{"list":"other","total":72,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"2507.18071","title":"Group Sequence Policy Optimization","created":"2025-07-24","cited_by_count":835},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"2311.03099","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","created":"2023-11-06","cited_by_count":694},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621},{"id":"1804.08838","title":"Measuring the Intrinsic Dimension of Objective Landscapes","created":"2018-04-24","cited_by_count":370},{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364},{"id":"2303.10512","title":"AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning","created":"2023-03-18","cited_by_count":357},{"id":"2310.14152","title":"Orthogonal Subspace Learning for Language Model Continual Learning","created":"2023-10-22","cited_by_count":312},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237},{"id":"2405.05904","title":"Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?","created":"2024-05-09","cited_by_count":232},{"id":"2305.12827","title":"Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models","created":"2023-05-22","cited_by_count":221},{"id":"2306.07280","title":"Controlling Text-to-Image Diffusion by Orthogonal Finetuning","created":"2023-06-12","cited_by_count":208},{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197},{"id":"2404.13628","title":"Mixture of LoRA Experts","created":"2024-04-21","cited_by_count":181},{"id":"1810.01256","title":"Continual Learning of Context-dependent Processing in Neural Networks","created":"2018-09-29","cited_by_count":179},{"id":"2309.05444","title":"Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning","created":"2023-09-11","cited_by_count":150},{"id":"2308.03303","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","created":"2023-08-07","cited_by_count":137},{"id":"1711.04735","title":"Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice","created":"2017-11-13","cited_by_count":132},{"id":"2404.19245","title":"HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning","created":"2024-04-30","cited_by_count":123},{"id":"2410.19735","title":"Model merging with SVD to tie the Knots","created":"2024-10-25","cited_by_count":122},{"id":"2311.06243","title":"Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization","created":"2023-11-10","cited_by_count":114},{"id":"2010.11635","title":"Continual Learning in Low-rank Orthogonal Subspaces","created":"2020-10-22","cited_by_count":99},{"id":"2311.11696","title":"Sparse Low-rank Adaptation of Pre-trained Language Models","created":"2023-11-20","cited_by_count":96},{"id":"2306.03745","title":"Soft Merging of Experts with Adaptive Routing","created":"2023-06-06","cited_by_count":90},{"id":"2402.16842","title":"Asymmetry in Low-Rank Adapters of Foundation Models","created":"2024-02-26","cited_by_count":86},{"id":"2302.07027","title":"AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models","created":"2023-02-14","cited_by_count":84},{"id":"2310.04742","title":"Parameter Efficient Multi-task Model Fusion with Partial Linearization","created":"2023-10-07","cited_by_count":65},{"id":"2507.04632","title":"Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?","created":"2025-07-07","cited_by_count":52},{"id":"2504.10957","title":"When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers","created":"2025-04-15","cited_by_count":38},{"id":"2309.12696","title":"Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning","created":"2023-09-22","cited_by_count":37},{"id":"2306.04073","title":"Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks","created":"2023-06-07","cited_by_count":35},{"id":"2501.16404","title":"DynaPrompt: Dynamic Test-Time Prompt Tuning","created":"2025-01-27","cited_by_count":31},{"id":"2411.07934","title":"Doubly Mild Generalization for Offline Reinforcement Learning","created":"2024-11-12","cited_by_count":21},{"id":"2501.11039","title":"Model Predictive Task Sampling for Efficient and Robust Adaptation","created":"2025-01-19","cited_by_count":21},{"id":"2311.08935","title":"Supported Trust Region Optimization for Offline Reinforcement Learning","created":"2023-11-15","cited_by_count":20},{"id":"2504.07448","title":"LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation","created":"2025-04-10","cited_by_count":19},{"id":"2101.06887","title":"Can a Fruit Fly Learn Word Embeddings?","created":"2021-01-18","cited_by_count":17},{"id":"2410.19400","title":"Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression","created":"2024-10-25","cited_by_count":17},{"id":"2502.01427","title":"Structural features of the fly olfactory circuit mitigate the stability-plasticity dilemma in continual learning","created":"2025-02-03","cited_by_count":14},{"id":"2504.19139","title":"Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments","created":"2025-04-27","cited_by_count":12},{"id":"2001.04907","title":"Bio-Inspired Hashing for Unsupervised Similarity Search","created":"2020-01-14","cited_by_count":11},{"id":"2404.06486","title":"GO4Align: Group Optimization for Multi-Task Alignment","created":"2024-04-09","cited_by_count":11},{"id":"2408.10556","title":"Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks","created":"2024-08-20","cited_by_count":11},{"id":"2501.13074","title":"Autonomy-of-Experts Models","created":"2025-01-22","cited_by_count":7},{"id":"2206.09222","title":"Bioinspired random projections for robust, sparse classification","created":"2022-06-18","cited_by_count":4},{"id":"2112.07157","title":"Federated Nearest Neighbor Classification with a Colony of Fruit-Flies: With Supplement","created":"2021-12-14","cited_by_count":3},{"id":"1812.01844","title":"Improving Similarity Search with High-dimensional Locality-sensitive Hashing","created":"2018-12-05","cited_by_count":2}],"next_cursor":null}