{"list":"other","total":141,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"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":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"1608.04644","title":"Towards Evaluating the Robustness of Neural Networks","created":"2016-08-16","cited_by_count":2998},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"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":"1511.07528","title":"The Limitations of Deep Learning in Adversarial Settings","created":"2015-11-24","cited_by_count":790},{"id":"2310.04451","title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","created":"2023-10-03","cited_by_count":785},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"1412.1897","title":"Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images","created":"2014-12-05","cited_by_count":776},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651},{"id":"2401.06373","title":"How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs","created":"2024-01-12","cited_by_count":573},{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551},{"id":"1909.01326","title":"The Woman Worked as a Babysitter: On Biases in Language Generation","created":"2019-09-03","cited_by_count":541},{"id":"1712.09665","title":"Adversarial Patch","created":"2017-12-27","cited_by_count":517},{"id":"2308.03825","title":"\"Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models","created":"2023-08-07","cited_by_count":489},{"id":"1605.07277","title":"Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples","created":"2016-05-24","cited_by_count":446},{"id":"2310.06387","title":"Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations","created":"2023-10-10","cited_by_count":431},{"id":"2308.06463","title":"GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher","created":"2023-08-12","cited_by_count":423},{"id":"2311.05608","title":"FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts","created":"2023-11-09","cited_by_count":398},{"id":"2101.05783","title":"Persistent Anti-Muslim Bias in Large Language Models","created":"2021-01-14","cited_by_count":377},{"id":"2311.03191","title":"DeepInception: Hypnotize Large Language Model to Be Jailbreaker","created":"2023-11-06","cited_by_count":367},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"2304.05197","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","created":"2023-04-11","cited_by_count":333},{"id":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315},{"id":"2310.02446","title":"Low-Resource Languages Jailbreak GPT-4","created":"2023-10-03","cited_by_count":309},{"id":"2310.02949","title":"Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models","created":"2023-10-04","cited_by_count":297},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292},{"id":"2302.05733","title":"Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks","created":"2023-02-11","cited_by_count":278},{"id":"2311.17600","title":"MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models","created":"2023-11-29","cited_by_count":274},{"id":"1610.06940","title":"Safety Verification of Deep Neural Networks","created":"2016-10-21","cited_by_count":263},{"id":"2310.06474","title":"Multilingual Jailbreak Challenges in Large Language Models","created":"2023-10-10","cited_by_count":240},{"id":"2310.17389","title":"ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation","created":"2023-10-26","cited_by_count":231},{"id":"2404.03027","title":"JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks","created":"2024-04-03","cited_by_count":230},{"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":"2306.09265","title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models","created":"2023-06-15","cited_by_count":217},{"id":"2309.07045","title":"SafetyBench: Evaluating the Safety of Large Language Models","created":"2023-09-13","cited_by_count":199},{"id":"2402.08679","title":"COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability","created":"2024-02-13","cited_by_count":175},{"id":"2311.09096","title":"Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization","created":"2023-11-15","cited_by_count":170},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169},{"id":"1807.07769","title":"Physical Adversarial Examples for Object Detectors","created":"2018-07-20","cited_by_count":163},{"id":"1907.06826","title":"Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving","created":"2019-07-16","cited_by_count":152},{"id":"1806.02299","title":"DPatch: An Adversarial Patch Attack on Object Detectors","created":"2018-06-05","cited_by_count":147},{"id":"1709.07857","title":"Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping","created":"2017-09-22","cited_by_count":144},{"id":"1909.10838","title":"Talk2Car: Taking Control of Your Self-Driving Car","created":"2019-09-24","cited_by_count":142},{"id":"2403.09792","title":"Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models","created":"2024-03-14","cited_by_count":136},{"id":"2402.02309","title":"Jailbreaking Attack against Multimodal Large Language Model","created":"2024-02-04","cited_by_count":135},{"id":"2103.01050","title":"Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World","created":"2021-03-01","cited_by_count":127},{"id":"2307.10490","title":"Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs","created":"2023-07-19","cited_by_count":124},{"id":"2005.09830","title":"Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review","created":"2020-05-20","cited_by_count":116},{"id":"2310.15140","title":"AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models","created":"2023-10-23","cited_by_count":111},{"id":"2311.16101","title":"How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs","created":"2023-11-27","cited_by_count":108},{"id":"2106.09249","title":"Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks","created":"2021-06-17","cited_by_count":101},{"id":"2004.08467","title":"Lidar for Autonomous Driving: The principles, challenges, and trends for automotive lidar and perception systems","created":"2020-04-17","cited_by_count":100},{"id":"2006.16974","title":"Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasures","created":"2020-06-30","cited_by_count":95},{"id":"2312.03777","title":"On the Robustness of Large Multimodal Models Against Image Adversarial Attacks","created":"2023-12-06","cited_by_count":92},{"id":"2401.04334","title":"Large Language Models for Robotics: Opportunities, Challenges, and Perspectives","created":"2024-01-09","cited_by_count":89},{"id":"1803.11469","title":"Jacquard: A Large Scale Dataset for Robotic Grasp Detection","created":"2018-03-30","cited_by_count":87},{"id":"2304.10436","title":"Safety Assessment of Chinese Large Language Models","created":"2023-04-20","cited_by_count":85},{"id":"2406.12030","title":"SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model","created":"2024-06-17","cited_by_count":85},{"id":"2312.02296","title":"LLMs Accelerate Annotation for Medical Information Extraction","created":"2023-12-04","cited_by_count":77},{"id":"2402.16717","title":"CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models","created":"2024-02-26","cited_by_count":76},{"id":"2103.06504","title":"Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink","created":"2021-03-11","cited_by_count":75},{"id":"1907.04449","title":"PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving","created":"2019-07-09","cited_by_count":72},{"id":"2404.02928","title":"Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models","created":"2024-04-02","cited_by_count":72},{"id":"1609.09475","title":"Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challenge","created":"2016-09-29","cited_by_count":70},{"id":"1708.09537","title":"DolphinAtack: Inaudible Voice Commands","created":"2017-08-31","cited_by_count":69},{"id":"2405.20773","title":"Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character","created":"2024-05-25","cited_by_count":68},{"id":"2112.04532","title":"Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection","created":"2021-12-08","cited_by_count":67},{"id":"1801.08535","title":"CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition","created":"2018-01-24","cited_by_count":66}],"next_cursor":"100"}