{"list":"other","total":57,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501},{"id":"2311.05608","title":"FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts","created":"2023-11-09","cited_by_count":398},{"id":"2404.18930","title":"Hallucination of Multimodal Large Language Models: A Survey","created":"2024-04-29","cited_by_count":388},{"id":"2304.06712","title":"What does CLIP know about a red circle? Visual prompt engineering for VLMs","created":"2023-04-13","cited_by_count":218},{"id":"2403.14003","title":"Multi-Modal Hallucination Control by Visual Information Grounding","created":"2024-03-20","cited_by_count":208},{"id":"2303.08131","title":"A Simple Framework for Open-Vocabulary Segmentation and Detection","created":"2023-03-14","cited_by_count":198},{"id":"2402.07872","title":"PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs","created":"2024-02-12","cited_by_count":190},{"id":"2207.10660","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","created":"2022-07-21","cited_by_count":160},{"id":"2402.08567","title":"Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast","created":"2024-02-13","cited_by_count":153},{"id":"2406.19389","title":"OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding","created":"2024-06-27","cited_by_count":127},{"id":"2303.10883","title":"Explicit Visual Prompting for Low-Level Structure Segmentations","created":"2023-03-20","cited_by_count":114},{"id":"2406.04031","title":"Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt","created":"2024-06-06","cited_by_count":109},{"id":"2305.01115","title":"In-Context Learning Unlocked for Diffusion Models","created":"2023-05-01","cited_by_count":104},{"id":"2403.14598","title":"PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model","created":"2024-03-21","cited_by_count":101},{"id":"2211.11635","title":"Understanding and Improving Visual Prompting: A Label-Mapping Perspective","created":"2022-11-21","cited_by_count":87},{"id":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83},{"id":"2403.04279","title":"Controllable Generation with Text-to-Image Diffusion Models: A Survey","created":"2024-03-07","cited_by_count":83},{"id":"2402.00357","title":"Safety of Multimodal Large Language Models on Images and Texts","created":"2024-02-01","cited_by_count":75},{"id":"2312.09158","title":"General Object Foundation Model for Images and Videos at Scale","created":"2023-12-14","cited_by_count":71},{"id":"2303.14773","title":"BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning","created":"2023-03-26","cited_by_count":70},{"id":"2401.11624","title":"In-context Learning with Retrieved Demonstrations for Language Models: A Survey","created":"2024-01-21","cited_by_count":70},{"id":"2407.05890","title":"Affordances-Oriented Planning using Foundation Models for Continuous Vision-Language Navigation","created":"2024-07-08","cited_by_count":65},{"id":"2403.02325","title":"Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training","created":"2024-03-04","cited_by_count":64},{"id":"2403.04014","title":"PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement","created":"2024-03-06","cited_by_count":62},{"id":"2308.00906","title":"ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation","created":"2023-08-02","cited_by_count":59},{"id":"2403.12037","title":"MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control","created":"2024-03-18","cited_by_count":53},{"id":"2312.02918","title":"Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration","created":"2023-12-05","cited_by_count":50},{"id":"2309.13205","title":"A Practical Survey on Zero-shot Prompt Design for In-context Learning","created":"2023-09-22","cited_by_count":49},{"id":"2312.12436","title":"A Challenger to GPT-4V? Early Explorations of Gemini in Visual Expertise","created":"2023-12-19","cited_by_count":49},{"id":"2403.12488","title":"DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM","created":"2024-03-19","cited_by_count":46},{"id":"2306.06211","title":"A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering","created":"2023-05-12","cited_by_count":45},{"id":"2407.15050","title":"Arondight: Red Teaming Large Vision Language Models with Auto-generated Multi-modal Jailbreak Prompts","created":"2024-07-21","cited_by_count":42},{"id":"2406.07549","title":"A3VLM: Actionable Articulation-Aware Vision Language Model","created":"2024-06-11","cited_by_count":33},{"id":"2401.03201","title":"3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding","created":"2024-01-06","cited_by_count":32},{"id":"2405.03685","title":"Language-Image Models with 3D Understanding","created":"2024-05-06","cited_by_count":31},{"id":"2403.11835","title":"Agent3D-Zero: An Agent for Zero-shot 3D Understanding","created":"2024-03-18","cited_by_count":29},{"id":"2405.03194","title":"CityLLaVA: Efficient Fine-Tuning for VLMs in City Scenario","created":"2024-05-06","cited_by_count":27},{"id":"2403.17001","title":"VP3D: Unleashing 2D Visual Prompt for Text-to-3D Generation","created":"2024-03-25","cited_by_count":25},{"id":"2406.10462","title":"CoMM: A Coherent Interleaved Image-Text Dataset for Multimodal Understanding and Generation","created":"2024-06-15","cited_by_count":23},{"id":"2407.15850","title":"AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description","created":"2024-07-22","cited_by_count":23},{"id":"2405.05615","title":"Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning","created":"2024-05-09","cited_by_count":20},{"id":"2406.19263","title":"Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding","created":"2024-06-27","cited_by_count":18},{"id":"2310.05136","title":"InstructDET: Diversifying Referring Object Detection with Generalized Instructions","created":"2023-10-08","cited_by_count":16},{"id":"2405.15279","title":"Towards Global Optimal Visual In-Context Learning Prompt Selection","created":"2024-05-24","cited_by_count":15},{"id":"2406.05814","title":"TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models","created":"2024-06-09","cited_by_count":12},{"id":"2312.02520","title":"Towards More Unified In-context Visual Understanding","created":"2023-12-05","cited_by_count":10},{"id":"2403.12801","title":"RelationVLM: Making Large Vision-Language Models Understand Visual Relations","created":"2024-03-19","cited_by_count":9},{"id":"2405.18406","title":"RACCooN: A Versatile Instructional Video Editing Framework with Auto-Generated Narratives","created":"2024-05-28","cited_by_count":8},{"id":"2406.03303","title":"Learning Visual Prompts for Guiding the Attention of Vision Transformers","created":"2024-06-05","cited_by_count":6},{"id":"2405.15161","title":"Are You Copying My Prompt? Protecting the Copyright of Vision Prompt for VPaaS via Watermark","created":"2024-05-24","cited_by_count":4}],"next_cursor":null}