"2021-05-09","cited_by_count":24,"area":null},{"id":"2110.08890","title":"Network Augmentation for Tiny Deep Learning","created":"2021-10-17","cited_by_count":24,"area":null},{"id":"2305.14224","title":"mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations","created":"2023-05-23","cited_by_count":24,"area":null},{"id":"2202.12950","title":"2021 BEETL Competition: Advancing Transfer Learning for Subject Independence & Heterogenous EEG Data Sets","created":"2022-02-14","cited_by_count":23,"area":null},{"id":"2204.02744","title":"Universal Representations: A Unified Look at Multiple Task and Domain Learning","created":"2022-04-06","cited_by_count":23,"area":null},{"id":"2205.11728","title":"ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterest","created":"2022-05-24","cited_by_count":23,"area":null},{"id":"2210.07886","title":"PedFormer: Pedestrian Behavior Prediction via Cross-Modal Attention Modulation and Gated Multitask Learning","created":"2022-10-14","cited_by_count":23,"area":null},{"id":"2302.11070","title":"Universal Morphology Control via Contextual Modulation","created":"2023-02-22","cited_by_count":23,"area":null},{"id":"2402.18922","title":"A Simple yet Effective Network based on Vision Transformer for Camouflaged Object and Salient Object Detection","created":"2024-02-29","cited_by_count":23,"area":null}],"next_cursor":"100"}