{"list":"other","total":69,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027},{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991},{"id":"2305.01569","title":"Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation","created":"2023-05-02","cited_by_count":977},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2211.14275","title":"Solving math word problems with process- and outcome-based feedback","created":"2022-11-25","cited_by_count":901},{"id":"2306.09341","title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","created":"2023-06-15","cited_by_count":890},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"2302.00482","title":"Improving and generalizing flow-based generative models with minibatch optimal transport","created":"2023-02-01","cited_by_count":879},{"id":"2311.12908","title":"Diffusion Model Alignment Using Direct Preference Optimization","created":"2023-11-21","cited_by_count":790},{"id":"2301.13826","title":"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models","created":"2023-01-31","cited_by_count":702},{"id":"2203.02923","title":"GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation","created":"2022-03-06","cited_by_count":516},{"id":"2408.15240","title":"Generative Verifiers: Reward Modeling as Next-Token Prediction","created":"2024-08-27","cited_by_count":480},{"id":"2305.16381","title":"DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":450},{"id":"2212.05032","title":"Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis","created":"2022-12-09","cited_by_count":388},{"id":"2406.03816","title":"ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search","created":"2024-06-06","cited_by_count":344},{"id":"2205.09712","title":"Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning","created":"2022-05-19","cited_by_count":334},{"id":"2405.08748","title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","created":"2024-05-14","cited_by_count":298},{"id":"2410.08146","title":"Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning","created":"2024-10-10","cited_by_count":279},{"id":"2106.10934","title":"GRAND: Graph Neural Diffusion","created":"2021-06-21","cited_by_count":258},{"id":"2404.03683","title":"Stream of Search (SoS): Learning to Search in Language","created":"2024-04-01","cited_by_count":145},{"id":"2502.06703","title":"Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling","created":"2025-02-10","cited_by_count":136},{"id":"2404.04650","title":"InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization","created":"2024-04-06","cited_by_count":123},{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112},{"id":"2310.17590","title":"Noise-Free Score Distillation","created":"2023-10-26","cited_by_count":99},{"id":"2307.10864","title":"Divide & Bind Your Attention for Improved Generative Semantic Nursing","created":"2023-07-20","cited_by_count":81},{"id":"2304.14530","title":"Generating images of rare concepts using pre-trained diffusion models","created":"2023-04-27","cited_by_count":79},{"id":"2305.03382","title":"Guided Image Synthesis via Initial Image Editing in Diffusion Model","created":"2023-05-05","cited_by_count":63},{"id":"2411.11694","title":"Enhancing LLM Reasoning with Reward-guided Tree Search","created":"2024-11-18","cited_by_count":58},{"id":"2405.18881","title":"Inference-Time Alignment of Diffusion Models with Direct Noise Optimization","created":"2024-05-29","cited_by_count":55},{"id":"2406.15657","title":"FIRST: Faster Improved Listwise Reranking with Single Token Decoding","created":"2024-06-21","cited_by_count":54},{"id":"2405.14828","title":"Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image Diffusion Models","created":"2024-05-23","cited_by_count":48},{"id":"2502.17437","title":"Fractal Generative Models","created":"2025-02-24","cited_by_count":46},{"id":"2412.10891","title":"Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection","created":"2024-12-14","cited_by_count":41},{"id":"2501.19252","title":"Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search","created":"2025-01-31","cited_by_count":41},{"id":"2505.17618","title":"Scaling Image and Video Generation via Test-Time Evolutionary Search","created":"2025-05-23","cited_by_count":40},{"id":"2501.05370","title":"Accelerated Diffusion Models via Speculative Sampling","created":"2025-01-09","cited_by_count":31},{"id":"2302.00849","title":"Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent","created":"2023-02-02","cited_by_count":25},{"id":"2404.01054","title":"Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment","created":"2024-04-01","cited_by_count":25},{"id":"2401.03140","title":"Fair Sampling in Diffusion Models through Switching Mechanism","created":"2024-01-06","cited_by_count":12},{"id":"2502.18873","title":"Multi-LLM Collaborative Search for Complex Problem Solving","created":"2025-02-26","cited_by_count":10},{"id":"2503.10183","title":"Through the Magnifying Glass: Adaptive Perception Magnification for Hallucination-Free VLM Decoding","created":"2025-03-13","cited_by_count":10},{"id":"2502.08690","title":"Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation","created":"2025-02-12","cited_by_count":4},{"id":"2411.15447","title":"Gotta Hear Them All: Towards Sound Source Aware Audio Generation","created":"2024-11-23","cited_by_count":1}],"next_cursor":null}