{"list":"other","total":61,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"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":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"2305.01937","title":"Can Large Language Models Be an Alternative to Human Evaluations?","created":"2023-05-03","cited_by_count":734},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2005.04790","title":"The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes","created":"2020-05-10","cited_by_count":490},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"2312.00849","title":"RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback","created":"2023-12-01","cited_by_count":412},{"id":"1709.02012","title":"On Fairness and Calibration","created":"2017-09-06","cited_by_count":406},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401},{"id":"2306.17492","title":"Preference Ranking Optimization for Human Alignment","created":"2023-06-30","cited_by_count":285},{"id":"2401.05561","title":"TrustLLM: Trustworthiness in Large Language Models","created":"2024-01-10","cited_by_count":285},{"id":"1709.03815","title":"OpenNMT: Open-source Toolkit for Neural Machine Translation","created":"2017-09-12","cited_by_count":251},{"id":"2209.01975","title":"Selective Annotation Makes Language Models Better Few-Shot Learners","created":"2022-09-05","cited_by_count":243},{"id":"2312.09245","title":"DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving","created":"2023-12-14","cited_by_count":233},{"id":"2402.05044","title":"SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models","created":"2024-02-07","cited_by_count":228},{"id":"2308.09662","title":"Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment","created":"2023-08-18","cited_by_count":223},{"id":"2003.07333","title":"RSVQA: Visual Question Answering for Remote Sensing Data","created":"2020-03-16","cited_by_count":203},{"id":"2307.00595","title":"RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot","created":"2023-07-02","cited_by_count":183},{"id":"2301.04883","title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images","created":"2023-01-12","cited_by_count":179},{"id":"2306.06687","title":"LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark","created":"2023-06-11","cited_by_count":169},{"id":"2306.11290","title":"Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation","created":"2023-06-20","cited_by_count":167},{"id":"2402.02207","title":"Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models","created":"2024-02-03","cited_by_count":167},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157},{"id":"2104.08391","title":"Learning To Count Everything","created":"2021-04-16","cited_by_count":150},{"id":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144},{"id":"2402.02416","title":"Aligner: Efficient Alignment by Learning to Correct","created":"2024-02-04","cited_by_count":98},{"id":"2305.11391","title":"A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation","created":"2023-05-19","cited_by_count":93},{"id":"2008.00334","title":"Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning","created":"2020-08-01","cited_by_count":91},{"id":"2402.00357","title":"Safety of Multimodal Large Language Models on Images and Texts","created":"2024-02-01","cited_by_count":75},{"id":"2402.03190","title":"Unified Hallucination Detection for Multimodal Large Language Models","created":"2024-02-05","cited_by_count":75},{"id":"2209.00731","title":"In conversation with Artificial Intelligence: aligning language models with human values","created":"2022-09-01","cited_by_count":62},{"id":"2401.01523","title":"GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse","created":"2024-01-03","cited_by_count":52},{"id":"2303.02913","title":"OpenICL: An Open-Source Framework for In-context Learning","created":"2023-03-06","cited_by_count":51},{"id":"2207.07106","title":"Benchmarking Omni-Vision Representation through the Lens of Visual Realms","created":"2022-07-14","cited_by_count":38},{"id":"2310.01779","title":"HallE-Control: Controlling Object Hallucination in Large Multimodal Models","created":"2023-10-03","cited_by_count":32},{"id":"2312.11523","title":"ToViLaG: Your Visual-Language Generative Model is Also An Evildoer","created":"2023-12-13","cited_by_count":27},{"id":"2203.07845","title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy","created":"2022-03-15","cited_by_count":21},{"id":"2310.05192","title":"HOD: A Benchmark Dataset for Harmful Object Detection","created":"2023-10-08","cited_by_count":10}],"next_cursor":null}