{"list":"other","total":64,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"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":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"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":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"1608.01413","title":"Solving General Arithmetic Word Problems","created":"2016-08-04","cited_by_count":360},{"id":"2408.08921","title":"Graph Retrieval-Augmented Generation: A Survey","created":"2024-08-15","cited_by_count":324},{"id":"2310.11454","title":"VeRA: Vector-based Random Matrix Adaptation","created":"2023-10-17","cited_by_count":300},{"id":"1706.09254","title":"The E2E Dataset: New Challenges For End-to-End Generation","created":"2017-06-28","cited_by_count":253},{"id":"1911.13299","title":"What's Hidden in a Randomly Weighted Neural Network?","created":"2019-11-29","cited_by_count":237},{"id":"2210.07558","title":"DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation","created":"2022-10-14","cited_by_count":233},{"id":"2010.11918","title":"AdapterDrop: On the Efficiency of Adapters in Transformers","created":"2020-10-22","cited_by_count":224},{"id":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223},{"id":"2101.00121","title":"WARP: Word-level Adversarial ReProgramming","created":"2021-01-01","cited_by_count":221},{"id":"2004.03829","title":"Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning","created":"2020-04-08","cited_by_count":139},{"id":"2311.12023","title":"LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning","created":"2023-11-20","cited_by_count":92},{"id":"2202.07962","title":"Revisiting Parameter-Efficient Tuning: Are We Really There Yet?","created":"2022-02-16","cited_by_count":76},{"id":"2001.05992","title":"Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks","created":"2020-01-16","cited_by_count":73},{"id":"2501.11284","title":"RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?","created":"2025-01-20","cited_by_count":60},{"id":"2210.07795","title":"EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning","created":"2022-10-14","cited_by_count":56},{"id":"2412.12359","title":"LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering","created":"2024-12-16","cited_by_count":51},{"id":"2505.13408","title":"CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process","created":"2025-05-19","cited_by_count":51},{"id":"2405.02421","title":"What does the Knowledge Neuron Thesis Have to do with Knowledge?","created":"2024-05-03","cited_by_count":49},{"id":"2501.19054","title":"Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models","created":"2025-01-31","cited_by_count":47},{"id":"1906.05661","title":"Training Neural Networks for and by Interpolation","created":"2019-06-13","cited_by_count":45},{"id":"2411.13504","title":"Disentangling Memory and Reasoning Ability in Large Language Models","created":"2024-11-20","cited_by_count":44},{"id":"2402.15179","title":"Advancing Parameter Efficiency in Fine-tuning via Representation Editing","created":"2024-02-23","cited_by_count":37},{"id":"2402.15896","title":"Multimodal Instruction Tuning with Conditional Mixture of LoRA","created":"2024-02-24","cited_by_count":36},{"id":"2305.15212","title":"Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning","created":"2023-05-24","cited_by_count":29},{"id":"2310.16069","title":"CPSeg: Finer-grained Image Semantic Segmentation via Chain-of-Thought Language Prompting","created":"2023-10-24","cited_by_count":28},{"id":"2501.00353","title":"RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions","created":"2024-12-31","cited_by_count":25},{"id":"2004.05867","title":"On the Neural Tangent Kernel of Deep Networks with Orthogonal Initialization","created":"2020-04-13","cited_by_count":21},{"id":"2410.18035","title":"MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning","created":"2024-10-23","cited_by_count":19},{"id":"2402.18039","title":"ResLoRA: Identity Residual Mapping in Low-Rank Adaption","created":"2024-02-28","cited_by_count":18},{"id":"2501.03681","title":"SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment","created":"2025-01-07","cited_by_count":18},{"id":"2403.04082","title":"Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference","created":"2024-03-06","cited_by_count":17},{"id":"2403.13269","title":"AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models","created":"2024-03-20","cited_by_count":15},{"id":"2407.03779","title":"Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity","created":"2024-07-04","cited_by_count":14},{"id":"2502.15401","title":"Problem-Solving Logic Guided Curriculum In-Context Learning for LLMs Complex Reasoning","created":"2025-02-21","cited_by_count":12},{"id":"2503.02783","title":"Teaching Your Models to Understand Code via Focal Preference Alignment","created":"2025-03-04","cited_by_count":10},{"id":"2408.09846","title":"Continual Dialogue State Tracking via Reason-of-Select Distillation","created":"2024-08-19","cited_by_count":8},{"id":"2503.06594","title":"Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation","created":"2025-03-09","cited_by_count":8},{"id":"2412.07801","title":"Learning to Correction: Explainable Feedback Generation for Visual Commonsense Reasoning Distractor","created":"2024-12-08","cited_by_count":7},{"id":"2412.03944","title":"Chain-of-Thought in Large Language Models: Decoding, Projection, and Activation","created":"2024-12-05","cited_by_count":6},{"id":"2502.11223","title":"Asymmetric Conflict and Synergy in Post-training for LLM-based Multilingual Machine Translation","created":"2025-02-16","cited_by_count":6},{"id":"2306.02379","title":"Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference","created":"2023-06-04","cited_by_count":4},{"id":"2505.16710","title":"Training Long-Context LLMs Efficiently via Chunk-wise Optimization","created":"2025-05-22","cited_by_count":4},{"id":"2401.03158","title":"CoT-Driven Framework for Short Text Classification: Enhancing and Transferring Capabilities from Large to Smaller Model","created":"2024-01-06","cited_by_count":2},{"id":"2411.06866","title":"Subgraph Retrieval Enhanced by Graph-Text Alignment for Commonsense Question Answering","created":"2024-11-11","cited_by_count":2},{"id":"2502.01090","title":"Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Model","created":"2025-02-03","cited_by_count":1}],"next_cursor":null}