{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1511.06434","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","created":"2015-11-19","cited_by_count":2054},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"2305.16322","title":"Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":359},{"id":"2204.14217","title":"CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers","created":"2022-04-28","cited_by_count":307},{"id":"2309.15807","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","created":"2023-09-27","cited_by_count":279},{"id":"2402.17245","title":"Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation","created":"2024-02-27","cited_by_count":256},{"id":"1706.08500","title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","created":"2017-06-26","cited_by_count":213},{"id":"2212.09611","title":"Optimizing Prompts for Text-to-Image Generation","created":"2022-12-19","cited_by_count":207},{"id":"2306.00983","title":"StyleDrop: Text-to-Image Generation in Any Style","created":"2023-06-01","cited_by_count":199},{"id":"2407.11062","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","created":"2024-07-10","cited_by_count":127},{"id":"2403.05121","title":"CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion","created":"2024-03-08","cited_by_count":72},{"id":"2403.01446","title":"GuardT2I: Defending Text-to-Image Models from Adversarial Prompts","created":"2024-03-03","cited_by_count":62},{"id":"2407.01414","title":"StyleShot: A Snapshot on Any Style","created":"2024-07-01","cited_by_count":62},{"id":"2405.03486","title":"UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images","created":"2024-05-06","cited_by_count":53},{"id":"2211.12112","title":"Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark","created":"2022-11-22","cited_by_count":41},{"id":"2410.15236","title":"Jailbreaking and Mitigation of Vulnerabilities in Large Language Models","created":"2024-10-20","cited_by_count":34},{"id":"2010.12136","title":"Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation","created":"2020-10-23","cited_by_count":33},{"id":"2312.06573","title":"ControlNet-XS: Rethinking the Control of Text-to-Image Diffusion Models as Feedback-Control Systems","created":"2023-12-11","cited_by_count":30},{"id":"2403.06381","title":"Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models","created":"2024-03-11","cited_by_count":27},{"id":"2409.08087","title":"Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks","created":"2024-09-12","cited_by_count":26},{"id":"2409.18991","title":"Surveying the MLLM Landscape: A Meta-Review of Current Surveys","created":"2024-09-17","cited_by_count":20},{"id":"2311.06752","title":"BeautifulPrompt: Towards Automatic Prompt Engineering for Text-to-Image Synthesis","created":"2023-11-12","cited_by_count":18},{"id":"2304.09728","title":"Any-to-Any Style Transfer: Making Picasso and Da Vinci Collaborate","created":"2023-04-19","cited_by_count":17},{"id":"2410.21966","title":"PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference","created":"2024-10-29","cited_by_count":17},{"id":"2408.15098","title":"CLIP-AGIQA: Boosting the Performance of AI-Generated Image Quality Assessment with CLIP","created":"2024-08-27","cited_by_count":14},{"id":"2311.12229","title":"NeuroPrompts: An Adaptive Framework to Optimize Prompts for Text-to-Image Generation","created":"2023-11-20","cited_by_count":10},{"id":"2403.18461","title":"An Efficient and Harmonized Framework for Balanced Cross-Domain Feature Integration","created":"2024-03-27","cited_by_count":7},{"id":"2404.14132","title":"CRNet: A Detail-Preserving Network for Unified Image Restoration and Enhancement Task","created":"2024-04-22","cited_by_count":6},{"id":"2411.05036","title":"From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models","created":"2024-11-06","cited_by_count":6},{"id":"2304.12035","title":"GRIG: Few-Shot Generative Residual Image Inpainting","created":"2023-04-24","cited_by_count":4},{"id":"2410.18866","title":"The Cat and Mouse Game: The Ongoing Arms Race Between Diffusion Models and Detection Methods","created":"2024-10-24","cited_by_count":4},{"id":"2310.09247","title":"Hypernymy Understanding Evaluation of Text-to-Image Models via WordNet Hierarchy","created":"2023-10-13","cited_by_count":3},{"id":"2311.13620","title":"The Challenges of Image Generation Models in Generating Multi-Component Images","created":"2023-11-22","cited_by_count":3},{"id":"2406.13281","title":"ECAFormer: Low-light Image Enhancement using Cross Attention","created":"2024-06-19","cited_by_count":2},{"id":"2302.09762","title":"Metropolis Theorem and Its Applications in Single Image Detail Enhancement","created":"2023-02-20","cited_by_count":1},{"id":"2308.11421","title":"TurboViT: Generating Fast Vision Transformers via Generative Architecture Search","created":"2023-08-22","cited_by_count":1}],"next_cursor":null}