{"list":"other","total":53,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"2310.11324","title":"Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting","created":"2023-10-17","cited_by_count":817},{"id":"2107.07511","title":"A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification","created":"2021-07-15","cited_by_count":792},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2404.12390","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","created":"2024-04-18","cited_by_count":550},{"id":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439},{"id":"1907.07484","title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","created":"2019-07-17","cited_by_count":336},{"id":"2401.00595","title":"State of What Art? A Call for Multi-Prompt LLM Evaluation","created":"2023-12-31","cited_by_count":310},{"id":"2307.01928","title":"Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners","created":"2023-07-04","cited_by_count":308},{"id":"1609.00451","title":"Least Ambiguous Set-Valued Classifiers with Bounded Error Levels","created":"2016-09-02","cited_by_count":272},{"id":"2406.06978","title":"Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation","created":"2024-06-11","cited_by_count":249},{"id":"2408.16500","title":"CogVLM2: Visual Language Models for Image and Video Understanding","created":"2024-08-29","cited_by_count":217},{"id":"2212.04037","title":"Demystifying Prompts in Language Models via Perplexity Estimation","created":"2022-12-08","cited_by_count":216},{"id":"2305.18404","title":"Conformal Prediction with Large Language Models for Multi-Choice Question Answering","created":"2023-05-28","cited_by_count":139},{"id":"2401.12794","title":"Benchmarking LLMs via Uncertainty Quantification","created":"2024-01-23","cited_by_count":126},{"id":"2203.01441","title":"3D Common Corruptions and Data Augmentation","created":"2022-03-02","cited_by_count":119},{"id":"2106.09707","title":"Learning to Predict Visual Attributes in the Wild","created":"2021-06-17","cited_by_count":96},{"id":"2401.06766","title":"Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements","created":"2024-01-12","cited_by_count":83},{"id":"2105.03519","title":"Understanding by Understanding Not: Modeling Negation in Language Models","created":"2021-05-07","cited_by_count":73},{"id":"2209.15517","title":"Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Study","created":"2022-09-30","cited_by_count":66},{"id":"2306.11270","title":"Evaluating the Zero-shot Robustness of Instruction-tuned Language Models","created":"2023-06-20","cited_by_count":66},{"id":"2004.12276","title":"Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset","created":"2020-04-26","cited_by_count":57},{"id":"2404.01266","title":"IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations","created":"2024-04-01","cited_by_count":38},{"id":"2212.03813","title":"Robustness of Learning from Task Instructions","created":"2022-12-07","cited_by_count":35},{"id":"2408.11865","title":"How Susceptible are LLMs to Influence in Prompts?","created":"2024-08-17","cited_by_count":33},{"id":"2312.17476","title":"Exploring the Sensitivity of LLMs' Decision-Making Capabilities: Insights from Prompt Variation and Hyperparameters","created":"2023-12-29","cited_by_count":32},{"id":"2404.10193","title":"Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering","created":"2024-04-16","cited_by_count":32},{"id":"2407.16837","title":"MLLM-CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs","created":"2024-07-23","cited_by_count":32},{"id":"2306.02080","title":"Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models","created":"2023-06-03","cited_by_count":31},{"id":"2402.09262","title":"MultiMedEval: A Benchmark and a Toolkit for Evaluating Medical Vision-Language Models","created":"2024-02-14","cited_by_count":29},{"id":"2402.14418","title":"Uncertainty-Aware Evaluation for Vision-Language Models","created":"2024-02-22","cited_by_count":29},{"id":"2305.08714","title":"Sensitivity and Robustness of Large Language Models to Prompt Template in Japanese Text Classification Tasks","created":"2023-05-15","cited_by_count":25},{"id":"2207.02159","title":"Robustness Analysis of Video-Language Models Against Visual and Language Perturbations","created":"2022-07-05","cited_by_count":23},{"id":"2304.01964","title":"PromptAid: Prompt Exploration, Perturbation, Testing and Iteration using Visual Analytics for Large Language Models","created":"2023-04-04","cited_by_count":19},{"id":"2307.13989","title":"This is not correct! Negation-aware Evaluation of Language Generation Systems","created":"2023-07-26","cited_by_count":17},{"id":"2305.17311","title":"Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models","created":"2023-05-27","cited_by_count":12},{"id":"2505.09368","title":"RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo","created":"2025-05-14","cited_by_count":7}],"next_cursor":null}