{"list":"other","total":56,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"2310.00426","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","created":"2023-09-30","cited_by_count":864},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2305.08322","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","created":"2023-05-15","cited_by_count":708},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"id":"2311.04257","title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","created":"2023-11-07","cited_by_count":547},{"id":"2306.09212","title":"CMMLU: Measuring massive multitask language understanding in Chinese","created":"2023-06-15","cited_by_count":449},{"id":"2306.16527","title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","created":"2023-06-21","cited_by_count":316},{"id":"2408.04840","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","created":"2024-08-09","cited_by_count":291},{"id":"2305.15005","title":"Sentiment Analysis in the Era of Large Language Models: A Reality Check","created":"2023-05-24","cited_by_count":268},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"2407.03320","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","created":"2024-07-03","cited_by_count":195},{"id":"1906.02569","title":"Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild","created":"2019-06-06","cited_by_count":178},{"id":"2401.05252","title":"PIXART-{\\delta}: Fast and Controllable Image Generation with Latent Consistency Models","created":"2024-01-10","cited_by_count":141},{"id":"2309.04946","title":"Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation","created":"2023-09-10","cited_by_count":81},{"id":"2305.11255","title":"Reasoning Implicit Sentiment with Chain-of-Thought Prompting","created":"2023-05-18","cited_by_count":80},{"id":"2304.09582","title":"Is ChatGPT Equipped with Emotional Dialogue Capabilities?","created":"2023-04-19","cited_by_count":54},{"id":"2402.12071","title":"EmoBench: Evaluating the Emotional Intelligence of Large Language Models","created":"2024-02-19","cited_by_count":53},{"id":"2402.03413","title":"Perceptual Video Quality Assessment: A Survey","created":"2024-02-05","cited_by_count":43},{"id":"2406.03070","title":"A-Bench: Are LMMs Masters at Evaluating AI-generated Images?","created":"2024-06-05","cited_by_count":39},{"id":"2409.20063","title":"Q-Bench-Video: Benchmarking the Video Quality Understanding of LMMs","created":"2024-09-30","cited_by_count":39},{"id":"2401.04608","title":"EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models","created":"2024-01-09","cited_by_count":37},{"id":"2308.13911","title":"A Wide Evaluation of ChatGPT on Affective Computing Tasks","created":"2023-08-26","cited_by_count":30},{"id":"2307.02808","title":"Advancing Zero-Shot Digital Human Quality Assessment through Text-Prompted Evaluation","created":"2023-07-06","cited_by_count":27},{"id":"2401.03429","title":"MERBench: A Unified Evaluation Benchmark for Multimodal Emotion Recognition","created":"2024-01-07","cited_by_count":27},{"id":"2409.00031","title":"Quality Assessment in the Era of Large Models: A Survey","created":"2024-08-17","cited_by_count":26},{"id":"2408.04638","title":"Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective","created":"2024-07-30","cited_by_count":25},{"id":"2302.08624","title":"InstructABSA: Instruction Learning for Aspect Based Sentiment Analysis","created":"2023-02-16","cited_by_count":23},{"id":"2303.08050","title":"Subjective and Objective Quality Assessment for in-the-Wild Computer Graphics Images","created":"2023-03-14","cited_by_count":21},{"id":"2306.05658","title":"GMS-3DQA: Projection-based Grid Mini-patch Sampling for 3D Model Quality Assessment","created":"2023-06-09","cited_by_count":21},{"id":"2410.21259","title":"AutoBench-V: Can Large Vision-Language Models Benchmark Themselves?","created":"2024-10-28","cited_by_count":21},{"id":"2401.06659","title":"WisdoM: Improving Multimodal Sentiment Analysis by Fusing Contextual World Knowledge","created":"2024-01-12","cited_by_count":16},{"id":"2209.09489","title":"Perceptual Quality Assessment for Digital Human Heads","created":"2022-09-20","cited_by_count":13},{"id":"2403.00354","title":"Self-Consistent Reasoning-based Aspect-Sentiment Quad Prediction with Extract-Then-Assign Strategy","created":"2024-03-01","cited_by_count":12},{"id":"2311.01876","title":"Sentiment Analysis through LLM Negotiations","created":"2023-11-03","cited_by_count":11},{"id":"2212.12734","title":"DDH-QA: A Dynamic Digital Humans Quality Assessment Database","created":"2022-12-24","cited_by_count":9},{"id":"2309.02045","title":"Enhance Multi-domain Sentiment Analysis of Review Texts through Prompting Strategies","created":"2023-09-05","cited_by_count":7},{"id":"2310.15984","title":"Geometry-Aware Video Quality Assessment for Dynamic Digital Human","created":"2023-10-24","cited_by_count":7},{"id":"2309.03787","title":"USA: Universal Sentiment Analysis Model & Construction of Japanese Sentiment Text Classification and Part of Speech Dataset","created":"2023-09-07","cited_by_count":6},{"id":"2310.16732","title":"A No-Reference Quality Assessment Method for Digital Human Head","created":"2023-10-25","cited_by_count":6},{"id":"2310.20251","title":"An Implementation of Multimodal Fusion System for Intelligent Digital Human Generation","created":"2023-10-31","cited_by_count":6},{"id":"2409.07236","title":"3DGCQA: A Quality Assessment Database for 3D AI-Generated Contents","created":"2024-09-11","cited_by_count":6},{"id":"2310.17147","title":"Simple Baselines for Projection-based Full-reference and No-reference Point Cloud Quality Assessment","created":"2023-10-26","cited_by_count":5}],"next_cursor":null}