{"list":"other","total":54,"rows":[{"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":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"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":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"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":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"1801.04062","title":"MINE: Mutual Information Neural Estimation","created":"2018-01-12","cited_by_count":683},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656},{"id":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346},{"id":"2310.11454","title":"VeRA: Vector-based Random Matrix Adaptation","created":"2023-10-17","cited_by_count":300},{"id":"2308.07317","title":"Platypus: Quick, Cheap, and Powerful Refinement of LLMs","created":"2023-08-14","cited_by_count":150},{"id":"2203.09795","title":"Three things everyone should know about Vision Transformers","created":"2022-03-18","cited_by_count":90},{"id":"2311.09578","title":"Tied-Lora: Enhancing parameter efficiency of LoRA with weight tying","created":"2023-11-16","cited_by_count":65},{"id":"1904.06963","title":"The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent","created":"2019-04-15","cited_by_count":46},{"id":"2406.14479","title":"Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity","created":"2024-06-20","cited_by_count":36},{"id":"2404.09610","title":"LoRA Dropout as a Sparsity Regularizer for Overfitting Control","created":"2024-04-15","cited_by_count":35},{"id":"2602.13035","title":"Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL","created":"2026-02-13","cited_by_count":27},{"id":"2505.18738","title":"AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping","created":"2025-05-24","cited_by_count":23},{"id":"2510.13219","title":"Prompt-based Adaptation in Large-scale Vision Models: A Survey","created":"2025-10-15","cited_by_count":21},{"id":"2207.06130","title":"Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation","created":"2022-07-13","cited_by_count":20},{"id":"2505.18399","title":"Taming Diffusion for Dataset Distillation with High Representativeness","created":"2025-05-23","cited_by_count":18},{"id":"2504.14117","title":"PEFT A2Z: Parameter-Efficient Fine-Tuning Survey for Large Language and Vision Models","created":"2025-04-19","cited_by_count":16},{"id":"2312.04823","title":"Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy","created":"2023-12-04","cited_by_count":13},{"id":"2511.22134","title":"DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action","created":"2025-11-27","cited_by_count":12},{"id":"2503.07938","title":"CAD-VAE: Leveraging Correlation-Aware Latents for Comprehensive Fair Disentanglement","created":"2025-03-11","cited_by_count":11},{"id":"2505.20154","title":"UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models","created":"2025-05-26","cited_by_count":11},{"id":"2510.02630","title":"HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance","created":"2025-10-03","cited_by_count":10},{"id":"2506.12323","title":"Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback","created":"2025-06-14","cited_by_count":9},{"id":"2603.06932","title":"HIERAMP: Coarse-to-Fine Autoregressive Amplification for Generative Dataset Distillation","created":"2026-03-06","cited_by_count":9},{"id":"2510.16670","title":"All You Need is One: Capsule Prompt Tuning with a Single Vector","created":"2025-10-19","cited_by_count":8},{"id":"2511.17583","title":"Learning Straight Flows: Variational Flow Matching for Efficient Generation","created":"2025-11-15","cited_by_count":8},{"id":"2505.19352","title":"Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions","created":"2025-05-25","cited_by_count":7},{"id":"2507.14787","title":"FOCUS: Fused Observation of Channels for Unveiling Spectra","created":"2025-07-20","cited_by_count":7},{"id":"2509.23122","title":"Stochastic Interpolants via Conditional Dependent Coupling","created":"2025-09-27","cited_by_count":7},{"id":"2603.13683","title":"Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation","created":"2026-03-14","cited_by_count":5},{"id":"2109.10497","title":"A Simple Approach to Jointly Rank Passages and Select Relevant Sentences in the OBQA Context","created":"2021-09-22","cited_by_count":4},{"id":"2602.06663","title":"PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Tasks","created":"2026-02-06","cited_by_count":4},{"id":"2511.12410","title":"Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection","created":"2025-11-16","cited_by_count":3}],"next_cursor":null}