{"list":"other","total":83,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"2407.07726","title":"PaliGemma: A versatile 3B VLM for transfer","created":"2024-07-10","cited_by_count":696},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560},{"id":"1802.01886","title":"Texygen: A Benchmarking Platform for Text Generation Models","created":"2018-02-06","cited_by_count":491},{"id":"2003.12462","title":"TextCaps: a Dataset for Image Captioning with Reading Comprehension","created":"2020-03-24","cited_by_count":400},{"id":"2402.12354","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","created":"2024-02-19","cited_by_count":377},{"id":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"1807.07356","title":"Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks","created":"2018-07-19","cited_by_count":280},{"id":"1907.04907","title":"Topic Modeling in Embedding Spaces","created":"2019-07-08","cited_by_count":224},{"id":"1810.04020","title":"A Comprehensive Survey of Deep Learning for Image Captioning","created":"2018-10-06","cited_by_count":214},{"id":"2404.13628","title":"Mixture of LoRA Experts","created":"2024-04-21","cited_by_count":181},{"id":"1906.05963","title":"Image Captioning: Transforming Objects into Words","created":"2019-06-14","cited_by_count":171},{"id":"1711.03953","title":"Breaking the Softmax Bottleneck: A High-Rank RNN Language Model","created":"2017-11-10","cited_by_count":152},{"id":"2404.15159","title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","created":"2024-04-22","cited_by_count":147},{"id":"2005.10283","title":"Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation","created":"2020-05-20","cited_by_count":138},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137},{"id":"1803.00047","title":"Analyzing Uncertainty in Neural Machine Translation","created":"2018-02-28","cited_by_count":126},{"id":"2210.15191","title":"Truncation Sampling as Language Model Desmoothing","created":"2022-10-27","cited_by_count":123},{"id":"2402.11004","title":"The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains","created":"2024-02-16","cited_by_count":118},{"id":"1612.00370","title":"Improved Image Captioning via Policy Gradient optimization of SPIDEr","created":"2016-12-01","cited_by_count":113},{"id":"2110.04260","title":"Taming Sparsely Activated Transformer with Stochastic Experts","created":"2021-10-08","cited_by_count":113},{"id":"2202.00666","title":"Locally Typical Sampling","created":"2022-02-01","cited_by_count":111},{"id":"1612.00197","title":"Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses","created":"2016-12-01","cited_by_count":97},{"id":"1906.03631","title":"Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction","created":"2019-06-09","cited_by_count":96},{"id":"2004.10450","title":"Trading Off Diversity and Quality in Natural Language Generation","created":"2020-04-22","cited_by_count":96},{"id":"2306.03745","title":"Soft Merging of Experts with Adaptive Routing","created":"2023-06-06","cited_by_count":90},{"id":"2309.11674","title":"A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models","created":"2023-09-20","cited_by_count":89},{"id":"1906.06362","title":"Comparison of Diverse Decoding Methods from Conditional Language Models","created":"2019-06-14","cited_by_count":78},{"id":"1909.04849","title":"A Discrete Hard EM Approach for Weakly Supervised Question Answering","created":"2019-09-11","cited_by_count":78},{"id":"1606.07839","title":"Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles","created":"2016-06-24","cited_by_count":77},{"id":"1902.07816","title":"Mixture Models for Diverse Machine Translation: Tricks of the Trade","created":"2019-02-20","cited_by_count":77},{"id":"2310.00035","title":"LoRA ensembles for large language model fine-tuning","created":"2023-09-29","cited_by_count":67},{"id":"2210.14140","title":"Contrastive Search Is What You Need For Neural Text Generation","created":"2022-10-25","cited_by_count":59},{"id":"2107.09817","title":"Audio Captioning Transformer","created":"2021-07-21","cited_by_count":55},{"id":"1711.09151","title":"Convolutional Image Captioning","created":"2017-11-24","cited_by_count":52},{"id":"2502.01839","title":"Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification","created":"2025-02-03","cited_by_count":50},{"id":"1903.12020","title":"Describing like humans: on diversity in image captioning","created":"2019-03-28","cited_by_count":46},{"id":"1706.10006","title":"Automated Audio Captioning with Recurrent Neural Networks","created":"2017-06-30","cited_by_count":40},{"id":"2402.04161","title":"Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains","created":"2024-02-06","cited_by_count":40},{"id":"2502.01235","title":"LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently","created":"2025-02-03","cited_by_count":38},{"id":"2104.08277","title":"Divide-and-Conquer for Lane-Aware Diverse Trajectory Prediction","created":"2021-04-16","cited_by_count":37},{"id":"2010.13303","title":"Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning","created":"2020-10-26","cited_by_count":35},{"id":"2410.02724","title":"Large Language Models as Markov Chains","created":"2024-10-03","cited_by_count":35},{"id":"2410.12757","title":"StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples","created":"2024-10-16","cited_by_count":35},{"id":"2110.04684","title":"Can Audio Captions Be Evaluated with Image Caption Metrics?","created":"2021-10-10","cited_by_count":33},{"id":"1912.10982","title":"DMCL: Distillation Multiple Choice Learning for Multimodal Action Recognition","created":"2019-12-23","cited_by_count":30},{"id":"2112.06558","title":"MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-based Image Captioning","created":"2021-12-13","cited_by_count":27},{"id":"2105.03236","title":"Towards Accurate Text-based Image Captioning with Content Diversity Exploration","created":"2021-04-23","cited_by_count":25},{"id":"1706.03475","title":"Confident Multiple Choice Learning","created":"2017-06-12","cited_by_count":24},{"id":"2205.05949","title":"Automated Audio Captioning: An Overview of Recent Progress and New Challenges","created":"2022-05-12","cited_by_count":23},{"id":"2011.00966","title":"Diverse Image Captioning with Context-Object Split Latent Spaces","created":"2020-11-02","cited_by_count":22},{"id":"2406.05130","title":"An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models","created":"2024-06-07","cited_by_count":22},{"id":"2212.11281","title":"Language models are better than humans at next-token prediction","created":"2022-12-21","cited_by_count":15},{"id":"2110.06691","title":"Diverse Audio Captioning via Adversarial Training","created":"2021-10-13","cited_by_count":14},{"id":"2309.00454","title":"CoNeTTE: An efficient Audio Captioning system leveraging multiple datasets with Task Embedding","created":"2023-09-01","cited_by_count":13},{"id":"2211.09403","title":"Learning Mixtures of Markov Chains and MDPs","created":"2022-11-17","cited_by_count":12},{"id":"2311.01052","title":"Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis","created":"2023-11-02","cited_by_count":12},{"id":"2407.15580","title":"Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealing","created":"2024-07-22","cited_by_count":12},{"id":"2209.14627","title":"An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation","created":"2022-09-29","cited_by_count":11},{"id":"2210.17143","title":"Exploring Train and Test-Time Augmentations for Audio-Language Learning","created":"2022-10-31","cited_by_count":11},{"id":"2406.04706","title":"Winner-takes-all learners are geometry-aware conditional density estimators","created":"2024-06-07","cited_by_count":6},{"id":"2405.15719","title":"Hierarchical Uncertainty Exploration via Feedforward Posterior Trees","created":"2024-05-24","cited_by_count":4},{"id":"2409.09401","title":"Towards Diverse and Efficient Audio Captioning via Diffusion Models","created":"2024-09-14","cited_by_count":2},{"id":"2211.08983","title":"Is my automatic audio captioning system so bad? spider-max: a metric to consider several caption candidates","created":"2022-11-14","cited_by_count":1}],"next_cursor":null}