{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"2402.12354","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","created":"2024-02-19","cited_by_count":377},{"id":"2006.12983","title":"dm_control: Software and Tasks for Continuous Control","created":"2020-06-22","cited_by_count":375},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328},{"id":"2111.00210","title":"Mastering Atari Games with Limited Data","created":"2021-10-30","cited_by_count":237},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214},{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174},{"id":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174},{"id":"1909.05398","title":"Interactive Fiction Games: A Colossal Adventure","created":"2019-09-11","cited_by_count":168},{"id":"2003.13661","title":"Multi-Task Reinforcement Learning with Soft Modularization","created":"2020-03-30","cited_by_count":143},{"id":"2303.07109","title":"Transformer-based World Models Are Happy With 100k Interactions","created":"2023-03-13","cited_by_count":139},{"id":"2104.06294","title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","created":"2021-04-13","cited_by_count":90},{"id":"2312.09979","title":"LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin","created":"2023-12-15","cited_by_count":82},{"id":"2402.08609","title":"Mixtures of Experts Unlock Parameter Scaling for Deep RL","created":"2024-02-13","cited_by_count":78},{"id":"2104.06303","title":"Learning and Planning in Complex Action Spaces","created":"2021-04-13","cited_by_count":77},{"id":"2211.15144","title":"Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes","created":"2022-11-28","cited_by_count":73},{"id":"2402.19078","title":"Smooth Tchebycheff Scalarization for Multi-Objective Optimization","created":"2024-02-29","cited_by_count":54},{"id":"2208.02813","title":"Towards Understanding Mixture of Experts in Deep Learning","created":"2022-08-04","cited_by_count":52},{"id":"2302.11289","title":"Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learning","created":"2023-02-22","cited_by_count":51},{"id":"2311.11385","title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts","created":"2023-11-19","cited_by_count":49},{"id":"2210.11653","title":"PaCo: Parameter-Compositional Multi-Task Reinforcement Learning","created":"2022-10-21","cited_by_count":46},{"id":"2401.09561","title":"Sharing Knowledge in Multi-Task Deep Reinforcement Learning","created":"2024-01-17","cited_by_count":44},{"id":"2403.20320","title":"MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning","created":"2024-03-29","cited_by_count":44},{"id":"2311.11501","title":"MultiLoRA: Democratizing LoRA for Better Multi-Task Learning","created":"2023-11-20","cited_by_count":32},{"id":"2306.14884","title":"Learning to Modulate pre-trained Models in RL","created":"2023-06-26","cited_by_count":28},{"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":"2310.00344","title":"HarmonyDream: Task Harmonization Inside World Models","created":"2023-09-30","cited_by_count":22},{"id":"2402.09844","title":"Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent","created":"2024-02-15","cited_by_count":21},{"id":"2504.07448","title":"LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation","created":"2025-04-10","cited_by_count":19},{"id":"2410.09437","title":"MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning","created":"2024-10-12","cited_by_count":17},{"id":"2311.01075","title":"Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning","created":"2023-11-02","cited_by_count":10},{"id":"2312.14472","title":"Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing","created":"2023-12-22","cited_by_count":8},{"id":"2306.01839","title":"Efficient Multi-Task and Transfer Reinforcement Learning with Parameter-Compositional Framework","created":"2023-06-02","cited_by_count":7},{"id":"2311.07687","title":"Language Model-In-The-Loop: Data Optimal Approach to Learn-To-Recommend Actions in Text Games","created":"2023-11-13","cited_by_count":3},{"id":"2508.06871","title":"Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning","created":"2025-08-09","cited_by_count":2},{"id":"2402.16848","title":"InterroGate: Learning to Share, Specialize, and Prune Representations for Multi-task Learning","created":"2024-02-26","cited_by_count":1}],"next_cursor":null}