Zhangyang Wang

Oscillation Inversion: Training-Free Image and Video Enhancement Through Oscillated Latents in Large Flow Models AAAI 2026 FlowMorph: Revealing an Optimizable Flow Latent Space for Controlled Image Morphing WACV 2026 From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications ICML 2025 On the Provable Separation of Scales in Maximal Update Parameterization ICML 2025 Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention ICML 2025 On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM Serving ICML 2025 PIPA: Preference Alignment as Prior-Informed Statistical Estimation ICML 2025 HALoS: Hierarchical Asynchronous Local SGD over Slow Networks for Geo-Distributed Large Language Model Training ICML 2025 MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models EMNLP 2025 LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing ICLR 2025 Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing ICLR 2025 Copy or Not? Reference-Based Face Image Restoration with Fine Details WACV 2025 4K4DGen: Panoramic 4D Generation at 4K Resolution ICLR 2025 Sparse Transfer Learning Accelerates and Enhances Certified Robustness: A Comprehensive Study AAAI 2025 HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models ICLR 2025 Random Pruning Over-parameterized Neural Networks Can Improve Generalization: A Training Dynamics Analysis JMLR 2025 FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting CVPR 2025 Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement ACL 2025 Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields CVPR 2025 Steepest Descent Density Control for Compact 3D Gaussian Splatting CVPR 2025 StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text CVPR 2025 Transformers Provably Learn Two-Mixture of Linear Classification via Gradient Flow ICLR 2025 Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding ICML 2025 SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity AISTATS 2025 SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training ICLR 2025 A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs CVPR 2025 R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference ICLR 2025 AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models NIPS 2024 $\texttt{Model-GLUE}$: Democratized LLM Scaling for A Large Model Zoo in the Wild NIPS 2024 Large Spatial Model: End-to-end Unposed Images to Semantic 3D NIPS 2024 Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis NIPS 2024 Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding NIPS 2024 Diffusion4D: Fast Spatial-temporal Consistent 4D generation via Video Diffusion Models NIPS 2024 $\textit{Read-ME}$: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design NIPS 2024 LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS NIPS 2024 Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community ICLR 2024 Doubly Robust Instance-Reweighted Adversarial Training ICLR 2024 FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting ECCV 2024 VersatileGaussian: Real-time Neural Rendering for Versatile Tasks using Gaussian Splatting ECCV 2024 FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and Altitude WACV 2024 DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting ECCV 2024 Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK JMLR 2024 RankMean: Module-Level Importance Score for Merging Fine-tuned LLM Models ACL 2024 Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields CVPR 2024 Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D CVPR 2024 OpenBias: Open-set Bias Detection in Text-to-Image Generative Models CVPR 2024 Taming Mode Collapse in Score Distillation for Text-to-3D Generation CVPR 2024 PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor CVPR 2024 Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models CVPR 2024 Zero-Painter: Training-Free Layout Control for Text-to-Image Synthesis CVPR 2024 GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection ICML 2024 Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark ICML 2024 Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity ICML 2024 Junk DNA Hypothesis: Pruning Small Pre-Trained Weights $\textitIrreversibly$ and $\textitMonotonically$ Impairs “Difficult" Downstream Tasks in LLMs ICML 2024 Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once ICML 2024 Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression ICML 2024 Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference ICML 2024 LLaGA: Large Language and Graph Assistant ICML 2024 LoCoCo: Dropping In Convolutions for Long Context Compression ICML 2024 Flextron: Many-in-One Flexible Large Language Model ICML 2024 Compressing LLMs: The Truth is Rarely Pure and Never Simple ICLR 2024 Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day ICLR 2024 DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer ICLR 2024 Latent 3D Graph Diffusion ICLR 2024 Polynomial Width is Sufficient for Set Representation with High-dimensional Features ICLR 2024 Principled Architecture-aware Scaling of Hyperparameters ICLR 2024 Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality ICLR 2024 Safe and Robust Watermark Injection with a Single OoD Image ICLR 2024 Expressive Gaussian Human Avatars from Monocular RGB Video NIPS 2024 M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation ICLR 2023 “No Free Lunch” in Neural Architectures? A Joint Analysis of Expressivity, Convergence, and Generalization AUTOML 2023 Safeguarded Learned Convex Optimization AAAI 2023 Federated Robustness Propagation: Sharing Adversarial Robustness in Heterogeneous Federated Learning AAAI 2023 Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training AAAI 2023 DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models ACL 2023 On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks AISTATS 2023 Learning to Generalize Provably in Learning to Optimize AISTATS 2023 MMG-Ego4D: Multimodal Generalization in Egocentric Action Recognition CVPR 2023 Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models To Learn Any Unseen Style CVPR 2023 NeuralLift-360: Lifting an In-the-Wild 2D Photo to a 3D Object With 360deg Views CVPR 2023 AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training CVPR 2023 StegaNeRF: Embedding Invisible Information within Neural Radiance Fields ICCV 2023 Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts ICCV 2023 Versatile Diffusion: Text, Images and Variations All in One Diffusion Model ICCV 2023 Robust Mixture-of-Expert Training for Convolutional Neural Networks ICCV 2023 AdaMV-MoE: Adaptive Multi-Task Vision Mixture-of-Experts ICCV 2023 Physics-Driven Turbulence Image Restoration with Stochastic Refinement ICCV 2023 Vision HGNN: An Image is More than a Graph of Nodes ICCV 2023 Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators ICCV 2023 Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations ICLR 2023 Is Attention All That NeRF Needs? ICLR 2023 More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity ICLR 2023 Equivariant Hypergraph Diffusion Neural Operators ICLR 2023 HotProtein: A Novel Framework for Protein Thermostability Prediction and Editing ICLR 2023 NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes ICLR 2023 Graph Domain Adaptation via Theory-Grounded Spectral Regularization ICLR 2023 Continuous-Discrete Convolution for Geometry-Sequence Modeling in Proteins ICLR 2023 REVISITING PRUNING AT INITIALIZATION THROUGH THE LENS OF RAMANUJAN GRAPH ICLR 2023 Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together! ICLR 2023 Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers ICLR 2023 Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection ICLR 2023 Learning to Grow Pretrained Models for Efficient Transformer Training ICLR 2023 Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights? ICML 2023 Learning to Optimize Differentiable Games ICML 2023 Are Large Kernels Better Teachers than Transformers for ConvNets? ICML 2023 Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication ICML 2023 Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models ICML 2023 Towards Constituting Mathematical Structures for Learning to Optimize ICML 2023 Lowering the Pre-training Tax for Gradient-based Subset Training: A Lightweight Distributed Pre-Training Toolkit ICML 2023 Data Efficient Neural Scaling Law via Model Reusing ICML 2023 Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation ICML 2023 Attend Who Is Weak: Pruning-Assisted Medical Image Localization Under Sophisticated and Implicit Imbalances WACV 2023 Point Cloud Domain Adaptation via Masked Local 3D Structure Prediction ECCV 2022 Data-Efficient Double-Win Lottery Tickets from Robust Pre-training ICML 2022 Learning to Optimize: A Primer and A Benchmark JMLR 2022 Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets ICML 2022 VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian Novelty ICML 2022 Density-Aware Personalized Training for Risk Prediction in Imbalanced Medical Data MLHC 2022 Scalable Learning to Optimize: A Learned Optimizer Can Train Big Models ECCV 2022 AutoCoG: A Unified Data-Model Co-Search Framework for Graph Neural Networks AUTOML 2022 Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization NIPS 2022 Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork NIPS 2022 Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis NIPS 2022 Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets NIPS 2022 Back Razor: Memory-Efficient Transfer Learning by Self-Sparsified Backpropagation NIPS 2022 M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design NIPS 2022 Signal Processing for Implicit Neural Representations NIPS 2022 Symbolic Distillation for Learned TCP Congestion Control NIPS 2022 Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again NIPS 2022 A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking NIPS 2022 Sparse Winning Tickets are Data-Efficient Image Recognizers NIPS 2022 Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative NIPS 2022 Aug-NeRF: Training Stronger Neural Radiance Fields With Triple-Level Physically-Grounded Augmentations CVPR 2022 CADTransformer: Panoptic Symbol Spotting Transformer for CAD Drawings CVPR 2022 The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy CVPR 2022 Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free CVPR 2022 EI-CLIP: Entity-Aware Interventional Contrastive Learning for E-Commerce Cross-Modal Retrieval CVPR 2022 VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution CVPR 2022 DiSparse: Disentangled Sparsification for Multitask Model Compression CVPR 2022 Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Search WACV 2022 VFDS: Variational Foresight Dynamic Selection in Bayesian Neural Networks for Efficient Human Activity Recognition AISTATS 2022 Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better AAAI 2022 SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image ECCV 2022 DNA: Improving Few-Shot Transfer Learning with Low-Rank Decomposition and Alignment ECCV 2022 Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and a New Physics-Inspired Transformer Model ECCV 2022 Fast and High Quality Image Denoising via Malleable Convolution ECCV 2022 Unified Implicit Neural Stylization ECCV 2022 A Simple Single-Scale Vision Transformer for Object Detection and Instance Segmentation ECCV 2022 Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable ICLR 2022 Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization ICLR 2022 Auto-scaling Vision Transformers without Training ICLR 2022 The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training ICLR 2022 Optimizer Amalgamation ICLR 2022 Unified Visual Transformer Compression ICLR 2022 Peek-a-Boo: What (More) is Disguised in a Randomly Weighted Neural Network, and How to Find It Efficiently ICLR 2022 Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods ICLR 2022 Bayesian Modeling and Uncertainty Quantification for Learning to Optimize: What, Why, and How ICLR 2022 Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity ICLR 2022 Symbolic Learning to Optimize: Towards Interpretability and Scalability ICLR 2022 Sparsity Winning Twice: Better Robust Generalization from More Efficient Training ICLR 2022 Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice ICLR 2022 Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot, Any-Sparsity, And No Retraining ICLR 2022 Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity WACV 2022 Knowledge-Augmented Contrastive Learning for Abnormality Classification and Localization in Chest X-Rays With Radiomics Using a Feedback Loop WACV 2022 Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition ICML 2022 Removing Batch Normalization Boosts Adversarial Training ICML 2022 Neural Implicit Dictionary Learning via Mixture-of-Expert Training ICML 2022 Universality of Winning Tickets: A Renormalization Group Perspective ICML 2022 Training Your Sparse Neural Network Better with Any Mask ICML 2022 Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness ICML 2022 Efficient Lottery Ticket Finding: Less Data is More ICML 2021 EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets ACL 2021 Learning Model-Based Privacy Protection under Budget Constraints AAAI 2021 Searching for Two-Stream Models in Multivariate Space for Video Recognition ICCV 2021 SSH: A Self-Supervised Framework for Image Harmonization ICCV 2021 GDP: Stabilized Neural Network Pruning via Gates With Differentiable Polarization ICCV 2021 Hyperparameter Tuning is All You Need for LISTA NIPS 2021 Sparse Training via Boosting Pruning Plasticity with Neuroregeneration NIPS 2021 Improving Contrastive Learning on Imbalanced Data via Open-World Sampling NIPS 2021 You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership NIPS 2021 AugMax: Adversarial Composition of Random Augmentations for Robust Training NIPS 2021 Robust Overfitting may be mitigated by properly learned smoothening ICLR 2021 Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective ICLR 2021 Contrastive Syn-to-Real Generalization ICLR 2021 Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning ICLR 2021 Learning A Minimax Optimizer: A Pilot Study ICLR 2021 UMEC: Unified model and embedding compression for efficient recommendation systems ICLR 2021 A Design Space Study for LISTA and Beyond ICLR 2021 Undistillable: Making A Nasty Teacher That CANNOT teach students ICLR 2021 EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets IJCNLP 2021 Stronger NAS with Weaker Predictors NIPS 2021 The Elastic Lottery Ticket Hypothesis NIPS 2021 IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers NIPS 2021 A Unified Lottery Ticket Hypothesis for Graph Neural Networks ICML 2021 Self-Damaging Contrastive Learning ICML 2021 Graph Contrastive Learning Automated ICML 2021 Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm ICML 2021 Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective NIPS 2021 Troubleshooting Blind Image Quality Models in the Wild CVPR 2021 Chasing Sparsity in Vision Transformers: An End-to-End Exploration NIPS 2021 TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up NIPS 2021 Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot? NIPS 2021 Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems NIPS 2021 The Lottery Tickets Hypothesis for Supervised and Self-Supervised Pre-Training in Computer Vision Models CVPR 2021 Debiased Subjective Assessment of Real-World Image Enhancement CVPR 2021 Self-Supervised Learning for Generalizable Out-of-Distribution Detection AAAI 2020 Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free NIPS 2020 DAVID: Dual-Attentional Video Deblurring WACV 2020 Calibrated Domain-Invariant Learning for Highly Generalizable Large Scale Re-Identification WACV 2020 MATE: Plugging in Model Awareness to Task Embedding for Meta Learning NIPS 2020 FasterSeg: Searching for Faster Real-time Semantic Segmentation ICLR 2020 Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches ECCV 2020 I Am Going MAD: Maximum Discrepancy Competition for Comparing Classifiers Adaptively ICLR 2020 Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference ICLR 2020 Drawing Early-Bird Tickets: Toward More Efficient Training of Deep Networks ICLR 2020 FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training NIPS 2020 The Lottery Ticket Hypothesis for Pre-trained BERT Networks NIPS 2020 Robust Pre-Training by Adversarial Contrastive Learning NIPS 2020 Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference AAAI 2020 Peek-a-Boo: Occlusion Reasoning in Indoor Scenes With Plane Representations CVPR 2020 L2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks CVPR 2020 Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning CVPR 2020 Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery AISTATS 2020 NADS: Neural Architecture Distribution Search for Uncertainty Awareness ICML 2020 Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training ICML 2020 Automated Synthetic-to-Real Generalization ICML 2020 AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks ICML 2020 Eliminating the Invariance on the Loss Landscape of Linear Autoencoders ICML 2020 When Does Self-Supervision Help Graph Convolutional Networks? ICML 2020 GAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework ECCV 2020 HALO: Hardware-Aware Learning to Optimize ECCV 2020 ShiftAddNet: A Hardware-Inspired Deep Network NIPS 2020 AutoSpeech: Neural Architecture Search for Speaker Recognition INTERSPEECH 2020 Graph Contrastive Learning with Augmentations NIPS 2020 Training Stronger Baselines for Learning to Optimize NIPS 2020 Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images CVPR 2019 Single Image Deraining: A Comprehensive Benchmark Analysis CVPR 2019 DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better ICCV 2019 AutoGAN: Neural Architecture Search for Generative Adversarial Networks ICCV 2019 Delving Into Robust Object Detection From Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach ICCV 2019 ALISTA: Analytic Weights Are As Good As Learned Weights in LISTA ICLR 2019 E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savings NIPS 2019 Model Compression with Adversarial Robustness: A Unified Optimization Framework NIPS 2019 Plug-and-Play Methods Provably Converge with Properly Trained Denoisers ICML 2019 ABD-Net: Attentive but Diverse Person Re-Identification ICCV 2019 Adaptive Activity Monitoring with Uncertainty Quantification in Switching Gaussian Process Models AISTATS 2019 Learning to Optimize in Swarms NIPS 2019 Controllable Artistic Text Style Transfer via Shape-Matching GAN ICCV 2019 When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach IJCAI 2018 Theoretical Linear Convergence of Unfolded ISTA and Its Practical Weights and Thresholds NIPS 2018 Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions ICML 2018 Can We Gain More from Orthogonality Regularizations in Training Deep Networks? NIPS 2018 Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study ECCV 2018 Doubly Sparsifying Network IJCAI 2017 AOD-Net: All-In-One Dehazing Network ICCV 2017 Robust Video Super-Resolution With Learned Temporal Dynamics ICCV 2017 Studying Very Low Resolution Recognition Using Deep Networks CVPR 2016 D3: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images CVPR 2016 A Joint Optimization Framework of Sparse Coding and Discriminative Clustering IJCAI 2015 On a Theory of Nonparametric Pairwise Similarity for Clustering: Connecting Clustering to Classification NIPS 2014