{"list":"other","total":99,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"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":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2211.12572","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","created":"2022-11-22","cited_by_count":906},{"id":"2304.08465","title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","created":"2023-04-17","cited_by_count":727},{"id":"2306.10012","title":"MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing","created":"2023-06-16","cited_by_count":624},{"id":"2303.07345","title":"Erasing Concepts from Diffusion Models","created":"2023-03-13","cited_by_count":539},{"id":"2311.10089","title":"Emu Edit: Precise Image Editing via Recognition and Generation Tasks","created":"2023-11-16","cited_by_count":324},{"id":"2403.06135","title":"MACE: Mass Concept Erasure in Diffusion Models","created":"2024-03-10","cited_by_count":307},{"id":"2407.05282","title":"UltraEdit: Instruction-based Fine-Grained Image Editing at Scale","created":"2024-07-07","cited_by_count":268},{"id":"2403.20150","title":"TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods","created":"2024-03-29","cited_by_count":249},{"id":"2511.18870","title":"HunyuanVideo 1.5 Technical Report","created":"2025-11-24","cited_by_count":160},{"id":"2401.01686","title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","created":"2024-01-03","cited_by_count":129},{"id":"2410.18775","title":"Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances","created":"2024-10-24","cited_by_count":110},{"id":"2412.10859","title":"DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting","created":"2024-12-14","cited_by_count":107},{"id":"2412.20413","title":"EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers","created":"2024-12-29","cited_by_count":95},{"id":"2410.12261","title":"CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching","created":"2024-10-16","cited_by_count":94},{"id":"2407.02158","title":"UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks","created":"2024-07-02","cited_by_count":65},{"id":"2308.14103","title":"Towards Unified Token Learning for Vision-Language Tracking","created":"2023-08-27","cited_by_count":62},{"id":"2504.12782","title":"Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts","created":"2025-04-17","cited_by_count":62},{"id":"2506.18046","title":"TAB: Unified Benchmarking of Time Series Anomaly Detection Methods","created":"2025-06-22","cited_by_count":60},{"id":"2502.10721","title":"A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspective","created":"2025-02-15","cited_by_count":58},{"id":"2404.10343","title":"The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report","created":"2024-04-16","cited_by_count":57},{"id":"2111.09571","title":"Person Re-identification Method Based on Color Attack and Joint Defence","created":"2021-11-18","cited_by_count":56},{"id":"2406.07255","title":"Towards Realistic Data Generation for Real-World Super-Resolution","created":"2024-06-11","cited_by_count":56},{"id":"2407.21773","title":"RainMamba: Enhanced Locality Learning with State Space Models for Video Deraining","created":"2024-07-31","cited_by_count":56},{"id":"2505.11250","title":"Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline","created":"2025-05-16","cited_by_count":55},{"id":"2503.06617","title":"Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling","created":"2025-03-09","cited_by_count":48},{"id":"2401.01724","title":"Lightweight Adaptive Feature De-drifting for Compressed Image Classification","created":"2024-01-03","cited_by_count":46},{"id":"2401.10090","title":"Cross-Modality Perturbation Synergy Attack for Person Re-identification","created":"2024-01-18","cited_by_count":45},{"id":"2510.23672","title":"DBLoss: Decomposition-based Loss Function for Time Series Forecasting","created":"2025-10-27","cited_by_count":45},{"id":"2101.08533","title":"Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method","created":"2021-01-21","cited_by_count":42},{"id":"2503.21309","title":"FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval","created":"2025-03-27","cited_by_count":42},{"id":"2507.05631","title":"OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrieval","created":"2025-07-08","cited_by_count":40},{"id":"2405.07023","title":"Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolution","created":"2024-05-11","cited_by_count":37},{"id":"2502.00425","title":"MQuant: Unleashing the Inference Potential of Multimodal Large Language Models via Full Static Quantization","created":"2025-02-01","cited_by_count":35},{"id":"2503.00877","title":"Patch-wise Structural Loss for Time Series Forecasting","created":"2025-03-02","cited_by_count":35},{"id":"2509.12662","title":"Chat-Driven Text Generation and Interaction for Person Retrieval","created":"2025-09-16","cited_by_count":34},{"id":"2509.21278","title":"Does FLUX Already Know How to Perform Physically Plausible Image Composition?","created":"2025-09-25","cited_by_count":32},{"id":"2512.02792","title":"HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval","created":"2025-12-02","cited_by_count":32},{"id":"2507.20177","title":"Towards Universal Modal Tracking with Online Dense Temporal Token Learning","created":"2025-07-27","cited_by_count":30},{"id":"2401.15865","title":"LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection","created":"2024-01-29","cited_by_count":29},{"id":"2501.16583","title":"Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image Restoration","created":"2025-01-27","cited_by_count":28},{"id":"2312.06162","title":"Textual Prompt Guided Image Restoration","created":"2023-12-11","cited_by_count":27},{"id":"2408.08665","title":"QMambaBSR: Burst Image Super-Resolution with Query State Space Model","created":"2024-08-16","cited_by_count":27},{"id":"2405.18975","title":"Hierarchical Classification Auxiliary Network for Time Series Forecasting","created":"2024-05-29","cited_by_count":26},{"id":"2411.10798","title":"Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolution","created":"2024-11-16","cited_by_count":26},{"id":"2410.09836","title":"Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift","created":"2024-10-13","cited_by_count":24},{"id":"2504.04517","title":"Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detection","created":"2025-04-06","cited_by_count":24},{"id":"2401.10512","title":"Exploring Color Invariance through Image-Level Ensemble Learning","created":"2024-01-19","cited_by_count":23},{"id":"2407.13640","title":"Beyond Augmentation: Empowering Model Robustness under Extreme Capture Environments","created":"2024-07-18","cited_by_count":23},{"id":"2507.21606","title":"Exploring Decoupled Spatio-Temporal Consistency Learning and Self-Prompting Evolution for Self-Supervised Tracking","created":"2025-07-29","cited_by_count":23},{"id":"2601.12768","title":"Delving Deeper: Hierarchical Visual Perception for Robust Video-Text Retrieval","created":"2026-01-19","cited_by_count":23},{"id":"2503.08271","title":"LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization","created":"2025-03-11","cited_by_count":22},{"id":"2508.21767","title":"UItron: Foundational GUI Agent with Advanced Perception and Planning","created":"2025-08-29","cited_by_count":22},{"id":"2502.12913","title":"GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning","created":"2025-02-18","cited_by_count":21},{"id":"2404.16484","title":"Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Survey","created":"2024-04-25","cited_by_count":19},{"id":"2411.06456","title":"Dropout the High-rate Downsampling: A Novel Design Paradigm for UHD Image Restoration","created":"2024-11-10","cited_by_count":19},{"id":"2412.00878","title":"Beyond Pixels: Text Enhances Generalization in Real-World Image Restoration","created":"2024-12-01","cited_by_count":17},{"id":"2505.12266","title":"PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement","created":"2025-05-18","cited_by_count":17},{"id":"2402.04855","title":"Dual-Path Coupled Image Deraining Network via Spatial-Frequency Interaction","created":"2024-02-07","cited_by_count":16},{"id":"2409.02431","title":"Adversarial Learning for Neural PDE Solvers with Sparse Data","created":"2024-09-04","cited_by_count":16},{"id":"2502.12802","title":"PPGF: Probability Pattern-Guided Time Series Forecasting","created":"2025-02-18","cited_by_count":16},{"id":"2504.00870","title":"Data-free Knowledge Distillation with Diffusion Models","created":"2025-04-01","cited_by_count":16},{"id":"2408.10145","title":"Multi-Scale Representation Learning for Image Restoration with State-Space Model","created":"2024-08-19","cited_by_count":15},{"id":"2601.18625","title":"CONQUER: Context-Aware Representation with Query Enhancement for Text-Based Person Search","created":"2026-01-26","cited_by_count":15},{"id":"2508.09173","title":"Camel: Energy-Aware LLM Inference on Resource-Constrained Devices","created":"2025-08-07","cited_by_count":14},{"id":"2508.16830","title":"AIM 2025 Low-light RAW Video Denoising Challenge: Dataset, Methods and Results","created":"2025-08-22","cited_by_count":14},{"id":"2601.16155","title":"HVD: Human Vision-Driven Video Representation Learning for Text-Video Retrieval","created":"2026-01-22","cited_by_count":14},{"id":"2309.04780","title":"Latent Degradation Representation Constraint for Single Image Deraining","created":"2023-09-09","cited_by_count":13},{"id":"2508.03077","title":"RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions","created":"2025-08-05","cited_by_count":13},{"id":"2411.11906","title":"$\\text{S}^{3}$Mamba: Arbitrary-Scale Super-Resolution via Scaleable State Space Model","created":"2024-11-16","cited_by_count":12},{"id":"2507.10293","title":"Show and Polish: Reference-Guided Identity Preservation in Face Video Restoration","created":"2025-07-14","cited_by_count":12},{"id":"2406.07006","title":"MIPI 2024 Challenge on Few-shot RAW Image Denoising: Methods and Results","created":"2024-06-11","cited_by_count":11},{"id":"2406.14912","title":"FC3DNet: A Fully Connected Encoder-Decoder for Efficient Demoir'eing","created":"2024-06-21","cited_by_count":11},{"id":"2410.07901","title":"Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization","created":"2024-10-10","cited_by_count":11},{"id":"2503.17132","title":"Temporal-Guided Spiking Neural Networks for Event-Based Human Action Recognition","created":"2025-03-21","cited_by_count":11},{"id":"2510.03302","title":"Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Models","created":"2025-09-30","cited_by_count":11},{"id":"2503.19474","title":"A-MESS: Anchor based Multimodal Embedding with Semantic Synchronization for Multimodal Intent Recognition","created":"2025-03-25","cited_by_count":10},{"id":"2505.00941","title":"FreCT: Frequency-augmented Convolutional Transformer for Robust Time Series Anomaly Detection","created":"2025-05-02","cited_by_count":10},{"id":"2509.23584","title":"VividFace: High-Quality and Efficient One-Step Diffusion For Video Face Enhancement","created":"2025-09-28","cited_by_count":10},{"id":"2109.04381","title":"Copy-Move Image Forgery Detection Based on Evolving Circular Domains Coverage","created":"2021-09-09","cited_by_count":9},{"id":"2406.16477","title":"DaLPSR: Leverage Degradation-Aligned Language Prompt for Real-World Image Super-Resolution","created":"2024-06-24","cited_by_count":9},{"id":"2507.17617","title":"Reusing Attention for One-stage Lane Topology Understanding","created":"2025-07-23","cited_by_count":9},{"id":"2504.14205","title":"Dual-channel Heterophilic Message Passing for Graph Fraud Detection","created":"2025-04-19","cited_by_count":8},{"id":"2504.14204","title":"DConAD: A Differencing-based Contrastive Representation Learning Framework for Time Series Anomaly Detection","created":"2025-04-19","cited_by_count":7},{"id":"2505.13489","title":"Contrastive Cross-Course Knowledge Tracing via Concept Graph Guided Knowledge Transfer","created":"2025-05-14","cited_by_count":7},{"id":"2506.11127","title":"UITron-Speech: Towards Automated GUI Agents Based on Speech Instructions","created":"2025-06-10","cited_by_count":7},{"id":"2510.06635","title":"StruSR: Structure-Aware Symbolic Regression with Physics-Informed Taylor Guidance","created":"2025-10-08","cited_by_count":6},{"id":"2508.08789","title":"Never compromise with vulnerabilities: a comprehensive survey on AI governance","created":"2025-08-12","cited_by_count":5},{"id":"2601.00322","title":"Depth-Synergized Mamba Meets Memory Experts for All-Day Image Reflection Separation","created":"2026-01-01","cited_by_count":5},{"id":"2507.13373","title":"Butter: Frequency Consistency and Hierarchical Fusion for Autonomous Driving Object Detection","created":"2025-07-12","cited_by_count":4},{"id":"2603.20310","title":"GraphiContact: Pose-aware Human-Scene Robust Contact Perception for Interactive Systems","created":"2026-03-19","cited_by_count":1}],"next_cursor":null}