What Objects Enable, Not What They Are: Functional Latent Spaces for Affordance Reasoning
Conference on Robot Learning (CoRL)
Publication
Below are a list of recent and selected papers.
A mark * denotes the author to be a VITA student or Dr. Wang's mentee.
An up-to-date full paper list can be found here.
Past and Present (2018 - 2027)
Band thickness shows annual paper counts on a shared scale. Select a year within a topic to see its papers.
View annual counts
| Topic | 2018 | 2019 | 2020 | 2021 | 2022 | 2023 | 2024 | 2025 | 2026 | 2027 |
|---|---|---|---|---|---|---|---|---|---|---|
| Model Training & Optimization Algorithms | 0 | 1 | 6 | 8 | 10 | 11 | 5 | 15 | 5 | 0 |
| Efficient Inference & Architecture Design | 1 | 2 | 10 | 12 | 12 | 13 | 13 | 8 | 3 | 1 |
| Reasoning and Agents | 0 | 0 | 0 | 0 | 3 | 2 | 3 | 6 | 10 | 0 |
| Geometric Deep Learning & Graphs | 0 | 0 | 3 | 4 | 8 | 7 | 3 | 2 | 1 | 0 |
| Trustworthy AI | 1 | 1 | 6 | 7 | 12 | 6 | 6 | 6 | 3 | 0 |
| World Model & Physical AI | 0 | 0 | 1 | 0 | 4 | 8 | 13 | 9 | 8 | 0 |
| AI in Medicine & Healthcare | 1 | 2 | 1 | 0 | 1 | 5 | 4 | 3 | 0 | 0 |
| DL Theory: Sparse NNs & Transformers | 0 | 0 | 1 | 0 | 3 | 2 | 4 | 3 | 1 | 0 |
| Learning to Optimize & Inverse Problems | 2 | 3 | 2 | 3 | 7 | 6 | 0 | 0 | 0 | 0 |
| Image Generation & Restoration | 0 | 7 | 6 | 8 | 4 | 7 | 4 | 1 | 2 | 0 |
347 publications
Person Recognition at Altitude and Range: Fusion of Face, Body Shape and Gait
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
2026
LFS: Learning-Based Flexible CPU Scheduler
USENIX Symposium on Networked Systems Design and Implementation (NSDI)
2027
LLMs Can Get "Brain Rot"
Conference on Language Modeling (COLM)
Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?
Conference on Language Modeling (COLM)
The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows
Conference on Language Modeling (COLM)
2026
Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models
Conference on Language Modeling (COLM)
CrashTwin: A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models
European Conference on Computer Vision (ECCV) [Oral]
Seeing Where to Deploy: Metric RGB-Based Traversability Analysis for Aerial-to-Ground Hidden Space Inspection
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
2026
Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning
International Conference on Machine Learning (ICML)
MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games
International Conference on Machine Learning (ICML)
When Do Graph Foundation Models Transfer? A Data-Centric Theory
International Conference on Machine Learning (ICML)
GradientStabilizer: Fix the Norm, Not the Gradient
International Conference on Machine Learning (ICML)
Revisiting Spectral Representations in Generative Diffusion Models
International Conference on Machine Learning (ICML)
2026
Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process
International Conference on Machine Learning (ICML)
2026
Weight Space Should Be a First-Class Generative AI Modality
International Conference on Machine Learning (ICML) Position Track
2026
Mastering Regional 3DGS: Locating, Initializing, and Editing with Diverse 2D Priors
International Journal of Computer Vision (IJCV)
2026
POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shaking
Transactions on Machine Learning Research (TMLR)
Scaling Textual Gradients via Sampling-Based Momentum
ACM Conference on AI and Agentic Systems (CAIS)
2026
HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [Highlight]
VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [Short Version: Best Paper Award, ACM MM 2025 MFMSI Workshop]
Mining Attribute Subspaces for Efficient Fine-tuning of 3D Foundation Models
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
2026
An Overview of Low-Rank Structures in the Training and Adaptation of Large Models
IEEE Signal Processing Magazine (SPM)
2026
Neon: Negative Extrapolation From Self-Training Improves Image Generation
International Conference on Learning Representations (ICLR) [Oral]
Nabla-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Textual Space
International Conference on Learning Representations (ICLR)
Understanding the Mixture-of-Experts with Nadaraya-Watson Kernel
International Conference on Learning Representations (ICLR)
2026
RAPID3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer
International Conference on Learning Representations (ICLR)
LAD-VF: LLM-Automatic Differentiation Enables Fine-Tuning-Free Robot Planning from Formal Methods Feedback
IEEE International Conference on Robotics and Automation (ICRA)
UNCAP: Uncertainty-Guided Neurosymbolic Planning Using Natural Language Communication for Cooperative Autonomous Vehicles
International Conference on Autonomous Agents and Multiagent Systems (AAMAS) [Best Paper Finalist]
Oscillation Inversion: Training-free Image and Video Enhancement through Oscillated Latents in Large Flow Models
AAAI Conference on Artificial Intelligence (AAAI) [Oral]
2026
VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment
International Conference on 3D Vision (3DV) [Short Version: Best Paper Award, CVPR 2025 AI4CC Workshop]
Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
Advances in Neural Information Processing Systems (NeurIPS)
Scaling Up Parameter Generation: A Recurrent Diffusion Approach
Advances in Neural Information Processing Systems (NeurIPS)
REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
Advances in Neural Information Processing Systems (NeurIPS)
Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models
Advances in Neural Information Processing Systems (NeurIPS)
One Token Embedding Is Enough to Deadlock Your Reasoning Large Language Model
Advances in Neural Information Processing Systems (NeurIPS)
SAS: Simulated Attention Score
Advances in Neural Information Processing Systems (NeurIPS)
2025
Martian World Models: Controllable Video Synthesis with Physically Accurate 3D Reconstructions
Advances in Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS D & B)
MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models
Conference on Empirical Methods in Natural Language Processing (EMNLP)
SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?
Conference on Language Modeling (COLM)
SEAL: Steerable Reasoning Calibration of Large Language Models for Free
Conference on Language Modeling (COLM)
Can Scaling Test-Time Compute Improve World Foundation Model?
Conference on Language Modeling (COLM)
LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning
Conference on Language Modeling (COLM)
More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment
Conference on Language Modeling (COLM)
Complete AI-Enabled Echocardiography Interpretation With Multitask Deep Learning
Journal of the American Medical Association (JAMA)
From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories and Applications
International Conference on Machine Learning (ICML)
HALoS: Hierarchical Asynchronous Local SGD over Slow Networks for Geo-Distributed Large Language Model Training
International Conference on Machine Learning (ICML)
Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding
International Conference on Machine Learning (ICML)
On the Provable Separation of Scales in Maximal Update Parameterization
International Conference on Machine Learning (ICML)
2025
PIPA: Preference Alignment as Prior-Informed Statistical Estimation
International Conference on Machine Learning (ICML)
2025
On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM Serving
International Conference on Machine Learning (ICML)
Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention
International Conference on Machine Learning (ICML)
Why Neural Network Can Discover Symbolic Structures with Gradient-based Training: An Algebraic and Geometric Foundation for Neurosymbolic Reasoning
International Conference on Neuro-symbolic Systems (NeuS) [DAPRA Disruptive Idea Paper Award]
2025
Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement
Annual Meeting of the Association for Computational Linguistics (ACL)
FlexGS: Train Once Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Steepest Descent Density Control for Compact 3D Gaussian Splatting
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
StreamingT2V: Consistent Dynamic and Extendable Long Video Generation from Text
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for accelerating Large VLMs
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
APOLLO: SGD-like Memory AdamW-level Performance
Conference on Machine Learning and Systems (MLSys) [Outstanding Paper Honorable Mention]
Know Where You're Uncertain When Planning with Multimodal Foundation Models: A Formal Framework
Conference on Machine Learning and Systems (MLSys)
On How Iterative Magnitude Pruning Discovers Local Receptive Fields in Fully Connected Neural Networks
Conference on Parsimony and Learning (CPAL)
2025
Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients
Conference on Parsimony and Learning (CPAL)
Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing
International Conference on Learning Representations (ICLR)
Transformers Provably Learn Two-Mixture of Linear Classification via Gradient Flow
International Conference on Learning Representations (ICLR)
2025
LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing
International Conference on Learning Representations (ICLR)
2025
R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference
International Conference on Learning Representations (ICLR)
SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training
International Conference on Learning Representations (ICLR)
4K4DGen: Panoramic 4D Generation at 4K Resolution
International Conference on Learning Representations (ICLR) [Spotlight]
HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models
International Conference on Learning Representations (ICLR)
SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity
International Conference on Artificial Intelligence and Statistics (AISTATS)
Sparse Transfer Learning Accelerates and Enhances Certified Robustness
AAAI Conference on Artificial Intelligence (AAAI)
2025
AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving
Transactions on Machine Learning Research (TMLR)
Neuro-symbolic AI as an Antithesis to Scaling Laws
Proceedings of the National Academy of Sciences Nexus (PNAS Nexus)
2025
Deep Learning for Accurate Diagnosis of Viral Infections through scRNA-seq Analysis: A Comprehensive Benchmark Study
Journal of Data-centric Machine Learning Research (DMLR)
LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS
Advances in Neural Information Processing Systems (NeurIPS) [Spotlight]
Expressive Gaussian Human Avatars from Monocular RGB Video
Advances in Neural Information Processing Systems (NeurIPS)
Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
Advances in Neural Information Processing Systems (NeurIPS)
Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding
Advances in Neural Information Processing Systems (NeurIPS)
Large Spatial Model: End-to-end Unposed Images to Semantic 3D
Advances in Neural Information Processing Systems (NeurIPS)
Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis
Advances in Neural Information Processing Systems (NeurIPS)
2024
Diffusion4D: Fast Spatial-temporal Consistent 4D generation via Video Diffusion Models
Advances in Neural Information Processing Systems (NeurIPS)
AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models
Advances in Neural Information Processing Systems (NeurIPS)
Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild
Advances in Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS D & B)
FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting
European Conference on Computer Vision (ECCV)
DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting
European Conference on Computer Vision (ECCV)
VersatileGaussian: Real-time Neural Rendering for Versatile Tasks using Gaussian Splatting
European Conference on Computer Vision (ECCV)
LLM-PBE: Assessing Data Privacy in Large Language Models
International Conference on Very Large Data Bases (VLDB) [Best Paper Finalist]
MM3DGS SLAM: Multi-modal 3D Gaussian Splatting for SLAM Using Vision Depth and Inertial Measurements
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) [Oral Pitch Finalist]
Flextron: Many-in-One Flexible Large Language Model
International Conference on Machine Learning (ICML) [Oral]
2024
LoCoCo: Dropping In Convolutions for Long Context Compression
International Conference on Machine Learning (ICML)
Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs Difficult Downstream Tasks in LLMs
International Conference on Machine Learning (ICML)
Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity
International Conference on Machine Learning (ICML)
LLaGA: Large Language and Graph Assistant
International Conference on Machine Learning (ICML)
Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression
International Conference on Machine Learning (ICML)
Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once
International Conference on Machine Learning (ICML)
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
International Conference on Machine Learning (ICML) [Oral]
Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference
International Conference on Machine Learning (ICML)
Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
International Conference on Machine Learning (ICML)
Taming Mode Collapse in Score Distillation for Text-to-3D Generation
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [Highlight]
PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Zero-Painter: Training-Free Layout Control for Text-to-Image Synthesis
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Prompt-Free Diffusion: Taking 'Text' out of Text-to-Image Diffusion Models
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
OpenBias: Open-set Bias Detection in Generative Models
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [Highlight]
Q-Hitter: A Better Token Oracle for Efficient LLM Inference via Sparse-Quantized KV Cache
Conference on Machine Learning and Systems (MLSys)
Fine-Tuning Language Models Using Formal Methods Feedback
Conference on Machine Learning and Systems (MLSys)
2024
Compressing LLMs: The Truth is Rarely Pure and Never Simple
International Conference on Learning Representations (ICLR)
DP-OPT: Make Large Language Model Your Differentially-Private Prompt Engineer
International Conference on Learning Representations (ICLR) [Spotlight]
Efficient-3DiM: Learning a Generalizable Single-image Novel-view Synthesizer in One Day
International Conference on Learning Representations (ICLR)
2024
Principled Architecture-aware Scaling of Hyperparameters
International Conference on Learning Representations (ICLR)
Polynomial Width is Sufficient for Set Representation with High-dimensional Features
International Conference on Learning Representations (ICLR)
2024
Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality
International Conference on Learning Representations (ICLR)
Latent 3D Graph Diffusion
International Conference on Learning Representations (ICLR)
Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community
International Conference on Learning Representations (ICLR) [Spotlight]
Safe and Robust Watermark Injection with a Single OoD Image
International Conference on Learning Representations (ICLR)
Doubly Robust Instance-Reweighted Adversarial Training
International Conference on Learning Representations (ICLR)
2024
A Multimodality Video-Based AI Biomarker for Aortic Stenosis Development and Progression
JAMA Cardiology
2024
Zero-Shot Neural Architecture Search: Challenges Solutions and Opportunities
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
Towards Long-tailed Multi-label Disease Classification from Chest X-ray
Medical Image Analysis
Harnessing the power of longitudinal medical imaging for eye disease prognosis using Transformer-based sequence modeling
npj Digital Medicine
2024
AGG: Amortized Generative 3D Gaussians for Single Image to 3D
Transactions on Machine Learning Research (TMLR)
Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK
Journal of Machine Learning Research (JMLR)
2024
Random Pruning Over-parameterized Neural Networks Can Improve Generalization: A Training Dynamics Analysis
Journal of Machine Learning Research (JMLR)
2024
Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Search
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
Artificial intelligence-guided detection of under-recognized cardiomyopathies on point-of-care cardiac ultrasound: a multi-center study
Lancet Digital Health
2024
The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter
Advances in Neural Information Processing Systems (NeurIPS)
H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
Advances in Neural Information Processing Systems (NeurIPS)
Don't Just Prune by Magnitude! Your Mask Topology is A Secret Weapon
Advances in Neural Information Processing Systems (NeurIPS)
Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling
Advances in Neural Information Processing Systems (NeurIPS)
In-Context Learning Unlocked for Diffusion Models
Advances in Neural Information Processing Systems (NeurIPS) [Spotlight]
Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models
Advances in Neural Information Processing Systems (NeurIPS)
Dynamic Sparsity Is Channel-Level Sparsity Learner
Advances in Neural Information Processing Systems (NeurIPS)
Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts
IEEE International Conference on Computer Vision (ICCV)
Physics-Driven Turbulence Image Restoration with Stochastic Refinement
IEEE International Conference on Computer Vision (ICCV)
Vision HGNN: An Image is More than a Graph of Nodes
IEEE International Conference on Computer Vision (ICCV) [Oral]
AdaMV-MoE: Adaptive Multi-Task Vision Mixture-of-Experts
IEEE International Conference on Computer Vision (ICCV)
StegaNeRF: Embedding Invisible Information within Neural Radiance Fields
IEEE International Conference on Computer Vision (ICCV)
Versatile Diffusion: Text Images and Variations All in One Diffusion Model
IEEE International Conference on Computer Vision (ICCV)
Robust Mixture-of-Expert Training for Convolutional Neural Networks
IEEE International Conference on Computer Vision (ICCV) [Oral]
Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators
IEEE International Conference on Computer Vision (ICCV) [Oral]
How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers?
Medical Image Computing and Computer Assisted Interventions (MICCAI)
No Free Lunch in Neural Architectures? A Joint Analysis of Expressivity Convergence and Generalization
International Conference on Automated Machine Learning (AutoML-Conf)
DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models
Annual Meeting of the Association for Computational Linguistics (ACL)
Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models
International Conference on Machine Learning (ICML) [Oral]
Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication
International Conference on Machine Learning (ICML)
Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?
International Conference on Machine Learning (ICML)
Data Efficient Neural Scaling Law via Model Reusing
International Conference on Machine Learning (ICML)
Outline Then Details: Syntactically Guided Coarse-To-Fine Code Generation
International Conference on Machine Learning (ICML)
Learning to Optimize Differential Games
International Conference on Machine Learning (ICML)
Are Large Kernels Better Teachers than Transformers for ConvNets?
International Conference on Machine Learning (ICML)
Lowering the Pre-training Tax for Gradient-based Subset Training: A Lightweight Distributed Pre-Training Toolkit
International Conference on Machine Learning (ICML)
Towards Constituting Mathematical Structures for Learning to Optimize
International Conference on Machine Learning (ICML)
NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360? Views
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [Highlight]
AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
MMG-Ego4D: Multimodal Generalization in Egocentric Action Recognition
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models to Learn Any Unseen Style
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Revisiting Pruning at Initialization Through the Lens of Ramanujan Graph
International Conference on Learning Representations (ICLR) [Oral]
Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!
International Conference on Learning Representations (ICLR) [Spotlight]
Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers
International Conference on Learning Representations (ICLR) [Spotlight]
Learning to Grow Pretrained Models for Efficient Transformer Training
International Conference on Learning Representations (ICLR) [Spotlight]
Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection
International Conference on Learning Representations (ICLR) [Spotlight]
More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity
International Conference on Learning Representations (ICLR)
Is Attention All That NeRF Needs?
International Conference on Learning Representations (ICLR)
NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes
International Conference on Learning Representations (ICLR)
Layer Grafted Pre-training: Bridging Contrastive Learning and Masked Image Modeling For Label-Efficient Representations
International Conference on Learning Representations (ICLR)
HotProtein: A Novel Framework for Protein Thermostability Prediction and Editing
International Conference on Learning Representations (ICLR)
Equivariant Hypergraph Diffusion Neural Operators
International Conference on Learning Representations (ICLR)
Graph Domain Adaptation via Theory-Grounded Spectral Regularization
International Conference on Learning Representations (ICLR)
M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation
International Conference on Learning Representations (ICLR)
Continuous-Discrete Convolution for (3+1)D Geometry-Sequence Modeling in Proteins
International Conference on Learning Representations (ICLR)
On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks
International Conference on Artificial Intelligence and Statistics (AISTATS)
Learning to Generalize Provably in Learning to Optimize
International Conference on Artificial Intelligence and Statistics (AISTATS)
Safeguarded Learned Convex Optimization
AAAI Conference on Artificial Intelligence (AAAI)
2023
Federated Robustness Propagation: Sharing Adversarial Robustness in Heterogeneous Federated Learning
AAAI Conference on Artificial Intelligence (AAAI)
2023
Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training
AAAI Conference on Artificial Intelligence (AAAI)
Search Behavior Prediction: A Hypergraph Perspective
ACM International Conference on Web Search and Data Mining (WSDM)
A Multi-Purpose Real Haze Benchmark with Quantifiable Haze Levels and Ground Truth
IEEE Transactions on Image Processing (TIP)
How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts
Transactions on Machine Learning Research (TMLR)
2023
Can Pruning Improve Certified Robustness of Neural Networks?
Transactions on Machine Learning Research (TMLR)
Neuro-Symbolic Computing: Advancements and Challenges in Hardware-Software Co-Design
IEEE Transactions on Circuits and Systems II (TCAS-II)
2023
You Only Transfer What You Share: Intersection-Induced Graph Transfer Learning for Link Prediction
Transactions on Machine Learning Research (TMLR)
Severe Aortic Stenosis Detection by Deep Learning Applied to Echocardiography
European Heart Journal (EHJ) [Editor's Pick]
Integrating the Traffic Science with Representation Learning for City-Wide Network Congestion Prediction
Elsevier Information Fusion
Chasing Better Deep Image Priors between Over- and Under-Parameterization
Transactions on Machine Learning Research (TMLR)
Improving Model Fairness in Image-based Computer-Aided Diagnosis
Nature Communications
CR-MoE: Consistent Routed Mixture-of-Experts for Scaling Contrastive Learning
Transactions on Machine Learning Research (TMLR)
Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained Graph Tickets
Learning on Graphs Conference (LoG) [Oral & Best Paper Award]
Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis
Advances in Neural Information Processing Systems (NeurIPS)
Signal Processing for Implicit Neural Representations
Advances in Neural Information Processing Systems (NeurIPS)
M3ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design
Advances in Neural Information Processing Systems (NeurIPS)
Back Razor: Memory-Efficient Transfer Learning by Self-Sparsified Backpropogation
Advances in Neural Information Processing Systems (NeurIPS)
Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets
Advances in Neural Information Processing Systems (NeurIPS)
Symbolic Distillation for Learned TCP Congestion Control
Advances in Neural Information Processing Systems (NeurIPS)
Old can be Gold: Better Gradient Flow can make Vanilla-GCNs Great Again
Advances in Neural Information Processing Systems (NeurIPS)
Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork
Advances in Neural Information Processing Systems (NeurIPS)
Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization
Advances in Neural Information Processing Systems (NeurIPS)
2022
Sparse Winning Tickets are Data-Efficient Image Recognizers
Advances in Neural Information Processing Systems (NeurIPS)
Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative
Advances in Neural Information Processing Systems (NeurIPS)
A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking
Advances in Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS D & B)
SinNeRF: Training Neural Radiance Field on Complex Scenes from a Single Image
European Conference on Computer Vision (ECCV)
Unified Implicit Neural Stylization
European Conference on Computer Vision (ECCV)
Scalable Learning to Optimize: A Learned Optimizer Can Train Big Models
European Conference on Computer Vision (ECCV)
Point Cloud Domain Adaptation via Masked Local 3D Structure Prediction
European Conference on Computer Vision (ECCV)
DnA: Improving Few-shot Transfer Learning with Low-Rank Decomposition and Alignment
European Conference on Computer Vision (ECCV)
Fast and High Quality Image Denoising via Malleable Convolution
European Conference on Computer Vision (ECCV)
A Simple Single-Scale Vision Transformer for Object Detection and Instance Segmentation
European Conference on Computer Vision (ECCV)
2022
Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Model
European Conference on Computer Vision (ECCV)
Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition
International Conference on Machine Learning (ICML) [Oral]
Removing Batch Normalization Boosts Adversarial Training
International Conference on Machine Learning (ICML)
Neural Implicit Dictionary Learning via Mixture-of-Expert Training
International Conference on Machine Learning (ICML)
Training Your Sparse Neural Network Better with Any Mask
International Conference on Machine Learning (ICML)
Linearity Grafting: How Neuron Pruning Helps Certifiable Robustness
International Conference on Machine Learning (ICML)
Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets
International Conference on Machine Learning (ICML)
Data-Efficient Double-Win Lottery Tickets from Robust Pre-training
International Conference on Machine Learning (ICML)
Universality of Winning Tickets: A Renormalization Group Perspective
International Conference on Machine Learning (ICML)
2022
VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian Novelty
International Conference on Machine Learning (ICML)
2022
AutoCoG: A Unified Data-Model Co-Search Framework for Graph Neural Networks
International Conference on Automated Machine Learning (AutoML-Conf)
Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent
ACM Conference on Fairness Accountability and Transparency (FAccT)
2022
The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Physically-Grounded Augmentations
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
CADTransformer: Panoptic Symbol Spotting Transformer for CAD Drawing
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [Oral]
Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
DiSparse: Disentangled Sparsification for Multitask Model Compression
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
EI-CLIP: Entity-aware Interventional Contrastive Learning for E-commerce Cross-modal Retrieval
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
2022
Symbolic Learning to Optimize: Towards Interpretability and Scalability
International Conference on Learning Representations (ICLR)
Peek-a-Boo: What (More) is Disguised in a Randomly Weighted Neural Network and How to Find It Efficiently
International Conference on Learning Representations (ICLR)
Optimizer Amalgamation
International Conference on Learning Representations (ICLR)
Sparsity Winning Twice: Better Robust Generalization from More Efficient Training
International Conference on Learning Representations (ICLR)
Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice
International Conference on Learning Representations (ICLR)
Auto-Scaling Vision Transformers without Training
International Conference on Learning Representations (ICLR)
Unified Visual Transformer Compression
International Conference on Learning Representations (ICLR)
Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot Any-Sparsity And No Retraining
International Conference on Learning Representations (ICLR) [Spotlight]
Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods
International Conference on Learning Representations (ICLR)
Audio Lottery: Speech Recognition Made Ultra-Lightweight Noise-Robust and Transferable
International Conference on Learning Representations (ICLR)
Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization
International Conference on Learning Representations (ICLR)
Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity
International Conference on Learning Representations (ICLR)
The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training
International Conference on Learning Representations (ICLR)
Bayesian Modeling and Uncertainty Quantification for Learning to Optimize: What Why and How
International Conference on Learning Representations (ICLR)
VFDS: Variational Foresight Dynamic Selection in Bayesian Neural Networks for Efficient Human Activity Recognition
International Conference on Artificial Intelligence and Statistics (AISTATS)
2022
Federated Dynamic Sparse Training: Computing Less Communicating Less Yet Learning Better
AAAI Conference on Artificial Intelligence (AAAI)
Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations
ACM International Conference on Web Search and Data Mining (WSDM)
Learning to Optimize: A Primer and A Benchmark
Journal of Machine Learning Research (JMLR)
Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
Queried Unlabeled Data Improves and Robustifies Class-Incremental Learning
Transactions on Machine Learning Research (TMLR) [Featured Certification]
Taxonomy of Machine Learning Safety: A Survey and Primer
ACM Computing Surveys (CSUR)
2022
Adversarial Feature Augmentation and Normalization for Visual Recognition
Transactions on Machine Learning Research (TMLR)
Radiomics-Guided Global-Local Transformer for Weakly Supervised Pathology Localization in Chest X-Rays
IEEE Transactions on Medical Imaging (TMI)
Can You Win Everything with A Lottery Ticket?
Transactions on Machine Learning Research (TMLR)
TransGAN: Two Pure Transformers Can Make One Strong GAN and That Can Scale Up
Advances in Neural Information Processing Systems (NeurIPS)
AugMax: Adversarial Composition of Random Augmentations for Robust Training
Advances in Neural Information Processing Systems (NeurIPS)
Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective
Advances in Neural Information Processing Systems (NeurIPS)
The Elastic Lottery Ticket Hypothesis
Advances in Neural Information Processing Systems (NeurIPS)
Chasing Sparsity in Vision Transformers: An End-to-End Exploration
Advances in Neural Information Processing Systems (NeurIPS)
Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems
Advances in Neural Information Processing Systems (NeurIPS)
You Are Caught Stealing My Winning Lottery Ticket! Making a Lottery Ticket Claim its Ownership
Advances in Neural Information Processing Systems (NeurIPS)
Improving Contrastive Learning on Imbalanced Seed Data via Open-World Sampling
Advances in Neural Information Processing Systems (NeurIPS)
Hyperparameter Tuning is All You Need for LISTA
Advances in Neural Information Processing Systems (NeurIPS)
Stronger NAS with Weaker Predictors
Advances in Neural Information Processing Systems (NeurIPS)
IA-RED2: Interpretability-Aware Redundancy Reduction for Vision Transformers
Advances in Neural Information Processing Systems (NeurIPS)
Sparse Training via Boosting Pruning Plasticity with Neuroregeneration
Advances in Neural Information Processing Systems (NeurIPS)
Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?
Advances in Neural Information Processing Systems (NeurIPS)
SSH: A Self-Supervised Framework for Image Harmonization
IEEE International Conference on Computer Vision (ICCV)
Searching for Two-Stream Models in Multivariate Space for Video Recognition
IEEE International Conference on Computer Vision (ICCV)
2021
GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization
IEEE International Conference on Computer Vision (ICCV)
2021
Graph Contrastive Learning Automated
International Conference on Machine Learning (ICML) [Oral]
Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm
International Conference on Machine Learning (ICML) [Oral]
A Unified Lottery Ticket Hypothesis for Graph Neural Networks
International Conference on Machine Learning (ICML)
Self-Damaging Contrastive Learning
International Conference on Machine Learning (ICML)
Efficient Lottery Ticket Finding: Less Data is More
International Conference on Machine Learning (ICML)
EarlyBERT: Efficient BERT Training via Early-Bird Lottery Tickets
Annual Meeting of the Association for Computational Linguistics (ACL)
Federated Adversarial Debiasing for Fair and Transferable Representations
ACM Conference on Knowledge Discovery and Data Mining (KDD)
The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Troubleshooting Blind Image Quality Models in the Wild
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Debiased Subjective Assessment of Real-World Image Enhancement
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
2021
Undistillable: Making A Nasty Teacher That CANNOT Teach Students
International Conference on Learning Representations (ICLR) [Spotlight]
Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning
International Conference on Learning Representations (ICLR)
Robust Overfitting May be Mitigated by Properly Learned Smoothening
International Conference on Learning Representations (ICLR)
Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
International Conference on Learning Representations (ICLR)
Contrastive Syn-to-Real Generalization
International Conference on Learning Representations (ICLR)
A Design Space Study for LISTA and Beyond
International Conference on Learning Representations (ICLR)
Learning A Minimax Optimizer: A Pilot Study
International Conference on Learning Representations (ICLR)
UMEC: Unified Model and Embedding Compression for Efficient Recommendation Systems
International Conference on Learning Representations (ICLR)
Learning Model-Based Privacy Protection under Budget Constraints
AAAI Conference on Artificial Intelligence (AAAI)
2021
EnlightenGAN: Deep Light Enhancement without Paired Supervision
IEEE Transactions on Image Processing (TIP) (IEEE SPS Young Author Best Paper Award, 2024)
Shape-Matching GAN++: Scale Controllable Dynamic Artistic Text Style Transfer
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
2021
Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition
International Journal of Computer Vision (IJCV)
Controllable Sketch-to-Image Translation for Robust Face Synthesis
IEEE Transactions on Image Processing (TIP)
SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training
IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
Scalable Perception-Action-Communication Loops with Convolutional and Graph Neural Networks
IEEE Transactions on Signal and Information Processing over Networks (TSIPN)
Training Stronger Baselines for Learning to Optimize
Advances in Neural Information Processing Systems (NeurIPS) [Spotlight]
Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free
Advances in Neural Information Processing Systems (NeurIPS)
The Lottery Ticket Hypothesis for Pre-trained BERT Networks
Advances in Neural Information Processing Systems (NeurIPS)
MATE: Plugging in Model Awareness to Task Embedding for Meta Learning
Advances in Neural Information Processing Systems (NeurIPS)
Robust Pre-Training by Adversarial Contrastive Learning
Advances in Neural Information Processing Systems (NeurIPS)
Graph Contrastive Learning with Augmentations
Advances in Neural Information Processing Systems (NeurIPS)
ShiftAddNet: A Hardware-Inspired Deep Network
Advances in Neural Information Processing Systems (NeurIPS)
FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training
Advances in Neural Information Processing Systems (NeurIPS)
GAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework
European Conference on Computer Vision (ECCV) [Spotlight]
Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches
European Conference on Computer Vision (ECCV)
HALO: Hardware-Aware Learning to Optimize
European Conference on Computer Vision (ECCV)
Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery
International Conference on Artificial Intelligence and Statistics (AISTATS)
2020
Automated Synthetic-to-Real Generalization
International Conference on Machine Learning (ICML)
Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training
International Conference on Machine Learning (ICML)
When Does Self-Supervision Help Graph Convolutional Networks?
International Conference on Machine Learning (ICML)
Eliminating the Invariance on the Loss Landscape of Linear Autoencoders
International Conference on Machine Learning (ICML)
2020
AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks
International Conference on Machine Learning (ICML)
NADS: Neural Architecture Distribution Search for Uncertainty Awareness
International Conference on Machine Learning (ICML)
SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation
IEEE/ACM International Symposium on Computer Architecture (ISCA)
2020
Adversarial Robustness: From Self-Supervised Pretraining to Fine-Tuning
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Peek-a-boo: Occlusion Reasoning in Indoor Scenes with Plane Representations
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [Oral]
2020
L2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Triple Wins: Boosting Accuracy Robustness and Efficiency Together by Enabling Input-Adaptive Inference
International Conference on Learning Representations (ICLR)
FasterSeg: Searching for Faster Real-time Semantic Segmentation
International Conference on Learning Representations (ICLR)
I am Going MAD: Maximum Discrepancy Competition for Comparing Classifiers Adaptively
International Conference on Learning Representations (ICLR)
Drawing Early-Bird Tickets: Toward More Efficient Training of Deep Networks
International Conference on Learning Representations (ICLR) [Spotlight]
Fractional Skipping: Toward Finer-Grained Dynamic Inference
AAAI Conference on Artificial Intelligence (AAAI)
Self-Supervised Learning for Generalizable Out-of-Distribution Detection
AAAI Conference on Artificial Intelligence (AAAI)
2020
Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New Dataset
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
Explainable Deep Relational Networks for Predicting Compound-Protein Affinities and Contacts
Journal of Chemical Information and Modeling (JCIM)
2020
A Comprehensive Benchmark Analysis of Single Image Deraining: Current Challenges and Future Perspectives
International Journal of Computer Vision (IJCV)
2020
Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study
IEEE Transactions on Image Processing (TIP)
2020
Bridging the Gap Between Computational Photography and Visual Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savings
Advances in Neural Information Processing Systems (NeurIPS)
Model Compression with Adversarial Robustness: A Unified Optimization Framework
Advances in Neural Information Processing Systems (NeurIPS)
Learning to Optimize in Swarms
Advances in Neural Information Processing Systems (NeurIPS)
Cone-Beam Computed Tomography (CBCT) Segmentation by Adversarial Learning Domain Adaptation
Medical Image Computing and Computer Assisted Interventions (MICCAI)
2019
Activity Monitoring with Uncertainty Quantification in Switching Gaussian Process Models
International Conference on Artificial Intelligence and Statistics (AISTATS)
2019
Controllable Artistic Text Style Transfer via Shape-Matching GAN
IEEE International Conference on Computer Vision (ICCV) [Oral]
Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach
IEEE International Conference on Computer Vision (ICCV)
AutoGAN: Neural Architecture Search for Generative Adversarial Networks
IEEE International Conference on Computer Vision (ICCV)
ABD-Net: Attentive but Diverse Person Re-Identification
IEEE International Conference on Computer Vision (ICCV)
DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
IEEE International Conference on Computer Vision (ICCV)
Plug-and-Play Methods Provably Converge with Properly Trained Denoisers
International Conference on Machine Learning (ICML)
Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-high Resolution Images
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [Oral]
Single Image Deraining: A Comprehensive Benchmark Analysis
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
ALISTA: Analytic Weights Are As Good As Learned Weights in LISTA
International Conference on Learning Representations (ICLR)
DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks
Oxford Bioinformatics
Benchmarking Single Image Dehazing and Beyond
IEEE Transactions on Image Processing (TIP)
Theoretical Linear Convergence of Unfolded ISTA and Its Practical Weights and Thresholds
Advances in Neural Information Processing Systems (NeurIPS) [Spotlight]
Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?
Advances in Neural Information Processing Systems (NeurIPS)
Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study
European Conference on Computer Vision (ECCV)
Subspace Network: Deep Multi-Task Censored Regression for Modeling Neurodegenerative Diseases
ACM Conference on Knowledge Discovery and Data Mining (KDD)
Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions
International Conference on Machine Learning (ICML)
No publications match these filters.