{"list":"other","total":82,"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"id":"2107.10833","title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","created":"2021-07-22","cited_by_count":970},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"2303.04671","title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","created":"2023-03-08","cited_by_count":668},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2204.08958","title":"MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment","created":"2022-04-19","cited_by_count":522},{"id":"2303.11381","title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","created":"2023-03-20","cited_by_count":517},{"id":"2312.17090","title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","created":"2023-12-28","cited_by_count":503},{"id":"2305.07015","title":"Exploiting Diffusion Prior for Real-World Image Super-Resolution","created":"2023-05-11","cited_by_count":489},{"id":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463},{"id":"1712.04143","title":"Benchmarking Single Image Dehazing and Beyond","created":"2017-12-12","cited_by_count":447},{"id":"2306.05301","title":"ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases","created":"2023-06-08","cited_by_count":393},{"id":"1610.02424","title":"Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models","created":"2016-10-07","cited_by_count":301},{"id":"2306.17492","title":"Preference Ranking Optimization for Human Alignment","created":"2023-06-30","cited_by_count":285},{"id":"2303.14968","title":"Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective","created":"2023-03-27","cited_by_count":280},{"id":"1811.11127","title":"Unprocessing Images for Learned Raw Denoising","created":"2018-11-27","cited_by_count":250},{"id":"2305.18752","title":"GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction","created":"2023-05-30","cited_by_count":248},{"id":"2207.14626","title":"Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models","created":"2022-07-29","cited_by_count":215},{"id":"2303.11950","title":"Learning A Sparse Transformer Network for Effective Image Deraining","created":"2023-03-21","cited_by_count":205},{"id":"1708.04512","title":"DesnowNet: Context-Aware Deep Network for Snow Removal","created":"2017-08-15","cited_by_count":200},{"id":"2311.06783","title":"Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models","created":"2023-11-12","cited_by_count":152},{"id":"2401.16468","title":"InstructIR: High-Quality Image Restoration Following Human Instructions","created":"2024-01-29","cited_by_count":140},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140},{"id":"2403.12036","title":"One-Step Image Translation with Text-to-Image Models","created":"2024-03-18","cited_by_count":116},{"id":"2310.01018","title":"Controlling Vision-Language Models for Multi-Task Image Restoration","created":"2023-10-02","cited_by_count":110},{"id":"2305.15023","title":"Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models","created":"2023-05-24","cited_by_count":101},{"id":"2310.10123","title":"AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion","created":"2023-10-16","cited_by_count":100},{"id":"2202.03373","title":"LEDNet: Joint Low-light Enhancement and Deblurring in the Dark","created":"2022-02-07","cited_by_count":96},{"id":"2407.16216","title":"Reinforcement Learning for LLM Post-Training: A Survey","created":"2024-07-23","cited_by_count":92},{"id":"2203.13278","title":"Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis","created":"2022-03-24","cited_by_count":86},{"id":"2406.11138","title":"Diffusion Models in Low-Level Vision: A Survey","created":"2024-06-17","cited_by_count":74},{"id":"2207.10564","title":"Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression","created":"2022-07-21","cited_by_count":73},{"id":"2304.03994","title":"RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors","created":"2023-04-08","cited_by_count":73},{"id":"2407.08939","title":"LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models","created":"2024-07-12","cited_by_count":71},{"id":"2311.11638","title":"Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model","created":"2023-11-20","cited_by_count":69},{"id":"2311.16512","title":"CoSeR: Bridging Image and Language for Cognitive Super-Resolution","created":"2023-11-27","cited_by_count":66},{"id":"2205.03346","title":"Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection","created":"2022-05-06","cited_by_count":59},{"id":"2303.13132","title":"Masked Image Training for Generalizable Deep Image Denoising","created":"2023-03-23","cited_by_count":57},{"id":"2311.15209","title":"See and Think: Embodied Agent in Virtual Environment","created":"2023-11-26","cited_by_count":54},{"id":"2401.03379","title":"Towards Effective Multiple-in-One Image Restoration: A Sequential and Prompt Learning Strategy","created":"2024-01-07","cited_by_count":50},{"id":"2404.10237","title":"Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models","created":"2024-04-16","cited_by_count":46},{"id":"2308.14153","title":"Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks","created":"2023-08-27","cited_by_count":45},{"id":"2407.18035","title":"RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models","created":"2024-07-25","cited_by_count":43},{"id":"2410.17809","title":"An Intelligent Agentic System for Complex Image Restoration Problems","created":"2024-10-23","cited_by_count":43},{"id":"2308.01738","title":"Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution","created":"2023-08-03","cited_by_count":39},{"id":"2405.18842","title":"Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Dataset","created":"2024-05-29","cited_by_count":38},{"id":"2307.07829","title":"HQG-Net: Unpaired Medical Image Enhancement with High-Quality Guidance","created":"2023-07-15","cited_by_count":36},{"id":"2306.04236","title":"Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond","created":"2023-06-07","cited_by_count":31},{"id":"2210.03061","title":"Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removal","created":"2022-10-06","cited_by_count":28},{"id":"2410.15334","title":"Modality-Fair Preference Optimization for Trustworthy MLLM Alignment","created":"2024-10-20","cited_by_count":26},{"id":"2402.05809","title":"You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement","created":"2024-02-08","cited_by_count":24},{"id":"2409.15739","title":"Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint","created":"2024-09-24","cited_by_count":24},{"id":"2403.07408","title":"NightHaze: Nighttime Image Dehazing via Self-Prior Learning","created":"2024-03-12","cited_by_count":23},{"id":"2403.02601","title":"Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning","created":"2024-03-05","cited_by_count":19},{"id":"2407.16957","title":"Raindrop Clarity: A Dual-Focused Dataset for Day and Night Raindrop Removal","created":"2024-07-24","cited_by_count":17},{"id":"2407.14900","title":"AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement","created":"2024-07-20","cited_by_count":16},{"id":"2207.04754","title":"Snow Mask Guided Adaptive Residual Network for Image Snow Removal","created":"2022-07-11","cited_by_count":13},{"id":"2208.09703","title":"SnowFormer: Context Interaction Transformer with Scale-awareness for Single Image Desnowing","created":"2022-08-20","cited_by_count":13},{"id":"2407.08280","title":"WayveScenes101: A Dataset and Benchmark for Novel View Synthesis in Autonomous Driving","created":"2024-07-11","cited_by_count":13},{"id":"2404.01342","title":"DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model","created":"2024-03-31","cited_by_count":12},{"id":"2107.14229","title":"Physics-informed Guided Disentanglement in Generative Networks","created":"2021-07-29","cited_by_count":9},{"id":"2311.11695","title":"Clarity ChatGPT: An Interactive and Adaptive Processing System for Image Restoration and Enhancement","created":"2023-11-20","cited_by_count":5},{"id":"2409.18899","title":"Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors","created":"2024-09-27","cited_by_count":4}],"next_cursor":null}