{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"1801.04062","title":"MINE: Mutual Information Neural Estimation","created":"2018-01-12","cited_by_count":683},{"id":"2310.08491","title":"Prometheus: Inducing Fine-grained Evaluation Capability in Language Models","created":"2023-10-12","cited_by_count":575},{"id":"1905.06922","title":"On Variational Bounds of Mutual Information","created":"2019-05-16","cited_by_count":559},{"id":"1703.00810","title":"Opening the Black Box of Deep Neural Networks via Information","created":"2017-03-02","cited_by_count":503},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"id":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"id":"1907.13625","title":"On Mutual Information Maximization for Representation Learning","created":"2019-07-31","cited_by_count":316},{"id":"2006.12013","title":"CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information","created":"2020-06-22","cited_by_count":235},{"id":"2212.00638","title":"Finetune like you pretrain: Improved finetuning of zero-shot vision models","created":"2022-12-01","cited_by_count":150},{"id":"2002.09116","title":"Learning Deep Kernels for Non-Parametric Two-Sample Tests","created":"2020-02-21","cited_by_count":130},{"id":"2407.12580","title":"E5-V: Universal Embeddings with Multimodal Large Language Models","created":"2024-07-17","cited_by_count":126},{"id":"1602.02311","title":"R\\'enyi Divergence Variational Inference","created":"2016-02-06","cited_by_count":104},{"id":"2405.18415","title":"Why are Visually-Grounded Language Models Bad at Image Classification?","created":"2024-05-28","cited_by_count":102},{"id":"2203.11364","title":"An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labels","created":"2022-03-21","cited_by_count":89},{"id":"1910.08350","title":"A Mutual Information Maximization Perspective of Language Representation Learning","created":"2019-10-18","cited_by_count":85},{"id":"2103.06413","title":"FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders","created":"2021-03-11","cited_by_count":75},{"id":"2109.09234","title":"Conditional probing: measuring usable information beyond a baseline","created":"2021-09-19","cited_by_count":62},{"id":"2205.13401","title":"Your Transformer May Not be as Powerful as You Expect","created":"2022-05-26","cited_by_count":55},{"id":"2408.01367","title":"Transformers are Universal In-context Learners","created":"2024-08-02","cited_by_count":43},{"id":"2303.10720","title":"Trainable Projected Gradient Method for Robust Fine-tuning","created":"2023-03-19","cited_by_count":37},{"id":"2311.01723","title":"Towards Calibrated Robust Fine-Tuning of Vision-Language Models","created":"2023-11-03","cited_by_count":35},{"id":"2206.02659","title":"Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees","created":"2022-06-06","cited_by_count":34},{"id":"1811.03205","title":"Robustness of Conditional GANs to Noisy Labels","created":"2018-11-08","cited_by_count":27},{"id":"2106.03783","title":"An Information-theoretic Approach to Distribution Shifts","created":"2021-06-07","cited_by_count":25},{"id":"2110.03652","title":"Neural Estimation of Statistical Divergences","created":"2021-10-07","cited_by_count":25},{"id":"2210.04982","title":"REV: Information-Theoretic Evaluation of Free-Text Rationales","created":"2022-10-10","cited_by_count":22},{"id":"2312.07424","title":"How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation","created":"2023-12-12","cited_by_count":22},{"id":"2305.13954","title":"Robust Prompt Optimization for Large Language Models Against Distribution Shifts","created":"2023-05-23","cited_by_count":19},{"id":"2410.03782","title":"DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation","created":"2024-10-03","cited_by_count":19},{"id":"2305.16446","title":"The Representation Jensen-Shannon Divergence","created":"2023-05-25","cited_by_count":9},{"id":"2501.09368","title":"Aligning Instruction Tuning with Pre-training","created":"2025-01-16","cited_by_count":7},{"id":"1705.09199","title":"Non-parametric estimation of Jensen-Shannon Divergence in Generative Adversarial Network training","created":"2017-05-25","cited_by_count":6}],"next_cursor":null}